This document discusses a project to develop a handwritten character recognition system using a neural network. It will take handwritten English characters as input and recognize the patterns using a trained neural network. The system aims to recognize individual characters as well as classify them into groups. It will first preprocess, segment, extract features from, and then classify the input characters using the neural network. The document reviews several existing approaches to handwritten character recognition and the use of gradient and edge-based feature extraction with neural networks. It defines the objectives and methods for the proposed system, which will involve preprocessing, segmentation, feature extraction, and classification/recognition steps. Finally, it outlines the hardware and software requirements to implement the system as a MATLAB application.
On-line handwriting recognition involves converting handwriting as it is written on a digitizer to digital text, while off-line recognition converts static images of handwriting. Both techniques face challenges from variability in handwriting styles. Current methods use feature extraction and neural networks, but do not match human-level recognition abilities. Handwriting recognition remains an important but difficult area of research.
This document describes a technique for Sinhala handwritten character recognition using feature extraction and an artificial neural network. The methodology includes preprocessing, segmentation, feature extraction based on character geometry, and classification using an ANN. Features like starters, intersections, and zoning are extracted from segmented characters. The ANN was trained on these feature vectors and tested on 170 characters, achieving an accuracy of 82.1%. While the technique showed some success, the author notes room for improvement, such as making the system more font-independent and improving feature extraction and character separation.
Handwriting Recognition Using Deep Learning and Computer VersionNaiyan Noor
This document presents a method for handwriting recognition using deep learning and computer vision. It discusses preprocessing images by removing noise and converting to grayscale. Thresholding is used to separate darker text pixels from lighter background pixels. The image is then segmented into individual lines and words. Python libraries like TensorFlow, Spyder and Jupyter Notebook are used. The goal is to build a system that can recognize text in images and display the text to users. Future work may include recognizing cursive text and additional languages.
Hand gesture recognition system(FYP REPORT)Afnan Rehman
This document is a final year project report submitted by three students - Afnan Ur Rehman, Haseeb Anser Iqbal, and Anwaar Ul Haq - for their bachelor's degree in computer science. The report describes the development of a hand gesture recognition system using computer vision and machine learning techniques. Key aspects of the project include image acquisition using a webcam, preprocessing the images using techniques like filtering and noise removal, detecting and cropping the hand region, extracting HU moments features, training a classifier on sample gesture images, and classifying new images using KNN. The system is also able to translate recognized gestures to speech using text-to-speech.
A presentation on Image Recognition, the basic definition and working of Image Recognition, Edge Detection, Neural Networks, use of Convolutional Neural Network in Image Recognition, Applications, Future Scope and Conclusion
Character Recognition using Machine LearningRitwikSaurabh1
The document discusses character recognition using machine learning. It explains that historic data will be split into training and test data. An algorithm will be trained on the training data and tested on the test data. The machine is then able to predict characters with an accuracy that is verified on the test data. Digital signal processing techniques were adapted to preprocess sensor data and analyze it, with applications in national security and analyzing nuclear weapons tests.
The slide was prepared on the purpose of presentation of our project face detection highlighting the basics of theory used and project details like goal, approach. Hope it's helpful.
Sign Language Recognition based on Hands symbols ClassificationTriloki Gupta
Communication is always having a great impact in every domain and how it is considered the meaning of the thoughts and expressions that attract the researchers to bridge this gap for every living being.
The objective of this project is to identify the symbolic expression through images so that the communication gap between a normal and hearing impaired person can be easily bridged.
Github Link:https://github.com/TrilokiDA/Hand_Sign_Language
On-line handwriting recognition involves converting handwriting as it is written on a digitizer to digital text, while off-line recognition converts static images of handwriting. Both techniques face challenges from variability in handwriting styles. Current methods use feature extraction and neural networks, but do not match human-level recognition abilities. Handwriting recognition remains an important but difficult area of research.
This document describes a technique for Sinhala handwritten character recognition using feature extraction and an artificial neural network. The methodology includes preprocessing, segmentation, feature extraction based on character geometry, and classification using an ANN. Features like starters, intersections, and zoning are extracted from segmented characters. The ANN was trained on these feature vectors and tested on 170 characters, achieving an accuracy of 82.1%. While the technique showed some success, the author notes room for improvement, such as making the system more font-independent and improving feature extraction and character separation.
Handwriting Recognition Using Deep Learning and Computer VersionNaiyan Noor
This document presents a method for handwriting recognition using deep learning and computer vision. It discusses preprocessing images by removing noise and converting to grayscale. Thresholding is used to separate darker text pixels from lighter background pixels. The image is then segmented into individual lines and words. Python libraries like TensorFlow, Spyder and Jupyter Notebook are used. The goal is to build a system that can recognize text in images and display the text to users. Future work may include recognizing cursive text and additional languages.
Hand gesture recognition system(FYP REPORT)Afnan Rehman
This document is a final year project report submitted by three students - Afnan Ur Rehman, Haseeb Anser Iqbal, and Anwaar Ul Haq - for their bachelor's degree in computer science. The report describes the development of a hand gesture recognition system using computer vision and machine learning techniques. Key aspects of the project include image acquisition using a webcam, preprocessing the images using techniques like filtering and noise removal, detecting and cropping the hand region, extracting HU moments features, training a classifier on sample gesture images, and classifying new images using KNN. The system is also able to translate recognized gestures to speech using text-to-speech.
A presentation on Image Recognition, the basic definition and working of Image Recognition, Edge Detection, Neural Networks, use of Convolutional Neural Network in Image Recognition, Applications, Future Scope and Conclusion
Character Recognition using Machine LearningRitwikSaurabh1
The document discusses character recognition using machine learning. It explains that historic data will be split into training and test data. An algorithm will be trained on the training data and tested on the test data. The machine is then able to predict characters with an accuracy that is verified on the test data. Digital signal processing techniques were adapted to preprocess sensor data and analyze it, with applications in national security and analyzing nuclear weapons tests.
The slide was prepared on the purpose of presentation of our project face detection highlighting the basics of theory used and project details like goal, approach. Hope it's helpful.
Sign Language Recognition based on Hands symbols ClassificationTriloki Gupta
Communication is always having a great impact in every domain and how it is considered the meaning of the thoughts and expressions that attract the researchers to bridge this gap for every living being.
The objective of this project is to identify the symbolic expression through images so that the communication gap between a normal and hearing impaired person can be easily bridged.
Github Link:https://github.com/TrilokiDA/Hand_Sign_Language
Virtual Mouse using hand gesture recognitionMuktiKalsekar
This project is to develop a Virtual Mouse using Hand Gesture Recognition. Hand gestures are the most effortless and natural way of communication. The aim is to perform various operations of the cursor. Instead of using more expensive sensors, a simple web camera can identify the gesture and perform the action. It helps the user to interact with a computer without any physical or hardware device to control mouse operation.
After an image has been segmented into regions ; the resulting pixels is usually is represented and described in suitable form for further computer processing.
This document discusses text detection and character recognition from images. It begins with an introduction and then discusses the aims, objectives, motivation and problem statement. It reviews relevant literature on segmentation and recognition techniques. The document then describes the methodology used, including preprocessing, segmentation using vertical projections and connected components, and recognition using pixel counting, projections, template matching, Fourier descriptors and heuristic filters. It presents results from four experiments comparing different segmentation and recognition methods. The discussion analyzes results and limitations. The conclusion finds that segmentation works best with connected components while recognition works best with template matching, Fourier descriptors and heuristic filters.
Handwritten Character Recognition: A Comprehensive Review on Geometrical Anal...iosrjce
IOSR Journal of Computer Engineering (IOSR-JCE) is a double blind peer reviewed International Journal that provides rapid publication (within a month) of articles in all areas of computer engineering and its applications. The journal welcomes publications of high quality papers on theoretical developments and practical applications in computer technology. Original research papers, state-of-the-art reviews, and high quality technical notes are invited for publications.
This documentation provides a brief insight of face recognition based attendance system using neural networks in terms of product architecture which can be used for educational purpose.
Optical character recognition (OCR) is the conversion of images of typed or printed text into machine-encoded text. The document discusses OCR including defining it, describing its problem overview, types, steps in the OCR process like pre-processing and character recognition, accuracy considerations, use of free OCR software, pros and cons, and areas for further research like improving recognition of cursive text.
This document provides an overview of facial recognition technology. It discusses the history of facial recognition, how the technology works by detecting nodal points on faces and creating faceprints for identification. It also covers implementations, comparing images to templates to verify or identify individuals, and applications in security and surveillance. Strengths are its non-invasive nature, but it can be impacted by changes in appearance.
Face recognization using artificial nerual networkDharmesh Tank
This document presents an overview of face recognition using artificial neural networks. It discusses the basic concepts of face recognition, issues with existing systems, and proposes a new system using discrete cosine transform (DCT) for feature extraction and an artificial neural network with backpropagation for classification. DCT is used to extract illumination invariant features and reduce dimensionality. The neural network is trained on these features to recognize faces. Thresholding rules are also introduced to improve recognition performance. Real-time applications of face recognition like Microsoft's Project Natal are mentioned.
An Introduction to Image Processing and Artificial IntelligenceWasif Altaf
This document provides an introduction to image processing and artificial intelligence. It defines what an image is from different perspectives including in literature, general terms, and in computer science as an exact replica of a storage device. It describes image processing as analyzing and manipulating images with three main steps: importing an image, manipulating or analyzing it, and outputting the result. It also discusses what noise is in images, methods to remove noise, color enhancement techniques, sharpening images to increase contrast, and segmentation and edge detection.
The document describes an optical character recognition (OCR) system that uses a grid infrastructure to improve translation speeds of scanned documents. It discusses how OCR allows conversion of paper documents into editable electronic files. The proposed system aims to support multi-lingual character recognition by utilizing distributed processing across a grid. Key components include the scanner, OCR software, and output interface. Algorithms like Hebb's rule are used for unsupervised training of the neural network. Modules include document processing, training, recognition, editing and searching. Design diagrams show the overall system architecture and classes.
Attendance system based on face recognition using python by Raihan Sikdarraihansikdar
The document discusses face recognition technology for use in an automatic attendance system. It first defines biometrics and face recognition, explaining that face recognition identifies individuals using facial features. It then covers how face recognition systems work by detecting nodal points on faces to create unique face prints. The document proposes using such a system to take student attendance in online classes during the pandemic, noting advantages like ease of use, increased security, and cost effectiveness. It provides examples of how the system would capture images, analyze features, and recognize enrolled students to record attendance automatically.
This document summarizes a face recognition attendance system project. The project uses face recognition technology to take attendance by comparing captured images to stored student records. It has a completed status. The methodology follows a waterfall model. System diagrams include context, data flow, and architecture diagrams. The database stores student data like name, roll number, attendance, and captured images. The system allows for student registration by capturing images, training the model, and recognizing faces to mark attendance. Developing this project provided experience with real-world software development processes.
Facial Emotion Recognition: A Deep Learning approachAshwinRachha
Neural Networks lie at the apogee of Machine Learning algorithms. With a large set of data and automatic feature selection and extraction process, Convolutional Neural Networks are second to none. Neural Networks can be very effective in classification problems.
Facial Emotion Recognition is a technology that helps companies and individuals evaluate customers and optimize their products and services by most relevant and pertinent feedback.
Knowledge representation techniques face several issues including representing important attributes of objects, relationships between attributes, choosing the level of detail in representations, depicting sets of multiple objects, and determining appropriate structures as needed.
Non-monotonic reasoning allows conclusions to be retracted when new information is introduced. It is used to model plausible reasoning where defaults may be overridden. For example, it is typically true that birds fly, so we could conclude that Tweety flies since Tweety is a bird. However, if we are later told Tweety is a penguin, we would retract the conclusion that Tweety flies since penguins do not fly despite being birds. Non-monotonic reasoning resolves inconsistencies by removing conclusions derived from default rules when specific countervailing information is received.
The document proposes developing Android applications to sense emotions using smartphones for better health and human-machine interactions. It discusses detecting emotions through passive sensors like cameras, microphones, and accelerometers that can capture facial expressions, speech, heart rate without interpreting input. Recognition involves extracting meaningful patterns from sensor data using techniques like speech recognition, facial expression detection to produce labels or inference algorithms. Specific techniques are discussed for recognizing emotions from speech, facial expressions based on the Facial Action Coding System, and heart rate variability. The conclusion states that understanding emotions with smartphones can help people succeed and make research easier.
This document provides an introduction to deep learning. It defines artificial intelligence, machine learning, data science, and deep learning. Machine learning is a subfield of AI that gives machines the ability to improve performance over time without explicit human intervention. Deep learning is a subfield of machine learning that builds artificial neural networks using multiple hidden layers, like the human brain. Popular deep learning techniques include convolutional neural networks, recurrent neural networks, and autoencoders. The document discusses key components and hyperparameters of deep learning models.
This is a presentation on Handwritten Digit Recognition using Convolutional Neural Networks. Convolutional Neural Networks give better results as compared to conventional Artificial Neural Networks.
HANDWRITTEN DIGIT RECOGNITION USING k-NN CLASSIFIERvineet raj
This document proposes using a k-nearest neighbor classifier to recognize handwritten digits from the MNIST database. It discusses existing methods that use star-layered histogram feature extraction and class-dependent feature selection, which achieve accuracies of around 93% and 92% respectively. However, these methods require thinning operations or have high computational costs. The document proposes using k-NN classification with pre-processing and feature extraction to achieve higher accuracy of around 96% with lower computation requirements than existing models.
Virtual Mouse using hand gesture recognitionMuktiKalsekar
This project is to develop a Virtual Mouse using Hand Gesture Recognition. Hand gestures are the most effortless and natural way of communication. The aim is to perform various operations of the cursor. Instead of using more expensive sensors, a simple web camera can identify the gesture and perform the action. It helps the user to interact with a computer without any physical or hardware device to control mouse operation.
After an image has been segmented into regions ; the resulting pixels is usually is represented and described in suitable form for further computer processing.
This document discusses text detection and character recognition from images. It begins with an introduction and then discusses the aims, objectives, motivation and problem statement. It reviews relevant literature on segmentation and recognition techniques. The document then describes the methodology used, including preprocessing, segmentation using vertical projections and connected components, and recognition using pixel counting, projections, template matching, Fourier descriptors and heuristic filters. It presents results from four experiments comparing different segmentation and recognition methods. The discussion analyzes results and limitations. The conclusion finds that segmentation works best with connected components while recognition works best with template matching, Fourier descriptors and heuristic filters.
Handwritten Character Recognition: A Comprehensive Review on Geometrical Anal...iosrjce
IOSR Journal of Computer Engineering (IOSR-JCE) is a double blind peer reviewed International Journal that provides rapid publication (within a month) of articles in all areas of computer engineering and its applications. The journal welcomes publications of high quality papers on theoretical developments and practical applications in computer technology. Original research papers, state-of-the-art reviews, and high quality technical notes are invited for publications.
This documentation provides a brief insight of face recognition based attendance system using neural networks in terms of product architecture which can be used for educational purpose.
Optical character recognition (OCR) is the conversion of images of typed or printed text into machine-encoded text. The document discusses OCR including defining it, describing its problem overview, types, steps in the OCR process like pre-processing and character recognition, accuracy considerations, use of free OCR software, pros and cons, and areas for further research like improving recognition of cursive text.
This document provides an overview of facial recognition technology. It discusses the history of facial recognition, how the technology works by detecting nodal points on faces and creating faceprints for identification. It also covers implementations, comparing images to templates to verify or identify individuals, and applications in security and surveillance. Strengths are its non-invasive nature, but it can be impacted by changes in appearance.
Face recognization using artificial nerual networkDharmesh Tank
This document presents an overview of face recognition using artificial neural networks. It discusses the basic concepts of face recognition, issues with existing systems, and proposes a new system using discrete cosine transform (DCT) for feature extraction and an artificial neural network with backpropagation for classification. DCT is used to extract illumination invariant features and reduce dimensionality. The neural network is trained on these features to recognize faces. Thresholding rules are also introduced to improve recognition performance. Real-time applications of face recognition like Microsoft's Project Natal are mentioned.
An Introduction to Image Processing and Artificial IntelligenceWasif Altaf
This document provides an introduction to image processing and artificial intelligence. It defines what an image is from different perspectives including in literature, general terms, and in computer science as an exact replica of a storage device. It describes image processing as analyzing and manipulating images with three main steps: importing an image, manipulating or analyzing it, and outputting the result. It also discusses what noise is in images, methods to remove noise, color enhancement techniques, sharpening images to increase contrast, and segmentation and edge detection.
The document describes an optical character recognition (OCR) system that uses a grid infrastructure to improve translation speeds of scanned documents. It discusses how OCR allows conversion of paper documents into editable electronic files. The proposed system aims to support multi-lingual character recognition by utilizing distributed processing across a grid. Key components include the scanner, OCR software, and output interface. Algorithms like Hebb's rule are used for unsupervised training of the neural network. Modules include document processing, training, recognition, editing and searching. Design diagrams show the overall system architecture and classes.
Attendance system based on face recognition using python by Raihan Sikdarraihansikdar
The document discusses face recognition technology for use in an automatic attendance system. It first defines biometrics and face recognition, explaining that face recognition identifies individuals using facial features. It then covers how face recognition systems work by detecting nodal points on faces to create unique face prints. The document proposes using such a system to take student attendance in online classes during the pandemic, noting advantages like ease of use, increased security, and cost effectiveness. It provides examples of how the system would capture images, analyze features, and recognize enrolled students to record attendance automatically.
This document summarizes a face recognition attendance system project. The project uses face recognition technology to take attendance by comparing captured images to stored student records. It has a completed status. The methodology follows a waterfall model. System diagrams include context, data flow, and architecture diagrams. The database stores student data like name, roll number, attendance, and captured images. The system allows for student registration by capturing images, training the model, and recognizing faces to mark attendance. Developing this project provided experience with real-world software development processes.
Facial Emotion Recognition: A Deep Learning approachAshwinRachha
Neural Networks lie at the apogee of Machine Learning algorithms. With a large set of data and automatic feature selection and extraction process, Convolutional Neural Networks are second to none. Neural Networks can be very effective in classification problems.
Facial Emotion Recognition is a technology that helps companies and individuals evaluate customers and optimize their products and services by most relevant and pertinent feedback.
Knowledge representation techniques face several issues including representing important attributes of objects, relationships between attributes, choosing the level of detail in representations, depicting sets of multiple objects, and determining appropriate structures as needed.
Non-monotonic reasoning allows conclusions to be retracted when new information is introduced. It is used to model plausible reasoning where defaults may be overridden. For example, it is typically true that birds fly, so we could conclude that Tweety flies since Tweety is a bird. However, if we are later told Tweety is a penguin, we would retract the conclusion that Tweety flies since penguins do not fly despite being birds. Non-monotonic reasoning resolves inconsistencies by removing conclusions derived from default rules when specific countervailing information is received.
The document proposes developing Android applications to sense emotions using smartphones for better health and human-machine interactions. It discusses detecting emotions through passive sensors like cameras, microphones, and accelerometers that can capture facial expressions, speech, heart rate without interpreting input. Recognition involves extracting meaningful patterns from sensor data using techniques like speech recognition, facial expression detection to produce labels or inference algorithms. Specific techniques are discussed for recognizing emotions from speech, facial expressions based on the Facial Action Coding System, and heart rate variability. The conclusion states that understanding emotions with smartphones can help people succeed and make research easier.
This document provides an introduction to deep learning. It defines artificial intelligence, machine learning, data science, and deep learning. Machine learning is a subfield of AI that gives machines the ability to improve performance over time without explicit human intervention. Deep learning is a subfield of machine learning that builds artificial neural networks using multiple hidden layers, like the human brain. Popular deep learning techniques include convolutional neural networks, recurrent neural networks, and autoencoders. The document discusses key components and hyperparameters of deep learning models.
This is a presentation on Handwritten Digit Recognition using Convolutional Neural Networks. Convolutional Neural Networks give better results as compared to conventional Artificial Neural Networks.
HANDWRITTEN DIGIT RECOGNITION USING k-NN CLASSIFIERvineet raj
This document proposes using a k-nearest neighbor classifier to recognize handwritten digits from the MNIST database. It discusses existing methods that use star-layered histogram feature extraction and class-dependent feature selection, which achieve accuracies of around 93% and 92% respectively. However, these methods require thinning operations or have high computational costs. The document proposes using k-NN classification with pre-processing and feature extraction to achieve higher accuracy of around 96% with lower computation requirements than existing models.
Artificial Neural Network For Recognition Of Handwritten Devanagari CharacterIOSR Journals
1) The document discusses recognizing handwritten Devanagari characters using artificial neural networks and zone-based feature extraction.
2) It proposes extracting features from images by dividing them into zones and calculating average pixel distances to the image and zone centroids.
3) This zone-based feature vector is then input to a feedforward neural network for character recognition.
Neural Networks in the Wild: Handwriting RecognitionJohn Liu
Demonstration of linear and neural network classification methods for the problem of offline handwriting recognition using the NIST SD19 Dataset. Tutorial on building neural networks in Pylearn2 without YAML. iPython notebook located at nbviewer.ipython.org/github/guard0g/HandwritingRecognition/tree/master/Handwriting%20Recognition%20Workbook.ipynb
Character Recognition using Artificial Neural NetworksJaison Sabu
Mini Project, Computer Science Department, College of Engineering Chengannur 2003-2007, Affiliated to Cochin University of Science and Technology (CUSAT), Kerala, India
Artificial Neural Network / Hand written character RecognitionDr. Uday Saikia
1. Overview
2.Development of System
3.GCR Model
4.Proposed model
5.Back ground Information
6. Preprocessing
7.Architecture
8.ANN(Artificial Neural Network)
9.How the Human Brain Learns?
10.Synapse
11.The Neuron Model
12.A typical Feed-forward neural network model
13.The neural Network
14.Training of characters using neural networks
15.Regression of trained neural networks
16.Training state of neural networks
17.Graphical user interface….
The presentation will describe an algorithm through which one can recognize Devanagari Characters. Devanagari is the script in which Hindi is represented. This algorithm
could automatically segment character from the image of Devenagari text and then recognize them.
For extracting the individual characters from the image of Devanagari text, algorithm segmented the image several
times using the vertical and horizontal projection.
The algorithm starts with first segmenting the lines separately from the document by taking horizontal projection and then the line
into words by taking vertical projection of the line. Another step which is particular to the separation of
Devanagari characters was required and was done by first removing the header line by finding horizontal projection
of each word. The characters can then be extracted by vertical projection of the word without the header line.
Algorithm uses a Kohonen Neural Netowrk for the recognition task. After the separation of the characters from the
image, the image matrix was then downsampled to bring it down to a fixed size so as to make the recognition
size independent. The matrix can then be fed as input neurons to the Kohonen Neural Network and the winning neuron is
found which identifies the recognized the character. This information in Kohonen Neural Network was stored
earlier during the training phase of the neural network. For this, we first assigned random weights from input neurons
to output neurons and then for each training set, the winning neuron was calculated by finding the maximum
output produced by the neurons. The wights for this winning neuron were then adjusted so that it responds to this
pattern more strongly the next time.
The document discusses artificial intelligence and pattern recognition. It introduces various pattern recognition concepts including defining a pattern, examples of patterns in different domains, and approaches to pattern recognition. It also provides an example of using discriminative methods to classify fish into salmon and sea bass using optical sensing and extracted features.
Pattern Recognition using Artificial Neural NetworkEditor IJCATR
An artificial neural network (ANN) usually called neural network. It can be considered as a resemblance to a paradigm
which is inspired by biological nervous system. In network the signals are transmitted by the means of connections links. The links
possess an associated way which is multiplied along with the incoming signal. The output signal is obtained by applying activation to
the net input NN are one of the most exciting and challenging research areas. As ANN mature into commercial systems, they are likely
to be implemented in hardware. Their fault tolerance and reliability are therefore vital to the functioning of the system in which they
are embedded. The pattern recognition system is implemented with Back propagation network and Hopfield network to remove the
distortion from the input. The Hopfield network has high fault tolerance which supports this system to get the accurate output.
This document summarizes a student project using a neural network for character recognition. The project aims to develop software that can recognize English characters by processing input characters, training a neural network algorithm, and modifying the characters. The methodology involves 4 phases - pre-processing the image, segmenting the image into individual characters, extracting features, and performing classification and recognition using an artificial neural network. The literature review summarizes several papers on using neural networks for handwritten character recognition in various languages.
A SURVEY ON DEEP LEARNING METHOD USED FOR CHARACTER RECOGNITIONIJCIRAS Journal
The field of Artificial Intelligence is very fashionable today, especially neural networks that work well in various areas such as speech recognition and natural language processing. This Research Article briefly describes how deep learning models work and what different techniques are used in text recognition. It also describes the great progress that has been made in the field of medicine, the analysis of forensic documents, the recognition of license plates, banking, health and the legal industry. The recognition of handwritten characters is one of the research areas in the field of artificial intelligence. The individual character recognition has a higher recognition accuracy than the complete word recognition. The new method for categorizing Freeman strings is presented using four connectivity events and eight connectivity events with a deep learning approach.
Off-line English Character Recognition: A Comparative Surveyidescitation
It has been decades since the evolution of idea that
human brain can be mimicked by artificial neuron like
mathematical structures. Till date, the development of this
endeavor has not reached the threshold of excellence. Neural
networks are commonly used to solve sample-recognition
problems. One of these is character recognition. The solution
of this problem is one of the easier implementations of neural
networks. This paper presents a detailed comparative
literature survey on the research accomplished for the last
few decades. The comparative literature review will help us
understand the platform on which we stand today to achieve
the highest efficiency in terms of Character Recognition
accuracy as well as computational resource and cost.
OCR-THE 3 LAYERED APPROACH FOR CLASSIFICATION AND IDENTIFICATION OF TELUGU HA...csandit
Optical Character recognition is the method of digitalization of hand and type written or
printed text into machine-encoded form and is superfluity of the various applications of envision
of human’s life. In present human life OCR has been successfully using in finance, legal,
banking, health care and home need appliances. India is a multi cultural, literature and
traditional scripted country. Telugu is the southern Indian language, it is a syllabic language,
symbol script represents a complete syllable and formed with the conjunct mixed consonants in
their representation. Recognition of mixed conjunct consonants is critical than the normal
consonants, because of their variation in written strokes, conjunct maxing with pre and post
level of consonants. This paper proposes the layered approach methodology to recognize the
characters, conjunct consonants, mixed- conjunct consonants and expressed the efficient
classification of the hand written and printed conjunct consonants. This paper implements the
Advanced Fuzzy Logic system controller to take the text in the form of written or printed,
collected the text images from the scanned file, digital camera, Processing the Image with
Examine the high intensity of images based on the quality ration, Extract the image characters
depends on the quality then check the character orientation and alignment then to check the
character thickness, base and print ration. The input image characters can classify into the two
ways, first way represents the normal consonants and the second way represents conjunct
consonants. Digitalized image text divided into three layers, the middle layer represents normal
consonants and the top and bottom layer represents mixed conjunct consonants. Here
recognition process starts from middle layer, and then it continues to check the top and bottom
layers. The recognition process treat as conjunct consonants when it can detect any symbolic
characters in top and bottom layers of present base character otherwise treats as normal
consonants. The post processing technique applied to all three layered characters. Post
processing of the image: concentrated on the image text readability and compatibility, if the
readability is not process then repeat the process again. In this recognition process includes
slant correction, thinning, normalization, segmentation, feature extraction and classification. In
the process of development of the algorithm the pre-processing, segmentation, character
recognition and post-processing modules were discussed. The main objectives to the
development of this paper are: To develop the classification, identification of deference
prototyping for written and printed consonants, conjunct consonants and symbols based on 3
layered approaches with different measurable area by using fuzzy logic and to determine
suitable features for handwritten character recognition.
OCR-THE 3 LAYERED APPROACH FOR CLASSIFICATION AND IDENTIFICATION OF TELUGU HA...cscpconf
Optical Character recognition is the method of digitalization of hand and type written or printed text into machine-encoded form and is superfluity of the various applications of envision of human’s life. In present human life OCR has been successfully using in finance, legal, banking, health care and home need appliances. India is a multi cultural, literature and traditional scripted country. Telugu is the southern Indian language, it is a syllabic language, symbol script represents a complete syllable and formed with the conjunct mixed consonants in their representation. Recognition of mixed conjunct consonants is critical than the normal
consonants, because of their variation in written strokes, conjunct maxing with pre and post level of consonants. This paper proposes the layered approach methodology to recognize the characters, conjunct consonants, mixed- conjunct consonants and expressed the efficient classification of the hand written and printed conjunct consonants. This paper implements the Advanced Fuzzy Logic system controller to take the text in the form of written or printed, collected the text images from the scanned file, digital camera, Processing the Image with Examine the high intensity of images based on the quality ration, Extract the image characters depends on the quality then check the character orientation and alignment then to check the character thickness, base and print ration. The input image characters can classify into the two ways, first way represents the normal consonants and the second way represents conjunct consonants. Digitalized image text divided into three layers, the middle layer represents normal consonants and the top and bottom layer represents mixed conjunct consonants. Here
recognition process starts from middle layer, and then it continues to check the top and bottom layers. The recognition process treat as conjunct consonants when it can detect any symbolic characters in top and bottom layers of present base character otherwise treats as normal consonants. The post processing technique applied to all three layered characters. Post processing of the image: concentrated on the image text readability and compatibility, if the
readability is not process then repeat the process again. In this recognition process includes slant correction, thinning, normalization, segmentation, feature extraction and classification. In the process of development of the algorithm the pre-processing, segmentation, character recognition and post processing modules were discussed. The main objectives to the development of this paper are: To develop the classification, identification of deference prototyping for written and printed consonants, conjunct consonants and symbols based on 3 layered approaches with different measurable area by using fuzzy logic and to determine suitable features for handwritten character recognition.
Handwritten Digit Recognition Using CNNIRJET Journal
This document discusses a research project on handwritten digit recognition using convolutional neural networks. The project aims to build a model that can recognize handwritten digits in images using the MNIST dataset to train a convolutional neural network. Specifically, it uses Keras and TensorFlow to create a 7-layer LeNet-5 CNN model on 70,000 MNIST images. The model is trained using stochastic gradient descent and backpropagation. Once trained, the model can be used to predict handwritten digits in new images. The document provides background on handwritten digit recognition and CNNs, describes the dataset and tools used, and outlines the methodology for building the recognition model.
IOSR Journal of Computer Engineering (IOSR-JCE) is a double blind peer reviewed International Journal that provides rapid publication (within a month) of articles in all areas of computer engineering and its applications. The journal welcomes publications of high quality papers on theoretical developments and practical applications in computer technology. Original research papers, state-of-the-art reviews, and high quality technical notes are invited for publications.
1. The document discusses an optical character recognition (OCR) system that uses a neural network to recognize handwritten English characters and numerals.
2. It describes the background of OCR, including offline vs online recognition. The key steps of OCR systems are discussed as image acquisition, preprocessing, feature extraction, training and recognition, and post processing.
3. Neural networks are described as being useful for pattern recognition problems like character classification. The proposed system uses a grid infrastructure to allow multi-lingual OCR and more efficient document processing compared to other methods.
A Novel Framework For Numerical Character Recognition With Zoning Distance Fe...IJERD Editor
Advancements of Computer technology has made every organization to implement the automatic processing systems for its activities. One of the examples is the recognition of handwritten characters, which has always been a challenging task in image processing and pattern recognition. In this paper we propose Zone based features for recognition of the handwritten characters. In this zoning approach a digit image is divided into 8x8 zones and centre pixel is computed for each zone. This procedure is sequentially repeated for entire zone. Finally features are extracted for classification and recognition.
Cursive Handwriting Recognition System using Feature Extraction and Artif...IRJET Journal
The document describes a system for recognizing cursive handwriting using feature extraction and an artificial neural network. It involves preprocessing scanned images, segmenting them into individual characters, extracting features from the characters using a diagonal scanning method, and classifying the characters using a neural network. This approach provides higher recognition accuracy compared to conventional methods. The key steps are preprocessing images, segmenting into characters, extracting 54 features from each character by moving along diagonals in a grid, and training a neural network classifier on the extracted features.
Character Recognition (Devanagari Script)IJERA Editor
This document summarizes research on using neural networks for optical character recognition of Devanagari script characters. It describes preprocessing scanned images, extracting features using neural networks, and post-processing to recognize characters. The system was tested on a dataset of Devanagari characters with neural networks trained over multiple epochs. Recognition accuracy increased with larger training sets as the network learned to identify characters more precisely. The system demonstrates an effective approach for digitally recognizing handwritten Devanagari characters.
OCR-THE 3 LAYERED APPROACH FOR DECISION MAKING STATE AND IDENTIFICATION OF TE...ijaia
Optical Character recognition is the method of digitalization of hand and type written or printed text into
machine-encoded form and is superfluity of the various applications of envision of human’s life. In present
human life OCR has been successfully using in finance, legal, banking, health care and home need
appliances. India is a multi cultural, literature and traditional scripted country. Telugu is the southern
Indian language, it is a syllabic language, symbol script represents a complete syllable and formed with the
conjunct mixed consonants in their representation. Recognition of mixed conjunct consonants is critical
than the normal consonants, because of their variation in written strokes, conjunct maxing with pre and
post level of consonants. This paper proposes the layered approach methodology to recognize the
characters, conjunct consonants, mixed- conjunct consonants and expressed the efficient classification of
the hand written and printed conjunct consonants. This paper implements the Advanced Fuzzy Logic system
controller to take the text in the form of written or printed, collected the text images from the scanned file,
digital camera, Processing the Image with Examine the high intensity of images based on the quality
ration, Extract the image characters depends on the quality then check the character orientation and
alignment then to check the character thickness, base and print ration. The input image characters can
classify into the two ways, first way represents the normal consonants and the second way represents
conjunct consonants. Digitalized image text divided into three layers, the middle layer represents normal
consonants and the top and bottom layer represents mixed conjunct consonants. Here recognition process
starts from middle layer, and then it continues to check the top and bottom layers. The recognition process
treat as conjunct consonants when it can detect any symbolic characters in top and bottom layers of
present base character otherwise treats as normal consonants. The post processing technique applied to all
three layered characters. Post processing of the image: concentrated on the image text readability and
compatibility, if the readability is not process then repeat the process again. In this recognition process
includes slant correction, thinning, normalization, segmentation, feature extraction and classification. In
the process of development of the algorithm the pre-processing, segmentation, character recognition and
post-processing modules were discussed. The main objectives to the development of this paper are: To
develop the classification, identification of deference prototyping for written and printed consonants,
conjunct consonants and symbols based on 3 layered approaches with different measurable area by using
fuzzy logic and to determine suitable features for handwritten character recognition.
Offline Character Recognition Using Monte Carlo Method and Neural Networkijaia
Human Machine interface are constantly gaining improvements because of increasing development of
computer tools. Handwritten Character Recognition do have various significant applications like form
scanning, verification, validation, or checks reading. Because of the importance of these applications
passionate research in the field of Off-Line handwritten character recognition is going on. The challenge in
recognising the handwritings lies in the nature of humans, having unique styles in terms of font, contours,
etc. This paper presents a novice approach to identify the offline characters; we call it as character divider
approach which can be used after pre-processing stage. We devise an innovative approach for feature
extraction known as vector contour. We also discuss the pros and cons including limitations, of our
approach
IRJET- Hand Sign Recognition using Convolutional Neural NetworkIRJET Journal
1) The document presents a study on using a convolutional neural network (CNN) to recognize American Sign Language (ASL) alphabets captured in real-time via a webcam.
2) The researchers trained a CNN model on 1600 images of 5 ASL alphabets (E, F, I, L, V) and tested it on 320 unlabeled images, achieving a validation accuracy of 74.8%.
3) While the model showed potential, the researchers acknowledged limitations like overfitting due to the small dataset and noted areas for improvement like recognizing a broader range of ASL letters and full sentences.
This document summarizes and reviews various techniques for optical character recognition (OCR) of English text, including matrix matching, fuzzy logic, feature extraction, structural analysis, and neural networks. It discusses the structure and stages of OCR systems, including image preprocessing, segmentation, feature extraction, classification, and output. Challenges for OCR systems include degraded documents like old books, photocopies, and newspapers. The document reviews several related works on OCR and discusses techniques for English, Indian languages, license plate recognition, document binarization, and removing "bleed-through" effects from financial documents.
This document summarizes and reviews various techniques for optical character recognition (OCR) of English text, including matrix matching, fuzzy logic, feature extraction, structural analysis, and neural networks. It discusses the structure and stages of OCR systems, including image preprocessing, segmentation, feature extraction, classification, and output. Challenges for OCR systems include degraded documents like old books, photocopies, and newspapers. The document reviews several related works on OCR and discusses techniques to improve recognition of degraded text.
Understanding Neural Networks Working and Applications.pptxkcharizmacruz
Neural networks are a set of algorithms modeled after the human brain that can recognize patterns and make predictions. They are used in image and speech recognition, natural language processing, and more. A neural network consists of layers of interconnected nodes that process and transmit information, with an input layer receiving data, hidden layers processing it, and an output layer producing a prediction. Neural networks require large amounts of data to train and optimize their parameters for accuracy.
Implementation and Performance Evaluation of Neural Network for English Alpha...ijtsrd
One of the most classical applications of the Artificial Neural Network is the character recognition system. This system is the base for many different types of applications in various fields, many of which are used in daily lives. Cost effective and less time consuming, businesses, post offices, banks, security systems, and even the field of robotics employ this system as the base of their operations. For character recognition, there are many prosperous algorithms for training neural networks. Back propagation (BP) is the most popular algorithm for supervised training multilayer neural networks. In this thesis, Back propagation (BP) algorithm is implemented for the training of multilayer neural networks employing in character recognition system. The neural network architecture used in this implementation is a fully connected three layer network. The network can train over 16 characters since the 4-element output vector is used as output units. This thesis also evaluates the performance of Back propagation (BP) algorithm with various learning rates and mean square errors. MATLAB Programming language is used for implementation. Myat Thida Tun"Implementation and Performance Evaluation of Neural Network for English Alphabet Recognition System" Published in International Journal of Trend in Scientific Research and Development (ijtsrd), ISSN: 2456-6470, Volume-2 | Issue-5 , August 2018, URL: http://www.ijtsrd.com/papers/ijtsrd15863.pdf http://www.ijtsrd.com/engineering/information-technology/15863/implementation-and-performance-evaluation-of-neural-network-for-english-alphabet-recognition-system/myat-thida-tun
Similar to Hand Written Character Recognition Using Neural Networks (20)
The ColdBox Debugger module is a lightweight performance monitor and profiling tool for ColdBox applications. It can generate a friendly debugging panel on every rendered page or a dedicated visualizer to make your ColdBox application development more excellent, funnier, and greater!
DDD tales from ProductLand - NewCrafts Paris - May 2024Alberto Brandolini
Are you working on a Software Product and trying to apply Domain-Driven Design concepts?
There may be some surprises, because DDD wasn't born for that. While some ideas work like a charm, other need to be adapted to the different scenario.
Making the implicit explicit will help us uncover what will work and what won't.
India best amc service management software.Grow using amc management software which is easy, low-cost. Best pest control software, ro service software.
LIVE DEMO: CCX for CSPs, a drop-in DBaaS solutionSeveralnines
This webinar aims to equip Cloud Service Providers (CSPs) with the knowledge and tools to differentiate themselves from hyperscalers by offering a Database-as-a-Service (DBaaS) solution. The session will introduce and demonstrate CCX, a drop-in, premium DBaaS designed for rapid adoption.
Learn more about CCX for CSPs here: https://bit.ly/3VabiDr
Stork Product Overview: An AI-Powered Autonomous Delivery FleetVince Scalabrino
Imagine a world where instead of blue and brown trucks dropping parcels on our porches, a buzzing drove of drones delivered our goods. Now imagine those drones are controlled by 3 purpose-built AI designed to ensure all packages were delivered as quickly and as economically as possible That's what Stork is all about.
These are the slides of the presentation given during the Q2 2024 Virtual VictoriaMetrics Meetup. View the recording here: https://www.youtube.com/watch?v=hzlMA_Ae9_4&t=206s
Topics covered:
1. What is VictoriaLogs
Open source database for logs
● Easy to setup and operate - just a single executable with sane default configs
● Works great with both structured and plaintext logs
● Uses up to 30x less RAM and up to 15x disk space than Elasticsearch
● Provides simple yet powerful query language for logs - LogsQL
2. Improved querying HTTP API
3. Data ingestion via Syslog protocol
* Automatic parsing of Syslog fields
* Supported transports:
○ UDP
○ TCP
○ TCP+TLS
* Gzip and deflate compression support
* Ability to configure distinct TCP and UDP ports with distinct settings
* Automatic log streams with (hostname, app_name, app_id) fields
4. LogsQL improvements
● Filtering shorthands
● week_range and day_range filters
● Limiters
● Log analytics
● Data extraction and transformation
● Additional filtering
● Sorting
5. VictoriaLogs Roadmap
● Accept logs via OpenTelemetry protocol
● VMUI improvements based on HTTP querying API
● Improve Grafana plugin for VictoriaLogs -
https://github.com/VictoriaMetrics/victorialogs-datasource
● Cluster version
○ Try single-node VictoriaLogs - it can replace 30-node Elasticsearch cluster in production
● Transparent historical data migration to object storage
○ Try single-node VictoriaLogs with persistent volumes - it compresses 1TB of production logs from
Kubernetes to 20GB
● See https://docs.victoriametrics.com/victorialogs/roadmap/
Try it out: https://victoriametrics.com/products/victorialogs/
What’s new in VictoriaMetrics - Q2 2024 UpdateVictoriaMetrics
These slides were presented during the virtual VictoriaMetrics User Meetup for Q2 2024.
Topics covered:
1. VictoriaMetrics development strategy
* Prioritize bug fixing over new features
* Prioritize security, usability and reliability over new features
* Provide good practices for using existing features, as many of them are overlooked or misused by users
2. New releases in Q2
3. Updates in LTS releases
Security fixes:
● SECURITY: upgrade Go builder from Go1.22.2 to Go1.22.4
● SECURITY: upgrade base docker image (Alpine)
Bugfixes:
● vmui
● vmalert
● vmagent
● vmauth
● vmbackupmanager
4. New Features
* Support SRV URLs in vmagent, vmalert, vmauth
* vmagent: aggregation and relabeling
* vmagent: Global aggregation and relabeling
* vmagent: global aggregation and relabeling
* Stream aggregation
- Add rate_sum aggregation output
- Add rate_avg aggregation output
- Reduce the number of allocated objects in heap during deduplication and aggregation up to 5 times! The change reduces the CPU usage.
* Vultr service discovery
* vmauth: backend TLS setup
5. Let's Encrypt support
All the VictoriaMetrics Enterprise components support automatic issuing of TLS certificates for public HTTPS server via Let’s Encrypt service: https://docs.victoriametrics.com/#automatic-issuing-of-tls-certificates
6. Performance optimizations
● vmagent: reduce CPU usage when sharding among remote storage systems is enabled
● vmalert: reduce CPU usage when evaluating high number of alerting and recording rules.
● vmalert: speed up retrieving rules files from object storages by skipping unchanged objects during reloading.
7. VictoriaMetrics k8s operator
● Add new status.updateStatus field to the all objects with pods. It helps to track rollout updates properly.
● Add more context to the log messages. It must greatly improve debugging process and log quality.
● Changee error handling for reconcile. Operator sends Events into kubernetes API, if any error happened during object reconcile.
See changes at https://github.com/VictoriaMetrics/operator/releases
8. Helm charts: charts/victoria-metrics-distributed
This chart sets up multiple VictoriaMetrics cluster instances on multiple Availability Zones:
● Improved reliability
● Faster read queries
● Easy maintenance
9. Other Updates
● Dashboards and alerting rules updates
● vmui interface improvements and bugfixes
● Security updates
● Add release images built from scratch image. Such images could be more
preferable for using in environments with higher security standards
● Many minor bugfixes and improvements
● See more at https://docs.victoriametrics.com/changelog/
Also check the new VictoriaLogs PlayGround https://play-vmlogs.victoriametrics.com/
Folding Cheat Sheet #6 - sixth in a seriesPhilip Schwarz
Left and right folds and tail recursion.
Errata: there are some errors on slide 4. See here for a corrected versionsof the deck:
https://speakerdeck.com/philipschwarz/folding-cheat-sheet-number-6
https://fpilluminated.com/deck/227
Female Bangalore Call Girls 👉 7023059433 👈 Vip Escorts Service Available
Hand Written Character Recognition Using Neural Networks
1. Hand Written Character Recognition Using Neural Network
Chapter 1
1 Introduction
The purpose of this project is to take handwritten English characters as input,
process the character, train the neural network algorithm, to recognize the pattern and
modify the character to a beautified version of the input.
This project is aimed at developing software which will be helpful in recognizing
characters of English language. This project is restricted to English characters only. It
can be further developed to recognize the characters of different languages. It engulfs
the concept of neural network.
One of the primary means by which computers are endowed with humanlike abilities is
through the use of a neural network. Neural networks are particularly useful for solving
problems that cannot be expressed as a series of steps, such as recognizing patterns,
classifying them into groups, series prediction and data mining.
Pattern recognition is perhaps the most common use of neural networks. The neural
network is presented with a target vector and also a vector which contains the pattern
information, this could be an image and hand written data. The neural network then
attempts to determine if the input data matches a pattern that the neural network has
memorized.
A neural network trained for classification is designed to take input samples and classify
them into groups. These groups may be fuzzy, without clearly defined boundaries. This
project concerns detecting free handwritten characters.
1.1 Objectives
To provide an easy user interface to input the object image.
User should be able to upload the image.
System should be able to pre-process the given input to suppress the background.
System should detect text regions present in the image.
System should retrieve text present in the image and display them to the user.
2. Hand Written Character Recognition Using Neural Network
1.2 Methods
The proposed method comprises of 4 phases:
1. Pre-processing.
2. Segmentation.
3. Feature Extraction.
4. Classification and Recognition.
Figure 1.2.1: Process Flow
3. Hand Written Character Recognition Using Neural Network
Chapter 2
2 Literature Survey
A few state of the art approaches that use hand written character recognition for
text identification have been summarized here:
Handwritten Character Recognition using Neural Network
Chirag I Patel,Ripal Patel, Palak Patel.
Objective of this paper is to recognize the characters in a given scanned
documents and study the effects of changing the Models of ANN. Today Neural
Networks are mostly used for Pattern Recognition task. The paper describes the
behaviors of different Models of Neural Network used in OCR. OCR is
widespread use of Neural Network. We have considered parameters like number
of Hidden Layer, size of Hidden Layer and epochs. We have used Multilayer Feed
Forward network with Back propagation. In Preprocessing we have applied some
basic algorithms for segmentation of characters, normalizing of characters and
De-skewing. We have used different Models of Neural Network and applied the
test set on each to find the accuracy of the respective Neural Network.
Handwritten Character Recognition Using Gradient Features
AshutoshAggarwal, Rajneesh Rani, RenuDhir.
Feature extraction is an integral part of any recognition system. The aim of feature
extraction is to describe the pattern by means of minimum number of features that
are effective in discriminating pattern classes. The gradient measures the
magnitude and direction of thegreatest change in intensity in a small
neighbourhood of eachpixel. (In what follows, "gradient" refers to both
thegradient magnitude and direct ion). Gradients are computedby means of the
Sobel operator.In this paper an effort is made towards recognition of English
Characters and obtained recognition accuracy of 94%.Due to its logical simplicity,
ease of use and high recognition rate, Gradient Features should be used for
recognition purposes.
4. Hand Written Character Recognition Using Neural Network
Character Recognition Using Matlab’s Neural Network Toolbox
Kauleshwar Prasad, Devvrat C. Nigam, AshmikaLakhotiya and DheerenUmre.
Recognition of Handwritten text has been one of the active and challenging areas
of research in the field of image processing and pattern recognition. It has
numerous applications which include, reading aid for blind, bank cheques and
conversion of any hand written document into structural text form. In this paper
we focus on recognition of English alphabet in a given scanned text document
with the help of Neural Networks. Using Mat lab Neural Network toolbox, we
tried to recognize handwritten characters by projecting them on different sized
grids. The first step is image acquisition which acquires the scanned image
followed by noise filtering, smoothing and normalization of scanned image,
rendering image suitable for segmentation where image is decomposed into sub
images. Feature Extraction improves recognition rate and misclassification. We
use character extraction and edge detection algorithm for training the neural
network to classify and recognize the handwritten characters.
Neural based handwritten character recognition
Hanmandlu M, Murali Mohan K.R,Kumar H.
This paper explores the existing ring based method (W.I.Reber, 1987), the new
sector based method and the combination of these, termed the Fusion method for
the recognition of handwritten English capital letters. The variability associated
with the characters is accounted for by way of considering a fixed number of
concentric rings in the case of the ring based approach and a fixed number of
sectors in the case of the sector approach. Structural features such as end points,
junction points and the number of branches are used for the preclassification of
characters, the local features such as normalized vector lengths and angles derived
from either ring or sector approaches are used in the training using the reference
characters and subsequent recognition of the test characters. The recognition rates
obtained are encouraging.
5. Hand Written Character Recognition Using Neural Network
A feature extraction technique based on character geometry for character
recognition.
Dinesh Dileep.
This paper describes a geometry based technique forfeature extraction applicable
to segmentation-based word recognitionsystems. The proposed system extracts the
geometric features of thecharacter contour. These features are based on the basic
line typesthat form the character skeleton. The system gives a feature vectoras its
output. The feature vectors so generated from a training setwere then used to train
a pattern recognition engine based on NeuralNetworks so that the system can be
benchmarked.
A Review of Gradient-Based and Edge-Based Feature Extraction Methodsfor
Object Detection.
Sheng Wang.
In computer vision research, object detection based on image processing is the
task of identifying a designated object on a static image or a sequence of video
frames. Projects based on such research works have been widely adapted to
various industrial and social applications. The field to which those applications
apply includes but not limited to, security surveillance, intelligent transportation
nsystem, automated manufacturing, and quality control and supply chain
management. In this paper, we are going to review a few most popular computer
vision methods based on image processing and pattern recognition. Those
methods have been extensively studied in various research papers and their
significance to computer vision research has been proven by subsequent research
works. In general, we categorize those methods into to gradient-based and edge
based feature extraction methods, depending on the low level features they use. In
this paper, the definitions for gradient and edge are extended. Because an image
can also be considered as a grid of image patches, it is therefore reasonable to
incorporate the concept of granules to gradient for a review.
6. Hand Written Character Recognition Using Neural Network
Chapter 3
3 Problem Definition
The purpose of this project is to take handwritten English characters as input,
process the character, train the neural network algorithm, to recognize the pattern and
modify the character to a beautified version of the input.
This project is aimed at developing software which will be helpful in recognizing
characters of English language. This project is restricted to English characters and
numerals only. It is also helpful in recognizing special characters. It can be further
developed to recognize the characters of different languages. It engulfs the concept of
neural network.
One of the primary means by which computers are endowed with humanlike abilities is
through the use of a neural network. Neural networks are particularly useful for solving
problems that cannot be expressed as a series of steps, such as recognizing patterns,
classifying them into groups, series prediction and data mining.
Pattern recognition is perhaps the most common use of neural networks. The neural
network is presented with a target vector and also a vector which contains the pattern
information, this could be an image and hand written data. The neural network then
attempts to determine if the input data matches a pattern that the neural network has
memorized.
A neural network trained for classification is designed to take input samples and classify
them into groups. These groups may be fuzzy, without clearly defined boundaries. This
project concerns detecting free handwritten characters.
7. Hand Written Character Recognition Using Neural Network
Chapter 4
4 System Requirement Specifications
4.1 Hardware and Software Requirements
Windows
MATLAB V.13
(R2013a)
Windows7
Processor Dual core, core2duo, Intel I3
RAM 2GB RAM
DISK Space Disk space varies depending on size of partition and
installation of online help files. The MathWorks
Installer will inform you of the hard disk space
requirement for your particular partition
Graphics adapter 8-bit graphics adapter and display (for 256
simultaneous colors
CD-ROM drive for installation from CD.
Table 4.1.1: Minimum Requirements
Windows
Processor RAM DISK Space Graphics adapter
MATLAB
V.13
(R2013a)
Intel I3 2GB 1 GB for
MATLAB only,
5 GB for a
typical
installation
A 32-bit or 64-bit
OpenGL capable
graphics adapter is
strongly recommended
Table 4.1.2 Recommended Requirements
8. Hand Written Character Recognition Using Neural Network
4.2 High Level Specifications
MATLAB V.13(R2013a)
Intel Dual core or core2duo, Intel I3XP based personal computer
2GB RAM recommended
8-bit graphics adapter and display (for 256 simultaneous colors). A 32-bit or 64bit
OpenGL capable graphics adapter is strongly recommended.
4.3 Low Level Specifications
Microsoft Windows supported graphics accelerator card, printer, and sound card.
Microsoft Word 8.0 (Office 97), Office 2000.
TCP/IP is required on all platforms when using a license server.
Some license types require a license server running FLEXlm 8.0d, which is
provided by the Math Works installer.
4.4 Functional Requirements
The system should process the input given by the user only if it is an image file
(JPG, PNG etc.)
System shall show the error message to the user when the input given is not in the
required format.
System should detect characters present in the image.
System should retrieve characters present in the image and display them to the
user.
9. Hand Written Character Recognition Using Neural Network
4.5 Non Functional Requirements
Performance: Handwritten characters in the input image will be recognized with
an accuracy of about 90% and more.
Functionality: This software will deliver on the functional requirements
mentioned in this document.
Availability: This system will retrieve the handwritten text regions only if the
image contains written text in it.
Flexibility: It provides the users to load the image easily.
Learn ability: The software is very easy to use and reduces the learning work.
Reliability: This software will work reliably for low resolution images and not for
graphical images.
10. Hand Written Character Recognition Using Neural Network
Chapter 5
5 System Modeling and Design
Purpose
The purpose of this design document is to explore the logical view of
architecture design, sequence diagram, data flow diagram, user interface design of the
software for performing the operations such as pre-processing, extracting features and
displaying the text present in the images.
Scope
The scope of this design document is to achieve the features of the system such
as pre-process the images, feature extraction, segmentation and display the text present
in the image.
5.1 Block Diagram and Algorithm
The proposed methodology uses some techniques to remove the background noise,
andfeatures extraction to detect and classify the handwritten text.
The proposed method comprises of 4 phases:
1. Pre-processing.
2. Segmentation.
3. Feature Extraction.
4. Classification and Recognition.
11. Hand Written Character Recognition Using Neural Network
The block schematic diagram of the proposed model is given in Fig.5.1.1
Figure 5.1.1: Block diagram of proposed method
5.1.1 Pre-processing
The pre-processing is a series of operations performed on scanned input image. It
essentially enhances the image rendering it suitable for segmentation. The role of pre-
processing is to segment the interesting pattern from the background. Generally, noise
filtering, smoothing and normalization should be done in this step. The pre-processing also
defines a compact representation of the pattern. Binarization process converts a gray scale
image into a binary image. Dilation of edges in the binarized image is done using sobel
technique.
5.1.2 Segmentation
In the segmentation stage, an image of sequence of characters is decomposed into
sub-images of individual character. The pre-processed input image is segmented into isolated
characters by assigning a number to each character using a labelling process. This labelling
provides information about number of characters in the image. Each individual character is
uniformly resized into pixels. Normalization: Afterextracting the character we need to
normalize the size of the characters. There are large variations in the sizes of each Character
hence we need a method to normalize the size.
Pre-processing of the uploaded image
Segmentation
Features Extraction from processed
image
Classification and Recognition
Training Neural Network
12. Hand Written Character Recognition Using Neural Network
Original Image Normalized Image
Figure 5.1.2.1: Normalization of Image
Character Extraction Algorithm
1. Create a Traverse List: - List of pixels which have been already traversed.
This list is initially empty.
2. Scan row Pixel-by-Pixel.
3. Whenever we get a black pixel check whether the pixel is already in the
traverse list, if it is simply ignore and move on else apply Edge-detection
Algorithm.
4. Add the List of Pixels returned by Edge-detection Algorithm to Traverse
List.
5. Continue the steps 2 - 5 for all rows.
Edge Detection Algorithm
The Edge Detection Algorithm has a list called traverse list. It is the list of
pixel already traversed by the algorithm.
EdgeDetection(x,y,TraverseList);
1) Add the current pixel to TraverseList. The
current position of pixel is (x,y).
2) NewTraverseList= TraverseList + current
position(x,y).
If pixel at (x-1,y-1) then
Check if it is not in TraverseList.
Edgedetection(x-1,y-1,NewTraverseList);
end if
If pixel at (x-1,y) then
Check if it is not in TraverseList.
13. Hand Written Character Recognition Using Neural Network
Edgedetection(x-1,y+1,NewTraverseList);
end if
If pixel at (x,y+1) then
Check if it is not in TraverseList.
Edgedetection(x,y+1,NewTraverseList);
Endif
3)return
5.1.3 Feature Extraction
There are two techniques employed based on the efficiencies obtained, while
training the neural network. They are as follows
Feature Extraction based on Character Geometry.
Feature Extraction Using Gradient Features.
5.1.3.1 Feature Extraction Based on Character Geometry.
It extracts different line types that form a particular character. It also
concentrates on the positional features of the same. The feature extraction technique
explained was tested using a Neural Network which was trained with the feature
vectors obtained from the system proposed.
Universe of Discourse
Universe of discourse is defined as the shortest matrix that fits the entire character
skeleton. The Universe of discourse is selected because the features extracted from
the character image include the positions of different line segments in the character
image. So every character image should be independent of its Image size.
Original Image Universe of Discourse
Figure 5.1.3.1.1: Universe of Discourse
14. Hand Written Character Recognition Using Neural Network
Zoning
After the universe of discourse is selected, the image is divided into windows of equal
size, and the feature is done on individual windows. For the system implemented, two
types of zoning were used. The image was zoned into 9 equal sized windows. Feature
extraction was applied to individual zones,rather than the whole image. This gives
more information about fine details of character skeleton. Also positions of different
line segments in a character skeleton become a feature if zoning is used. This is
because, a particular line segment of a character occurs in a particular zone in almost
cases. For instance, the horizontal line segment in character ’A’ almost occurs in the
central zone of the entire character zone.
To extract different line segments in a particular zone, the entire skeleton in that zone
should be traversed. For this purpose, certain pixels in the character skeleton were
defined as starters, intersections and minor starters.
Starters
Starters are those pixels with one neighbour in the character skeleton. Before
character traversal starts, all the starters in the particular zone is found and is
populated in a list.
Figure 5.1.3.1.2: Starters are rounded
Intersections
The definition for intersections is somewhat more complicated. The necessary but
insufficient criterion for a pixel to be an intersection is that it should have more than
one neighbour. A new property called true neighbours is defined for each pixel. Based
on the number of true neighbours for a particular pixel, it is classified as an
intersection or not. For this, neighbouring pixels are classified into two categories,
Direct pixels and diagonal pixels. Direct pixels are all those pixels in the
neighbourhood of the pixel under consideration in the horizontal and vertical
directions. Diagonal pixels are the remaining pixels in the neighbourhood which are
in a diagonal direction to the pixel under consideration. Now for finding number of
15. Hand Written Character Recognition Using Neural Network
true neighbours for the pixel under consideration, it has to be classified further based
onthe number of neighbours it have in the character skeleton. Pixels under
consideration are classified as those with 3 neighbours: If any one of the direct pixels
is adjacent to anyone of the diagonal pixels, then the pixel under consideration cannot
be an intersection, else if none of the neighbouring pixels are adjacent to each other
than its an intersection. 4 neighbours: If each and every direct pixel has an adjacent
diagonal pixel or vice-versa, then the pixel under consideration cannot be considered
as an intersection. 5 or neighbours: If the pixel under consideration has five or more
neighbours, then it is always considered as an intersection once all the intersections
are identified in the image, then they are populated in a list.
Figure 5.1.3.1.3: Intersections
Minor Starters
Minor starters are found along the course of traversal along the character skeleton.
They are created when pixel under consideration have more than two neighbours.
There are two conditions that can occur Intersections: When the current pixel is an
intersection. The current line segment will end there and all the unvisited neighbours
are populated in the minor starters list. Non-intersections: Situations can occur where
the pixel under consideration has more than two neighbours but still it’s not an
intersection. In such cases, the current direction of traversal is found by using the
position of the previous pixel. If any of the unvisited pixels in the neighbourhood is in
this direction, then it is considered as the next pixel and all other pixels are populated
in the minor starters list. If none of the pixels is not in the currentdirection of
traversal, then the current segment is ended there and the entireneighbourhood are
populated in the minor starters list.
When the algorithm proposed is applied to character ’A’, in most cases, the minor
starters found are given in the image.
16. Hand Written Character Recognition Using Neural Network
Figure 5.1.3.1.4: Minor Starters
After the line type of each segment is determined, feature vector is formed based on
this information. Every zone has a feature vector corresponding to it. Under the
algorithm proposed, every zone has a feature vector with a length of 8.
The contents of each zone feature vector are:
1) Number of horizontal lines.
2) Number of vertical lines.
3) Number of Right diagonal lines.
4) Number of Left diagonal lines.
5) Normalized Length of all horizontal lines.
6) Normalized Length of all vertical lines.
7) Normalized Length of all right diagonal lines.
8) Normalized Length of all left diagonal lines.
9) Normalized Area of the Skeleton.
The number of any particular line type is normalized using the following
method,Value = 1 - ((number of lines/10) x 2).
Normalized length of any particular line type is found using the following
method,Length = (Total Pixels in that line type)/ (Total zone pixels).
The feature vector explained here is extracted individually for each zone. So if
there are N zones, there will be 9N elements in feature vector for each zone. For the
system proposed, the original image was first zoned into 9 zones by dividing the
image matrix. The features were then extracted for each zone. Again the original
image was divided into 3 zones by dividing in the horizontal direction. Then features
were extracted for each such zone.
After zonal feature extraction, certain features were extracted for the entire image
based on the regional properties namely Euler Number: It is defined as the difference
of Number of Objects and Number of holes in the image. For instance, a perfectly
drawn ’A’ would have Euler number as zero, since number of objects is 1 and number
of holes is 2, whereas ‘B’ would have Euler number as -1, since it have two holes
17. Hand Written Character Recognition Using Neural Network
Regional Area: It is defined as the ratio of the number of the pixels in the skeleton to
the total number of pixels in the image. Eccentricity: It is defined as the eccentricity
of the smallest ellipse that fits the skeleton of the image.
5.1.3.2 Gradient Feature Extraction.
The gradient measures the magnitude and direction of the greatest change in
intensity in a small neighbourhood of each pixel. (In what follows, "gradient" refers
to both the gradient magnitude and direction). Gradients are computed by means of
the Sobel operator. The Sobel templates used to compute the horizontal (X) &
vertical (Y) components of the gradient are shown in Fig.
Horizontal Component Vertical Component
Figure 5.1.3.2.1: Sobel masks for Gradient
Given an input image of size D1×D2, each pixel neighbourhood is convolved with
these templates to determine these X and Y components, Sx and Sy, respectively.
Eq. (1) and (2) represents their mathematical representation:
(1)
S (i, j) = I(i -1, j +1) + 2 * I(i, j +1) + I(i +1, j +1)
-I(i-1,j-1)-2*I(i,j-1)-I(i+1,j-1). (1)
S (i, j) = I(i -1, j -1) + 2* I(i -1, j) + I(i -1, j +1) y -I(i+1,j -1) - 2* I(i +1, j) - I(i +1,
j +1)
(2)
Here, (i, j) range over the image rows (D1) and columns (D2), respectively. The
gradient strength and direction can be computed from the gradient vector [Sx, Sy].
After obtaining gradient vector of each pixel, the gradient image is decomposed into
four orientation planes or eight direction planes (chain code directions) as shown in
18. Hand Written Character Recognition Using Neural Network
Fig.3.
Figure 5.1.3.2.2: directions of chain codes
Generation of Gradient Feature Vector
A gradient feature vector is composed of the strength of gradient accumulated
separately in different directions as described below: (1) the direction of gradient
detected as above is decomposed along 8 chain code directions. (2) The character
image is divided into 81(9 horizontal × 9 vertical) blocks. The strength of the
gradient is accumulated separately in each of 8 directions, in each block, to
produce 81 local spectra of direction. (3) The spatial resolution is reduced from 9×9
to 5×5 by down sampling every two horizontal and every two vertical blocks
with 5×5 Gaussian Filter to produce a feature vector of size 200 (5 horizontal, 5
vertical, 8 directional resolution). (5) The variable transformation (y = x0.4) is
applied to make the distribution of the features Gaussian-like. The 5 × 5 Gaussian
Filter used is the high cut filter to reduce the aliasing due to the down sampling.
5.1.4 Classification
Artificial Neural Network
Animals recognize various objects and make sense out of large amount of
visual information, apparently requiring very little effort. Simulating the task
performed by animals to recognize to the extent allowed by physical limitations will
be enormously profitable for the system. This necessitates study and simulation of
Artificial Neural Network. In Neural Network, each node perform some simple
computation and each connection conveys a signal from one node to another labelled
by a number called the “connection strength” or weight indicating the extent to which
signal is amplified or diminished by the connection.
19. Hand Written Character Recognition Using Neural Network
Different choices for weight results in different functions are being evaluated by the
network. If in a given network whose weight are initial random and given that we
know the task to be accomplished by the network , a learning algorithm must be used
to determine the values of the weight that will achieve the desired task. Learning
Algorithm qualifies the computing system to be called Artificial Neural Network. The
node function was predetermined to apply specific function on inputs imposing a
fundamental limitation on the capabilities of the network. Typical pattern recognition
systems are designed using two pass. The first pass is a feature extractor that finds
features within the data which are specific to the task being solved (e.g. finding bars
of pixels within an image for character recognition). The second pass is the classifier,
which is more general purpose and can be trained using a neural network and sample
data sets. Clearly, the feature extractor typically requires the most design effort, since
it usually must be hand-crafted based on what the application is trying to achieve.
Back propagation was created by generalizing the Widrow-Hoff learning rule to
multiple-layer networks and nonlinear differentiable transfer functions. Input vectors
and the corresponding target vectors are used to train a network until it can
approximate a function, associate input vectors with specific output vectors, or
classify input vectors in an appropriate way as defined by you. Networks with biases,
a sigmoid layer, and a linear output layer are capable of approximating any function
with a finite number of discontinuities.
Figure 5.1.4.1: Typical Neural Network
20. Hand Written Character Recognition Using Neural Network
Figure 5.1.4.2: Neural Network
Once the network is trained, the match pattern is obtained to generate the associated
character.
Sample Input Sample Output
Figure 5.1.4.3: Sample Input & Output
Output will be the beautified version of the uploaded image and will be saved in
a .doc or in text file.
5.2 Use of tools for design
Image Processing Toolbox
Image Processing Toolbox™ provides a comprehensive set of reference-standard
algorithms, functions, and apps for image processing, analysis, visualization, and algorithm
development. You can perform image enhancement, image deblurring, feature detection,
noise reduction, image segmentation, geometric transformations, and image registration.
Many toolbox functions are multithreaded to take advantage of multi core and multiprocessor
computers.
21. Hand Written Character Recognition Using Neural Network
Image Processing Toolbox supports a diverse set of image types, including high dynamic
range, giga pixel resolution, embedded ICC profile and tomography. Visualization functions
let you explore an image, examine a region of pixels, adjust the contrast, create contours or
histograms, and manipulate regions of interest (ROIs). With toolbox algorithms you can
restore degraded images, detect and measure features, analyze shapes and textures, and adjust
color balance. Image Processing Toolbox is included in MATLAB and Simulink Student
Version.
Neural Network Toolbox
Neural Network Toolbox™ provides functions and apps for modeling
complex nonlinear systems that are not easily modeled with a closed-form equation. Neural
Network Toolbox supports supervised learning with feedforward, radial basis, and dynamic
networks. It also supports unsupervised learning with self-organizing maps and competitive
layers. With the toolbox you can design, train, visualize, and simulate neural networks. You
can use Neural Network Toolbox for applications such as data fitting, pattern
recognition, clustering, time-series prediction, and dynamic system modeling and control.
Rational Rose
Rational Rose is an object-oriented Unified Modeling Language (UML) software
design tool intended for visual modeling and component construction of enterprise-level
software applications. In much the same way a theatrical director blocks out a play, a
software designer uses Rational Rose to visually create (model) the framework for an
application by blocking out classes with actors (stick figures), use case elements (ovals),
objects (rectangles) and messages/relationships (arrows) in a sequence diagram using drag-
and-drop symbols. Rational Rose documents the diagram as it is being constructed and then
generates code in the designer's choice of C++, Visual Basic, Java, Oracle8, Corba or Data
Definition Language.
22. Hand Written Character Recognition Using Neural Network
5.3 Flow Chart
Fig: 5.3.1Flow chart
Start
Read Image
Background or Noise Removal
from the images
Segment the imageIn to
different partitions
Classification of image
Feature Extraction
Using Character
Geometry
Using Gradient
Features
Extracting Characters
from the Image
Text Contained in the image will be
displayed in a text file
Stop
23. Hand Written Character Recognition Using Neural Network
5.4 UML diagrams
5.4.1 Use Case Diagram
Figure 5.4.1: Use Case Diagram
Upload Image
Cancel
User
Convert Image-Gray
ScaleInitialize
Segmentation
Recognize
Generate Output
Pre-Process Image
System
Gray Scale To Binary
format
Normalization
<<include>>
<<include>>
<<include>>
24. Hand Written Character Recognition Using Neural Network
User Module
User Case Description
Actor User
Precondition Input image should be available.
Main Scenario User uploads image.
Extension
Scenario
If the image is not compatible.
Not possible to upload file.
Post Condition Image successfully uploaded.
Figure 5.4.1.1: User module
Pre-processing Module
User Case Description
Actor System
Precondition Uploaded input image
Main
Scenario
Pre-processing is carried out by
converting the image from RGB
format to binary format.
Post
Condition
Extract characters Before
segmentation
Figure 5.4.1.2: Pre-processing module
User
Upload Image
System
Pre-process Image
25. Hand Written Character Recognition Using Neural Network
Segmentation Module
User Case Description
Actor System
Precondition Pre-processed image should be
available.
Main Scenario The pre-processed input image is
segmented into isolated characters by
assigning a number to each character
using a labeling process. This labeling
provides information about number of
characters in the image. Each
individual character is uniformly
resized into pixels.
Extension
Scenario
If the image is not compatible.
Not possible to upload file.
Post Condition Image successfully uploaded.
Figure 5.4.1.3 Segmentation module
System
segmentation
26. Hand Written Character Recognition Using Neural Network
5.4.2 Sequential Diagram
Figure 5.4.2: Sequence Diagram
: User
GUI System
1: Displays Menu
2: Load/Upload Image
3: Process Image
4: Preprocessing
5: Segmentation
6: Recognition
7: Generate Output
8: Display Output
9: Browse/Upload Image
10: Process Image
11: Error Found
12: Send Error Message
13: Display Error
27. Hand Written Character Recognition Using Neural Network
5.4.3 Activity Diagram
Figure 5.4.3: Activity Diagram
Browse/Upload
Image
Error
Found image format
not supported
Pre
Processing
Feature
Extraction
Segmentatio
n
Recognitio
n
Output Generated
in .doc file
format
accepted
28. Hand Written Character Recognition Using Neural Network
5.4.4 Architecture of the system
Figure 5.4.4: Architecture of the proposed system
5.5 Design of the User Interface
GUIDE, the MATLAB graphical user interface development environment,
provides a set of tools for creating graphical user interfaces (GUIs). These tools
simplify the process of laying out and programming GUIs.
The GUIDE Layout Editor enables you to populate a GUI by clicking and dragging
GUI components — such as buttons, text fields, sliders, axes, and so on — into the
layout area. It also enables you to create menus and context menus for the GUI.
The three main principle elements required in the creation of Graphical User Interface
are:
Components: Each item on the MATLAB GUI is a graphical component. The
types of components include graphical controls (pushbuttons, edit boxes, lists,
sliders, etc, static elements (frames and text strings),menus and axes. Axes,
which are used to display the graphical data are created using function axes.
Graphical control and static elements are created by the function uicontrol, and
menus are created by function uimenu and uicontextmenu. Axes which are
used to display graphical data are created by the function axes.
Input
Image
Pre-
Processing
Segmentation
& Clipping
Feature
Extraction
Training &
Recognition
Output
Generation
29. Hand Written Character Recognition Using Neural Network
Figures: The components of the GUI must be arranged within the figure,
which is a window on the computer screen. In the post figure have been
created automatically whenever we have plotted data. However empty figure
can be created with the function figure and can be used to hold any
combination of components.
Call back: Finally, there must be some way to perform an action if a user
click a mouse on a button or type information on a keyboard .A mouse click or
a key press is an event, and the MATALAB program must respond to each
event if the program is to perform its function .The code executed in response
to an event is called a callback. There must be a callback to implement the
function of each graphical user component on the GUI.
5.6 Risks Identified
Matlab is an interpreted language. The main disadvantage of interpreted
languages is execution speed. When a language is compiled, all of the code is
analyzed and processed efficiently, before the programmer distributes the application.
With an interpreted language, the computer running the program has to analyze and
interpret the code (through the interpreter) before it can be executed (each and every
time), resulting in slower processing performance.
The values of 39 and 35 hidden neurons for gradient features and character geometry
respectively are chosen based on experiments conducted on several different images
and are used by classifiers to produce correct classification results. The variations in
the hidden neuron values might tend to produce wrong result. Hence these values
should be carefully chosen.
30. Hand Written Character Recognition Using Neural Network
Chapter 6
6 Implementation
6.1 Software and Hardware Used
Windows 8
Processor RAM DISK Space
MATLAB
V.13
(R2013a)
Dual core,
core2duo, Intel I3
2048 MB 1 GB for MATLAB
only,5 GB for a typical
installation
Table 6.1.1: Software and Hardware Used
6.2 Software Development Platform/Environment/framework
MATLAB is a high-performance language for technical computing. It
integrates computation, visualization, and programming in an easy-to-use
environment where problems and solutions are expressed in familiar
mathematical notation.
The name MATLAB stands for matrix laboratory. MATLAB was originally
written to provide easy access to matrix software developed by the LINPACK
and EISPACK projects, which together represent the state-of-the-art in
software for matrix computation.
6.2.1 The MATLAB language
This is a high-level matrix/array language with control flow statements,
functions, data structures, input/output, and object-oriented programming features. It
allows both "programming in the small" to rapidly create quick and dirty throw-away
programs, and "programming in the large" to create complete large and complex
application programs.
31. Hand Written Character Recognition Using Neural Network
6.2.2 The MATLAB working environment
This is the set of tools and facilities that you work with as the MATLAB user
or programmer. It includes facilities for managing the variables in your workspace
and importing and exporting data. It also includes tools for developing, managing,
debugging, and profiling M-files, MATLAB's applications.
6.2.3 MATLAB Image Processing Toolbox
We have used MATLAB Image Processing Toolbox for the development of
this software. Image processing involves changing the nature of an image in order to
improve pictorial information of the image for human interpretation for autonomous
human perception. The Image Processing Toolbox is a collection of functions that
extend the capability of the MATLAB numeric computing environment. The toolbox
supports a wide range of operations on the image.
Key Features
Image enhancement, including filtering, filters design, deblurring and contrast
enhancement.
Image analysis including features detection, morphology, segmentation, and
measurement.
Spatial transformations and image registration.
Support for multidimensional image processing.
Support for ICC version 4 color management system.
Modular interactive tools including ROI selection, histograms and distance
measurements.
Interactive image and video display.
DICOM import and export.
32. Hand Written Character Recognition Using Neural Network
6.2.4 MATLAB Neural Network Toolbox
Key Features
Supervised networks, including multilayer, radial basis, learning vector
quantization (LVQ), time-delay, nonlinear autoregressive (NARX), and layer-
recurrent
Unsupervised networks, including self-organizing maps and competitive
layers
Apps for data-fitting, pattern recognition, and clustering
Parallel computing and GPU support for accelerating training (using Parallel
Computing Toolbox)
Preprocessing and postprocessing for improving the efficiency of network
training and assessing network performance
Modular network representation for managing and visualizing networks of
arbitrary size
Simulink® blocks for building and evaluating neural networks and for control
systems applications
6.2.5 Working of the Front End
When you save your GUI layout, GUIDE automatically generates an M-file
that you can use to control how the GUI works. This M-file provides code to initialize
the GUI and contains a framework for the GUI callbacks the routines that execute in
response to user-generated events such as a mouse click. Using the M-file editor, you
can add code to the callbacks to perform the functions you want.
Home Page
1. The system displays the Home page with some options.
2. The user will browse for the input image.
3. User clicks on LOAD IMAGE Button to upload the image.
Processing Module
1. This GUI will receive the query image.
2. Displays the noiseless image of the uploaded image.
33. Hand Written Character Recognition Using Neural Network
3. The characters are extracted from the image and displayed.
4. Output will be displayed in a .txt /.doc file.
6.3 Screen Shots of the Front End
Home Page
Figure 6.3.1: Home Page
Uploaded Image
Figure 6.3.2: Uploading Image
34. Hand Written Character Recognition Using Neural Network
Neural Network Training
Figure 6.3.3: Neural Network Training
35. Hand Written Character Recognition Using Neural Network
Character Extraction
Figure 6.3.4: Extracting Characters
Output File
Figure 6.3.5: Output File
36. Hand Written Character Recognition Using Neural Network
6.4 Snapshot and description of Experimental Set up
Requirements
- An internet connection
- A DVD reader Or ISO file
- Matlab media – DVD
- Matlab serial number
1. Load the DVD into the PC you want to install Matlab onto. The DVD should
Automatically start the installation program whereby you will see the first splash
screen.
Figure 6.4.1: setup 1
37. Hand Written Character Recognition Using Neural Network
2. You need to agree to the Math works license.
Figure 6.4.2: setup 2
3. Choose the ‘Typical’ installation
Figure 6.4.3: setup 3
38. Hand Written Character Recognition Using Neural Network
4. Choose the location of the installation.
Figure 6.4.4: setup 4
5. Confirm the installation settings by pressing Install
Figure 6.4.5: setup 5
39. Hand Written Character Recognition Using Neural Network
7. Matlab will now install, this may take several minutes
Figure 6.4.6: setup 6
8. After the installation has completed, you then need to license your install.
Figure 6.4.7: setup 7
You need to have the serial number ready. This number can be located on the DVD
case.
40. Hand Written Character Recognition Using Neural Network
9. Matlab will initially make an internet connection the Mathworks prior to you
entering the serial number.
Figure 6.4.8: setup 8
12. Enter the serial number and your @cam email address e.g. ab123@cam.ac.ukand
Continue with the rest of the registration process then below figure will appear.
Figure 6.4.9: setup 9
41. Hand Written Character Recognition Using Neural Network
Chapter 7
7 Testing
7.1 Verification
The set of Test Cases are used to test the functionality of each module if that
module works properly then that Test Cases marked as Pass or else Fail.
Test Id. Test Case Input Description Expected
Output
Test Status
1 Uploading
Image
When user clicks
on open button
open field box will
be opened to select
the image file
Image file
should be
selected and
uploaded
Pass
2 To
preprocess
images
Image will be taken
for preprocessing
Conversion
from RGB to
B/W image
(Binarization)
Pass
3 Feature
extraction
A Gray Scale
Image
Character
features
should be
extracted
Pass
4 Output file Normalized
character to the
neural network
file
containing
only the text
Pass
Table 7.1: Verification
42. Hand Written Character Recognition Using Neural Network
7.2 Validation
The below table is used to determine whether or not a system satisfies the
acceptance criteria and to determine whether or not to accept the system.
SI
no
Functions Required Output Actual Output
1 Upload the image with
valid format
Image should be uploaded
if supported
Valid image is
uploaded successfully
2 Invalid image format Error message should be
displayed
Error message is
displayed if the image
format is not supported
3 Pre-processing of the
uploaded image
Image should be pre-
processed in order to
convert to Gray scale
Image is preprocessed
4 Extraction of features Character features such as
edges and curves are
calculated
Image features are
extracted
5 Displaying result Text of the file displayed Text contained in the
file is displayed
Table 7.2: Validation
7.3 Failure modes and action on failure
SlNo. Event Action
1.
Wrong input file uploaded
Error message should be
displayed to the user and
home screen must be
displayed
2 System shut down Tasks should be canceled
and process should be
restarted again
Table 7.3: Failure modes of system
44. Hand Written Character Recognition Using Neural Network
7.4 Evaluation
The Handwritten Character Recognition system was tested on several different
scanned images containing handwritten textwritten with different styles and the
results were highly encouraging.
The proposed method performs preprocessing on the image for removing the noise
and further uses feature extraction using gradient technique OR using character
geometry which gives relatively good classification compared to OCR.
The method is advantageous as it uses nine features to train the neural network using
character geometry and twelve features using gradient technique. The advantage lies
in less computation involved in feature extraction, training and classification phases
of the method.
The proposed methodology has produced good results for images containing
handwritten text written in different styles, different size and alignment with varying
background. It classifies most of the handwritten characters correctly if the image
contains less noise in the characters and also in the background. Characters written
with legible handwriting are classified more accurately.
45. Hand Written Character Recognition Using Neural Network
Chapter 8
8 Conclusion
8.1 Summary of work done
The effectiveness of the method that uses feature extraction using character geometry
and gradient technique from scanned images containing handwritten characters is
presented.
The feature extraction methodshave performed well in classification when fed to the
neural network and preprocessing of image using edge detection and normalization
are the ideal choice for degraded noisy images.
The method of training neural network with extracted features from sample imagesof
each character has detection accuracy to a greater extent.
The proposed methodology has produced good results for images containing
handwritten text written in different styles, different size and alignment with varying
background
The system is developed in MATLAB and evaluated for a set of sample images
containing handwritten texton Intel dual core computer.
The method is advantageous as it uses nine features to train the neural network using
character geometry and twelve features using gradient technique.
8.2 Proposal for enhancement or re-design
As the feature extraction methods such as gradient technique and character
geometryused in the method does not classify characters of different language, the
method can be extended for language independent classification from the images of
other languages with little modifications. The performance of the method has been
tested for classifying English text written in upper case, but needs further
exploration.
Refinement of the segmented characters can be done in order to achieve higher
accuracy rate.
The performance of the neural network can be increased by adding some more
features other than the existing ones.
46. Hand Written Character Recognition Using Neural Network
The classification rate can be increased by training the neural network with more
number of test images.
References
[1] Chirag I Patel, Ripal Patel, Palak Patel, “Handwritten Character Recognition Using
Neural Networks”, International Journal of Scientific & Engineering Research
Volume 2, Issue 5, May-2011.
[2] Kauleshwar Prasad, Devvrat C Nigam, AshmikaLakhotiya, DheerenUmre,
“Character Recognition Using Matlab’s Neural Toolbox”, International Journal of
u- and e- Service, Science and Technology Vol. 6, No. 1, February, 2013.
[3] AshutoshAggarwal, Rajneesh Rani, RenuDhir, ”Handwritten Character Recognition
Using Gradient Features”, International Journal of Advanced Research in Computer
Science and Software Engineering, Volume 2, Issue 5, May 2012.
[4] Vinita Dutt, Sunil Dutt, “Handwritten Character Recognition Using Artificial
Neural Network”, Advances in Computing: 2011; 1(1): 18-23.
[5] Rahul Kala, Harsh Vazirani, AnupamShukla, RituTiwari, “Offline Handwriting
Recognition”, International Journal of Computer Science issues, volume 7, March-
2010.
[6] Dinesh Dileep, “A Feature Extraction Technique Based on Character Geometry for
Character Recognition”.
[7] Alexander J. Faaborg, “Using Neural Networks to Create an Adaptive Character
Recognition System”, Cornell University, Ithaca NY, (May 14, 2002)
[8] Swapnil A. Vaidya, Balaji R. Bombade “A Novel Approach of Handwritten
Character Recognition using Positional Feature Extraction”,IJCSMC, Vol. 2, Issue.
6, June 2013.
[9] Sheng Wang “A Review of Gradient-Based and Edge-Based Feature Extraction
Methods for Object Detection”,Computer and Information Technology (CIT), 2011
IEEE 11th International Conference.
47. Hand Written Character Recognition Using Neural Network
Glossary
ANN
Artificial neural networks (ANNs) are
computational models inspired by an animal's
central nervous systems(in particular the
brain) which is capable of machine learning
as well as pattern recognition. Artificial
neural networks are generally presented as
systems of interconnected "neurons" which
can compute values from inputs.
Binary image This image format also stores an image as a
matrix but can only color a pixel black or
white (and nothing in between). It assigns a 0
for black and a 1 for white.
Contrast The difference in color and light between
parts of an image
Image processing Transforming digital information
representing images
Segmentation Image segmentation is the process of dividing
an image into multiple parts. This is typically
used to identify objects or other relevant
information in digital images
Noise Image noise is random (not present in the
object imaged) variation of brightness or
color information in images, and is usually an
aspect of electronic noise. Image noise is an
undesirable by-product of image capture that
adds spurious and extraneous information.
Gray scale image A gray scale or grey scale digital image is an
image in which the value of each pixel is a
single sample, that is, it carries only intensity
information. Images of this sort, also known
as black-and-white, are composed
exclusively of shades of gray, varying from
black at the weakest intensity to white at the
strongest