Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
Scribd Logo
Upload

Welcome to Scribd!

  • 164 views

    Project

    Uploaded by

    ayush negi
    This document discusses handwritten digit recognition using a convolutional neural network model. It begins by stating the goal is to recognize digits and potentially extend to letters and individual handwriting. Hardware and software requirements for the project are provided. The objective is to implement a classification algorithm to recognize handwritten digits from 0-9. It will evaluate different classifiers like KNN, SVM, random forest, and CNN on the MNIST dataset. The conclusion is that CNN proves more accurate than other classifiers for this task, achieving 98.72% accuracy on the test data while KNN achieved 96.67%. With more layers and neurons, CNN accuracy could be improved further for handwritten digit recognition.

    Copyright:

    © All Rights Reserved
    Download as PPTX, PDF, TXT or read online from Scribd

    Project

    Uploaded by

    ayush negi
    164 views15 pages
    This document discusses handwritten digit recognition using a convolutional neural network model. It begins by stating the goal is to recognize digits and potentially extend to letters and individual handwriting. Hardware and software requirements for the project are provided. The objective is to implement a classification algorithm to recognize handwritten digits from 0-9. It will evaluate different classifiers like KNN, SVM, random forest, and CNN on the MNIST dataset. The conclusion is that CNN proves more accurate than other classifiers for this task, achieving 98.72% accuracy on the test data while KNN achieved 96.67%. With more layers and neurons, CNN accuracy could be improved further for handwritten digit recognition.

    Original Title

    project ppt

    Copyright

    © © All Rights Reserved

    Available Formats

    PPTX, PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    This document discusses handwritten digit recognition using a convolutional neural network model. It begins by stating the goal is to recognize digits and potentially extend to letters and individual handwriting. Hardware and software requirements for the project are provided. The objective is to implement a classification algorithm to recognize handwritten digits from 0-9. It will evaluate different classifiers like KNN, SVM, random forest, and CNN on the MNIST dataset. The conclusion is that CNN proves more accurate than other classifiers for this task, achieving 98.72% accuracy on the test data while KNN achieved 96.67%. With more layers and neurons, CNN accuracy could be improved further for handwritten digit recognition.

    Copyright:

    © All Rights Reserved
    Download as PPTX, PDF, TXT or read online from Scribd
    Download as pptx, pdf, or txt
    164 views15 pages

    Project

    Uploaded by

    ayush negi
    This document discusses handwritten digit recognition using a convolutional neural network model. It begins by stating the goal is to recognize digits and potentially extend to letters and individual handwriting. Hardware and software requirements for the project are provided. The objective is to implement a classification algorithm to recognize handwritten digits from 0-9. It will evaluate different classifiers like KNN, SVM, random forest, and CNN on the MNIST dataset. The conclusion is that CNN proves more accurate than other classifiers for this task, achieving 98.72% accuracy on the test data while KNN achieved 96.67%. With more layers and neurons, CNN accuracy could be improved further for handwritten digit recognition.

    Copyright:

    © All Rights Reserved
    Download as PPTX, PDF, TXT or read online from Scribd
    Download as pptx, pdf, or txt
    of 15

    Handwritten Digit Recognition

    Problem Statement

    Though the goal is to create a model which can recognize the digits, it


    can be extended to letters and an individual's handwriting. The major
    goal of the proposed system is understanding Convolutional Neural
    Network, and applying it to the handwritten recognition system.
    What is Handwritten Digit Recognition?

    The handwritten digit recognition is the ability of computers to recognize


    human handwritten digits. It is a hard task for the machine because
    handwritten digits are not perfect and can be made with many different
    flavors. The handwritten digit recognition is the solution to this problem
    which uses the image of a digit and recognizes the digit present in the
    image.
    Requirements Specification
    HARDWARE REQUIREMENTS: -

    1. Processor 1.2ghZ or Faster


    2. RAM 4GB/8GB up to 20GB of Hard disk space for installation
    4. I/O Devices Keyboard, mouse and 1024x768 display

    SOFTWARE REQUIREMENTS: -

    1. Operating system Windows 7 and higher


    2. Python (3.7.4 used)
    3. IDE (Pycharm)
    Required frameworks are
    4. Tkinter
    5. keras.models
    6. win32gui
    7. Pillow ,PIL
    8. Numpy
    9. Tensorflow (2.5.0-rC0)
    Objective of Project
    The aim of this project is to implement
    a classification algorithm to recognize handwritten
    digits (0- 9). It has been shown in pattern recognition that
    no single classifier performs the best for all
    pattern classification problems consistently
    Data Flow Diagram
    Python Library use in Project
    Tkinter:-
    • Import the Tkinter module.
    • Create the GUI application main window.
    • Add one or more of the above-mentioned widgets to the GUI application.
    • Enter the main event loop to take action against each event triggered by the user.
    keras.models:-
    We have trained our neural network on the entire dataset and we can
    evaluate the performance of the network on the same dataset. This will only give
    us an idea of how well we have modeled the dataset (e.g. train accuracy), but no
    idea of how well the algorithm might perform on new data. We have done this
    for simplicity, but ideally, you could separate your data into train and test
    datasets for training and evaluation of your model
    Pillow(PIL):-
    Python Pillow module is built on top of PIL (Python Image Library). It is
    the essential modules for image processing in Python. But it is not supported by
    Python 3. But, we can use this module with the Python 3.x versions as PIL. It
    supports the variability of images such as jpeg, png, bmp, gif, ppm, and tiff.12 We
    can do anything on the digital images using the pillow module. In the upcoming
    section, we will learn various operations on the images such as filtering images,
    Creating thumbnail, merging images, cropping images, blur an image, resizing an
    image, creating a water mark and many other operations.
    Numpy:-
    Python NumPy arrays provide tools for integrating C, C++, etc. It is also useful
    in linear algebra, random number capability etc. NumPy array can also be used as
    an efficient multi-dimensional container for generic data. Now, let me tell you what
    exactly is a Python NumPy array
    The MNIST dataset :-

    This is probably one of the most popular datasets among machine learning and deep
    learning enthusiasts. The MNIST dataset contains 60,000 training images of handwritten
    digits from zero to nine and 10,000 images for testing. So, the MNIST dataset has 10 different
    classes. The handwritten digits images are represented as a 28×28 matrix where each cell
    contains grayscale pixel value.
    Testing Model
    Conclusion
    Handwritten digit recognition is the first step to the vast field of artificial intelligence and computer vision. As
    seen from the results of the experiment, CNN proves to be far better than other classifiers. The results can be
    made more accurate with more convolution layers and a greater number of hidden neurons In this project, the
    Handwritten Digit Recognition using Deep learning methods has been implemented. The most widely used
    Machine learning algorithms, KNN, SVM, RFC and CNN have been trained and tested on the same data in
    order acquire the comparison between the classifiers. Utilizing these deep learning techniques, a high amount
    of accuracy can be obtained. Compared to other research methods, this method focuses on which classifier
    works better by improving the accuracy of classification models by more than 99%. Using Keras as backend
    and TensorFlow as the software, a CNN model is able to give accuracy of about 98.72%. In this initial
    experiment, CNN gives an accuracy of 98.72%, while KNN gives an accuracy of 96.67%, while RFC and
    SVM are not that outstanding.

    You might also like