Optical Character Recognition (OCR) is an interesting and challenging field of research in patter... more Optical Character Recognition (OCR) is an interesting and challenging field of research in pattern recognition, artificial intelligence and machine vision and is used in many real life applications. Optical character recognition is a type of document analysis where a scanned document image that contains either machine printed or handwritten script is input to an OCR software engine, is translated into editable, machine-readable digital text format. With the spread of computers in public and private sectors and individual homes, automatic processing of tabular application forms, bank cheques, tax forms, census forms and postal mails has gained importance. Such automation needs research and development of handwritten characters/numerals recognition for different languages or scripts. The field of OCR is divided into two parts, one is recognition of machine printed characters and the second is recognition of handwritten characters. Recognizing handwritten text is an important area of r...
International Journal of Advance Research, Ideas and Innovations in Technology, 2018
Unmanned Aerial Vehicles (UAVs) have been gaining a lot of impetus in the recent times. Drones ar... more Unmanned Aerial Vehicles (UAVs) have been gaining a lot of impetus in the recent times. Drones are constantly being made available for a myriad of day-to-day applications like food delivery, surveillance, farming, etc. One of the most overshadowed regions in the list of applications remains to mine. Mining is a dangerous activity and more often than not, there are certain unknown hazards to it that are too dangerous for humans to be experimenting with all by themselves. Hence it makes sense to use a UAV in the form of a First-Person View (FPV) drone. For the development of a UAV, there are thousands of different permutations that can be used. After a detailed analysis of various of them ranging from a simple tri-copter to an octocopter, a quadcopter design was unanimously selected as it provides elegant support in the form of control, structure, reliability, cost, size, etc. Most important of them being size and structure. Mines can be constricting places and a wide frame may become...
Journal of emerging technologies and innovative research, 2019
Home security is a growing field. To provide security to home, face recognition system can be imp... more Home security is a growing field. To provide security to home, face recognition system can be implemented using different image processing methods. A standard USB camera captures the image to identify the person. It is a system that identifies the visitor. If the door recognizes the visitor, it will greet them by name, and door will be unlocked and opened. If they are not identified the door will remain locked. The system will perform the detection and recognition rapidly in real time. This project adds mainly four features: security, safety, control and monitoring to home automation. Firstly the system needs a face authentication for the user to be able to enter the home (locked/unlocked). When an unauthenticated person tries to log in, the face will be captured and would be sent to owner via Gmail as an attachment. The system also supports remote home control. Keywords— Face Recognition, Image processing, IOT, Raspberry Pi, Pi Camera
This paper presents a method of recognition of isolated offline handwritten Devanagari numerals u... more This paper presents a method of recognition of isolated offline handwritten Devanagari numerals using wavelets and neural network classifier. This method of optical character recognition takes the handwritten numeral image as input. After pre-processing, it is subjected to single level wavelet decomposition using Daubechies-4 wavelet filter. This wavelet decomposition allows viewing the input numeral at multiple resolutions. The Low-Low band components are used as inputs to multilayer perceptron (MLP) classifier. The feed forward back propagation algorithm is used for classification of the input numeral.
Unmanned Aerial Vehicles (UAVs) have been gaining a lot of impetus in the recent times. Drones ar... more Unmanned Aerial Vehicles (UAVs) have been gaining a lot of impetus in the recent times. Drones are constantly being made available for a myriad of day-today applications like food delivery, surveillance, farming, etc. One of the most overshadowed regions in the list of applications remains to mine. Mining is a dangerous activity and more often than not, there are certain unknown hazards to it that are too dangerous for humans to be experimenting with all by themselves. Hence it makes sense to use a UAV in the form of a First-Person View (FPV) drone. For the development of a UAV, there are thousands of different permutations that can be used. After a detailed analysis of various of them ranging from a simple tri-copter to an octocopter, a quadcopter design was unanimously selected as it provides elegant support in the form of control, structure, reliability, cost, size, etc. Most important of them being size and structure. Mines can be constricting places and a wide frame may become very difficult to control inside such enclosures. This project has been implemented on a much smaller scale than an actual prototype, primarily because of an ambitious development schedule coupled with a very limited budget. These constraints have forced a compromise on the quality of the components used but have not tampered with the real application objectives that the drone has to suffice. The drone at present is being controlled by a remote-control transmitter, receiver couple but we are working on creating our own GUI which will provide a direct control over all the systems from a remote laptop or android device.
Optical Character Recognition (OCR) is an interesting and challenging field of research in patter... more Optical Character Recognition (OCR) is an interesting and challenging field of research in pattern recognition, artificial intelligence and machine vision and is used in many real life applications. Optical character recognition is a type of document analysis where a scanned document image that contains either machine printed or handwritten script is input to an OCR software engine, is translated into editable, machine-readable digital text format. With the spread of computers in public and private sectors and individual homes, automatic processing of tabular application forms, bank cheques, tax forms, census forms and postal mails has gained importance. Such automation needs research and development of handwritten characters/numerals recognition for different languages or scripts. The field of OCR is divided into two parts, one is recognition of machine printed characters and the second is recognition of handwritten characters. Recognizing handwritten text is an important area of r...
International Journal of Advance Research, Ideas and Innovations in Technology, 2018
Unmanned Aerial Vehicles (UAVs) have been gaining a lot of impetus in the recent times. Drones ar... more Unmanned Aerial Vehicles (UAVs) have been gaining a lot of impetus in the recent times. Drones are constantly being made available for a myriad of day-to-day applications like food delivery, surveillance, farming, etc. One of the most overshadowed regions in the list of applications remains to mine. Mining is a dangerous activity and more often than not, there are certain unknown hazards to it that are too dangerous for humans to be experimenting with all by themselves. Hence it makes sense to use a UAV in the form of a First-Person View (FPV) drone. For the development of a UAV, there are thousands of different permutations that can be used. After a detailed analysis of various of them ranging from a simple tri-copter to an octocopter, a quadcopter design was unanimously selected as it provides elegant support in the form of control, structure, reliability, cost, size, etc. Most important of them being size and structure. Mines can be constricting places and a wide frame may become...
Journal of emerging technologies and innovative research, 2019
Home security is a growing field. To provide security to home, face recognition system can be imp... more Home security is a growing field. To provide security to home, face recognition system can be implemented using different image processing methods. A standard USB camera captures the image to identify the person. It is a system that identifies the visitor. If the door recognizes the visitor, it will greet them by name, and door will be unlocked and opened. If they are not identified the door will remain locked. The system will perform the detection and recognition rapidly in real time. This project adds mainly four features: security, safety, control and monitoring to home automation. Firstly the system needs a face authentication for the user to be able to enter the home (locked/unlocked). When an unauthenticated person tries to log in, the face will be captured and would be sent to owner via Gmail as an attachment. The system also supports remote home control. Keywords— Face Recognition, Image processing, IOT, Raspberry Pi, Pi Camera
This paper presents a method of recognition of isolated offline handwritten Devanagari numerals u... more This paper presents a method of recognition of isolated offline handwritten Devanagari numerals using wavelets and neural network classifier. This method of optical character recognition takes the handwritten numeral image as input. After pre-processing, it is subjected to single level wavelet decomposition using Daubechies-4 wavelet filter. This wavelet decomposition allows viewing the input numeral at multiple resolutions. The Low-Low band components are used as inputs to multilayer perceptron (MLP) classifier. The feed forward back propagation algorithm is used for classification of the input numeral.
Unmanned Aerial Vehicles (UAVs) have been gaining a lot of impetus in the recent times. Drones ar... more Unmanned Aerial Vehicles (UAVs) have been gaining a lot of impetus in the recent times. Drones are constantly being made available for a myriad of day-today applications like food delivery, surveillance, farming, etc. One of the most overshadowed regions in the list of applications remains to mine. Mining is a dangerous activity and more often than not, there are certain unknown hazards to it that are too dangerous for humans to be experimenting with all by themselves. Hence it makes sense to use a UAV in the form of a First-Person View (FPV) drone. For the development of a UAV, there are thousands of different permutations that can be used. After a detailed analysis of various of them ranging from a simple tri-copter to an octocopter, a quadcopter design was unanimously selected as it provides elegant support in the form of control, structure, reliability, cost, size, etc. Most important of them being size and structure. Mines can be constricting places and a wide frame may become very difficult to control inside such enclosures. This project has been implemented on a much smaller scale than an actual prototype, primarily because of an ambitious development schedule coupled with a very limited budget. These constraints have forced a compromise on the quality of the components used but have not tampered with the real application objectives that the drone has to suffice. The drone at present is being controlled by a remote-control transmitter, receiver couple but we are working on creating our own GUI which will provide a direct control over all the systems from a remote laptop or android device.
Uploads
Papers by Gaurav Tawde