Mouse gestural Hindi digits recognition using neural network
Dissertant
Abd al-Nasir, Maisa Muhyi al-Din
Thesis advisor
Comitee Members
al-Sadi, Jihad Ahmad
Aqil, Misbah Jumah
University
Middle East University
Faculty
Faculty of Information Technology
Department
Computer Science Department
University Country
Jordan
Degree
Master
Degree Date
2010
English Abstract
An efficient system for recognizing Hindi digits drawn by the mouse is proposed.
Our Hindi Digit Recognition using Neural Networks (HDRNN) system is designed and tested successfully.
The system deals with recognition the handwritten Hindi digits by using a Multilayer Perceptron (MLP) with one hidden layer.
The error backpropagation algorithm has been used to train the MLP network.
In addition, an analysis has been carried out to determine the number of hidden nodes to achieve high performance of backpropagation network in the recognition of handwritten Hindi digits.
The proposed system has been trained on samples of 800 images and tested on samples of 300 images written by different users selected from different ages.
An experimental result shows high accuracy of about 91% on the sample test.
Experiments showed that this approach is flexible and can achieve high recognition rate for the shapes of the digits represented in this study.
Main Subjects
Information Technology and Computer Science
No. of Pages
59
Table of Contents
Table of contents.
Abstract.
Abstract in Arabic.
Chapter One : Introduction.
Chapter Two : Literature review.
Chapter Three : Hindi digits recognition using neural network.
Chapter Four : Experimental result and discussion.
Chapter Five : Conclusion and future work.
References.
American Psychological Association (APA)
Abd al-Nasir, Maisa Muhyi al-Din. (2010). Mouse gestural Hindi digits recognition using neural network. (Master's theses Theses and Dissertations Master). Middle East University, Jordan
https://search.emarefa.net/detail/BIM-699590
Modern Language Association (MLA)
Abd al-Nasir, Maisa Muhyi al-Din. Mouse gestural Hindi digits recognition using neural network. (Master's theses Theses and Dissertations Master). Middle East University. (2010).
https://search.emarefa.net/detail/BIM-699590
American Medical Association (AMA)
Abd al-Nasir, Maisa Muhyi al-Din. (2010). Mouse gestural Hindi digits recognition using neural network. (Master's theses Theses and Dissertations Master). Middle East University, Jordan
https://search.emarefa.net/detail/BIM-699590
Language
English
Data Type
Arab Theses
Record ID
BIM-699590
