ABSTRACT
Neural Network Based Character Pattern Identification System has been one of the active and challenging research areas in the field of data computing, image processing and pattern recognition. It has numerous applications that includes, reading aid for blind, bank cheques and conversion of any hand written document into structural text form et cetera. Neural Network (NN) with its inherent learning ability offers promising solutions for handwritten character identification and recognition. This research work identifies the most suitable NN for the design and implementation of the subject matter. Different Neural Network (NN) topologies namely, back propagation neural network, nearest neighbour network and radial basis function network are built to classify the characters. As evident from the contents and disclosures of this work, all the NN based identification and recognition systems use the same training data set and are trained for the same purpose of speedy and accurate data computation through faultless or nearly faultless character identification and processing.
Not forgetting, during the course of this work, the terms "character identification" and "character recognition" were used interchangeably in many cases since the words have the same meaning giving the topic of this project.

TABLE OF CONTENTS
TITLE PAGE                                   
CERTIFICATION                               
APPROVAL                               
DEDICATION                                   
ACKNOWLEDGEMENT                       
ABSTRACT                                   
TABLE OF CONTENT