I- Introduction

II- Literature Review

III- Methodology

IV- Result

V- Conclusion

REFERENCES

Abstract

The idea has been popped up suddenly 50 years ago. Neural Computing is a separate science and is very extensive. Sample recognition problems are solved by using Neural Networks. Character Recognition is one among those. The implementation of the Neural Network is easy for obtaining the solution for this problem. Artificial Intelligence uses techniques that gives Computer the capability to learn with data and without being explicitly programmed. The neural network recognizes characters, numbers and some special symbols. The solution is obtained by using MATLAB’s Neural Network Toolbox. The accuracy of the output depends on the resolution of the input to the neural network.

INTRODUCTION

Many improvements are occurring in the area of Deep Learning. OCR is one of the active areas in where Deep Neural Network is used. Recognition of handwriting is not much difficult process for humans. It is a complicated process in case of computers. The reason is that handwriting varies between person to person and there are various characters. OCR is the fascinating area where the pattern recognition and image processing is used. The real time application of OCR includes Automatic number plate recognition, transforming the handwritten document into the structural text form, etc. The aim of OCR is to identify the digits, characters and special symbols. There are various steps which are to be carried out. They are Pre-processing, Scale region Detection, Segmentation, Classification. In this process, we can use MATLAB toolbox which help us to identify the parameters. OCR is an electronic or mechanical conversion of typed images or, printed text or handwritten into machine encoded text. It is used as data entry from the data records of the printed paper, whether passport documents, printouts of staticdata, bank statements, computerized receipts, documentation or mail.