Gaurav Y. Tawde Int. Journal of Engineering Research and Applications www.ijera.com ISSN : 2248-9622, Vol. 4, Issue 2( Version 1), February 2014, pp.605-611 www.ijera.com 605 | Page Optical Character Recognition for Isolated Offline Handwritten Devanagari Numerals Using Wavelets Gaurav Y. Tawde Dept. of Electronics and Telecommunication Engineering, St. Francis Institute of Technology, Mumbai University Abstract 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. Keywords—back propagation algorithm, classifier, multiple resolution, multilayer perceptron, optical character recognition, pattern recognition, pre-processing, wavelet decomposition I. INTRODUCTION 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 like postal pin code sorting, bank cheque processing, job application form processing, vehicle number plate recognition, tax forms processing, digit recognition. A lot of research work has been done in this field considering the scope of the area. In the literature, various approaches are available for implementation of pre-processing, feature extraction and classification. G. S. Lehal and Nivedan Bhatt [1] have proposed a contour extraction technique. Reena Bajaj [2] have used three different types of feature namely, density features, moment features and descriptive features for classification of Devanagari Numerals. R. J. Ramteke [3] has presented a method based on invariant moments and the divisions of image for the recognition of numerals. U. Bhattacharya [4] have used a combination of Artificial Neural Network (ANN) and Hidden Markov Model (HMM) classifier. In this paper, a method of recognizing offline handwritten Devanagari numeral using Daubechies-4 wavelet filter and multilayer perceptron neural network classifier is presented. The method is capable of providing recognition accuracy of about 60%-70%. The rest of the paper is organized as follows: Section II describes the classification of character recognition techniques; section III describes the general steps in OCR. The proposed scheme for handwritten numeral recognition and experimental results are presented in section IV. Section V then presents some concluding remarks. II. CLASSIFICATION OF CHARACTER RECOGNITION TECHNIQUES The system for character recognition can be examined in following two categories:  Systems classified according to the data acquisition techniques i. On-line character recognition systems ii. Off-line character recognition systems  Systems classified according to the text type i. Printed character recognition ii. Handwritten character recognition Handwriting recognition (or HWR) is the ability of a computer to receive and interpret intelligible handwritten input from sources such as paper documents, photographs, touch-screens and other devices. The domain of handwritten character recognition is divided into following two types:  On-line Handwritten Recognition  Off-line Handwritten Recognition A historical review of OCR research and development is presented [5]. On-line handwriting recognition-On-line handwriting recognition involves the automatic conversion of text as it is written on a special digitizer or PDA, where a sensor picks up the pen-tip movements as well as pen-up/pen-down switching. This kind of data is known as digital ink and can be regarded as a dynamic representation of handwriting. The obtained signal is converted into letter codes that are usable within computer and text-processing applications. RESEARCH ARTICLE OPEN ACCESS