Isolated Handwritten Digit Recognition using Adaptive Unsupervised Incremental Learning Technique

Abstract

paper presents a new approach to off-line handwritten numeral recognition. From the concept of perturbation due to writing habits and instruments, we propose a recognition method which is able to account for a variety of distortions due to eccentric handwriting. The recognition of handwritten numerals is a challenging task in the field of image processing and pattern recognition. It can be considered as one of the benchmarks in evaluating feature extraction methods and the performance of classifiers. The performance of character recognition system depends heavily on what kind of features are being used. The objective of this paper is to provide efficient and reliable techniques for recognition of handwritten numerals. In this paper we propose Zoning based feature extraction system which calculates the densities of object pixels in each zone. Firstly the whole image is divided into 4 4 zones. Further in order to gain more accuracy these zones are divided into 6 6 zones. The division of zones carried out up to 8 8 zones. Hence 116 features are extracted in all. Nearest neighbour classifier is used for subsequent classification and recognition purpose. For the testing purpose an Award List has been used. Data has been collected from 200 users and extracted individual digits from these forms. These forms are filled out from different users in order to take different samples of handwriting. This Award List has 4-digit Roll no, 4-digit Code no and 3-digit Marks. The outcome of the research will be an automated system for recognition of awards. This automated system will recognize only digits. This procedure can also be done manually, but that is a tedious task and prone to error. This system's complexity lies in the different handwriting styles which vary from human to human. Thus automated system provides better recognition accuracy than manual system. The award list which is used in the automated system is shown below: The rest of the paper is organized into five sections. In the Section 2 we will briefly explain about the review of literature in which the feature extraction technique along with the classifier is discussed. Section 3 describes the proposed system. In section 4 we will discuss about Recognition Result and Comparisons among Different Zoning Techniques and finally conclusion is given in section 5.