期刊名称：International Journal of Computer Science and Information Technologies
电子版ISSN：0975-9646
出版年度：2015
卷号：6
期号：4
页码：3349-3356
出版社：TechScience Publications
摘要：In this paper, a neural network based classifier using optical character recognition engine for Tamil language is proposed. At the first level, features derived at each sample point of the preprocessed character are used to construct a subspace using Optical Character Recognition (OCR) software. Recognition of the test sample is performed using a neural network based classifier. Based on the analysis of the proposed method, it was identified that Tamil character recognition was optimal and the implementation reduces the coding complexity to a greater extent. The proposed method can be used to recognize any language characters but in this paper only Tamil characters were tested for recognition. As a future enhancement, implementation of speech processing can be used to identify the classified characters to visually impaired persons for ease. The same technique can be used to resolve confusions between triplets and quadruples of similar characters. The same recognition could be carried out not only for individual characters but also for Tamil words. General Terms Optical Character Recognition, Neural Network, Tamil language
关键词：Feature matrix; Character grid; Character Switching; Nearest;neighbor classifier; Neural network based classifier
