JCS_V1_N3_RP1 S. Rajakumar V. Subbiah Bharathi Journal on Communication Engineering and Systems 2277-5242 1 3 17 24 Stone Inscriptions, Structural features, Feature Extraction In this paper we propose an approach for offline recognition of ancient Tamil characters using their structural features. Structural features are the features that are physically a part of the structure of the character, such as straight lines, arcs, circles, intersections etc. The features used for recognition are the positions of vertical lines, horizontal lines and branching in a character. Some other features, namely moments, zoning and number of transitions have also been explored to verify their utility in Tamil character recognition. For classification of the characters simple Euclidean distance was used. Ancient Tamil Character recognition is a classic problem in the field of image processing and neural networks. Lot of research has been done on recognition of handwritten Tamil characters but relatively less work has been done in the field of recognition of Ancient Tamil characters in Indian languages. In this paper we explore some structural features that can be used in offline Ancient Tamil character recognition. Structural features are insufficient to classify all the characters. Some other features along with the use of artificial neural networks can improve the performance of the system. The proposed algorithm obtained results in terms of accuracy (reaches 97.9% for some letters at average 80%) as well as in terms of time consuming. May - July 2012 Copyright © 2012 i-manager publications. All rights reserved. i-manager Publications http://www.imanagerpublications.com/Article.aspx?ArticleId=1891