Recognition of handprinted Tamil characters

Abstract In the last few years linguistic approach to picture processing has gained in popularity. A scheme for recognizing handprinted Tamil characters has been developed. In this scheme, the characters are assumed to be composed of line-like elements, called primitives, satisfying certain relational constraints. Labelled graphs are used to describe the structural composition of characters in terms of the primitives and the relational constraints satisfied by them. The recognition procedure consists of converting the input image into a labelled graph representing the input character and computing correlation coefficients with the labelled graphs stored for a set of basic symbols. The algorithm uses topological matching procedure to compute the correlation coefficients and then maximises the correlation coefficient. Some pre-processing techniques are discussed to convert the input image to a labelled graph.