Segmentation of Unconstrained Handwritten Hindi Words Using Polygonal Approximation

Segmentation of unconstrained handwritten words into characters in an optically scanned document image data is an essential task and presents challenges to researchers with a wide variety of handwritings, large varieties of pen-types, poor image quality, and a lack of ordering information of strokes. This paper contributes methods for accurate full segmentation of Hindi word images into constituent characters and modifiers. It follows the polygonal approximation approach for the segmentation, and makes use of structural properties along with directional measures to determine segmentation points in Hindi word images. The main methodological contribution of this paper is the use of polygonal approximation technique for word segmentation which is based on certain structural properties of Hindi language. Second focus of this work lies on the fact that segmentation is done without removal of shirorekha which eliminates the complexities present in earlier works. Experiments on real-world data show that our novel method is always competitive and results in more top performances than any of the other measures.