Handwritten Marathi Compound Character Segmentation with Morphological Operation
International Journal of Innovations in Engineering and Science, 2 (12):
8-12 (December 2017)Abstract
Segmentation phase plays vital role in any handwritten script Identification system. Aside from the large variation of individual’s handwriting, many researchers found difficulty to separate characters from the captured text document Image. The key factor of selection of segmentation algorithm is used to improve efficiency of character segmentation as well as good feature extraction. There are so many features of Marathi Script like large character set, complex shape, modifier in that one of the feature is compound character. Segmentation of such type characters is very difficult due to their complex structure. This paper proposed novel technique for separation of handwritten Marathi compound characters. The first step in the segmentation process to segment the line of text document, word from the line and at the last character of the word. For separating characters from compound character our aim is to first find termination points and bifurcation points of the characters. We proposed a novel algorithm minutiae detection algorithm which is used to find termination and bifurcation points in the given image.