Handwritten Marathi Compound Character Segmentation Using Minutiae Detection Algorithm

摘要

Segmentation process is the heart of handwritten Script Identification system. Aside from the large variation of individual's handwriting, many researchersfound difficulty to separate characters from scanned word document Image. The key factor of selection of segmentation algorithm is used to improve efficiency of character segmentation as well as good feature extraction. One of the feature of Marathi script is Compound Character, derived from Devnagari, occur rarely in the script. Segmentation of such type characters is very difficult due to their complex structure. This paper proposed new technique for segmentation of handwritten Marathi compound characters. The Proposed algorithm used the concept of Minutiae extraction for fingerprint for segmenting the compound character. Basically Segmentation is carried out using morphological operations such as erosion and dilation. For segmenting the character from compound character our aim to find termination point and bifurcation points. And for finding the termination and bifurcation point proposed algorithm used the morphological operation hit or miss transform. The experimentalresults shows 90% accuracy in finding termination and bifurcation points.