Character Segmentation of Handwritten Bangla Text by Vertex Characterization of Isothetic Covers
Soumen Bag, Partha Bhowmick, Gaurav Harit, Arindam Biswas · 2011
Segmentation of cursive handwriting is one of the most challenging problems in the area of handwritten character recognition. In this paper, we propose a novel approach towards character segmentation in a handwritten document. It is based on the vertex characterization of outer isothetic polygonal covers so that each cover corresponds to a particular word or part of a word. The proposed method has the potential to segment skewed text without deskewing them. Experiment is done on several Bangla handwritings of different individuals. The average success rate is 96.04\%. This method can be considered as a significant preprocessing step towards the development of a handwritten Bangla OCR system.