Segmentation in Malayalam OCR — Handling broken characters using active contour model

Character segmentation is a significant phase in an Optical Character Recognition (OCR) system. In this stage of OCR, the image of sequence of characters is decomposed into sub-images of individual symbols. The recognition of characters depends on this phase so that any mistake in the segmentation leads to a complete failure of the OCR system. One of the main reasons for incorrect segmentation of characters is the presence of broken characters in the input document. Here an approach based on Active Contour Model is proposed to solve this problem.