Segmentation of Offline Handwritten Bengali Script

TL;DR

This paper presents a novel segmentation technique for cursive handwritten Bengali script, achieving a 97.7% success rate in decomposing connected characters into individual symbols, addressing challenges unique to Bengali handwriting.

Contribution

The paper introduces a new segmentation method tailored for Bengali cursive handwriting, overcoming limitations of traditional approaches used for Latin scripts.

Findings

97.7% segmentation success rate on sample data

Effective handling of Bengali script's encircling characters

Potential for improved handwritten Bengali recognition

Abstract

Character segmentation has long been one of the most critical areas of optical character recognition process. Through this operation, an image of a sequence of characters, which may be connected in some cases, is decomposed into sub-images of individual alphabetic symbols. In this paper, segmentation of cursive handwritten script of world's fourth popular language, Bengali, is considered. Unlike English script, Bengali handwritten characters and its components often encircle the main character, making the conventional segmentation methodologies inapplicable. Experimental results, using the proposed segmentation technique, on sample cursive handwritten data containing 218 ideal segmentation points show a success rate of 97.7%. Further feature-analysis on these segments may lead to actual recognition of handwritten cursive Bengali script.