A complete printed Bangla OCR system

摘要

A complete Optical Character Recognition (OCR) system for printed Bangla, the fourth most popular script in the world, is presented. This is the first OCR system among all script forms used in the Indian sub-continent. The problem is difficult because (i) there are about 300 basic, modified and compound character shapes in the script, (ii) the characters in a word are topologically connected and (iii) Bangla is an inflectional language. In our system the document image captured by Flat-bed scanner is subject to skew correction, text graphics separation, line segmentation, zone detection, word and character segmentation using some conventional and some newly developed techniques. From zonal information and shape characteristics, the basic, modified and compound characters are separated for the convenience of classification. The basic and modified characters which are about 75 in number and which occupy about 96% of the text corpus, are recognized by a structural-feature-based tree classifier. The compound characters are recognized by a tree classifier followed by template-matching approach. The feature detection is simple and robust where preprocessing like thinning and pruning are avoided. The character unigram statistics is used to make the tree classifier efficient. Several heuristics are also used to speed up the template matching approach. A dictionary-based error-correction scheme has been used where separate dictionaries are compiled for root word and suffixes that contain morpho-syntactic informations as well. For single font clear documents 95.50% word level (which is equivalent to 99.10% character level) recognition accuracy has been obtained. Extension of the work to Devnagari, the third most popular script in the world, is also discussed.