OCRMPD: OCR system for Myanmar printed document image with a novel segmentation method and hierarchical classification scheme

摘要

As large quantity of document images is getting archived by the digital libraries, an efficient strategy that can convert Myanmar document image into machine understandable text format is needed. And Myanmar language contains many words, and most of them are similar, especially for small fonts, the accuracy of the Optical Character Recognition, OCR system for Myanmar may be low. Therefore, this paper designs an OCR system for Myanmar Printed Document (OCRMPD) with several proposed methods that can automatically convert Myanmar printed text to machine understandable text. In order to get more accurate system, enhance the input image by removing noise and making some correction on variants. A method for isolation of the character image is proposed by using connected component analysis for wrongly segmented characters produced by projection only. Finally, hierarchical mechanism is used for SVM classifier for recognition of the character image. The proposed algorithms have been tested on a variety of Myanmar printed documents and the results of the experiments indicate that the methods can increase the segmentation accuracy as well as recognition rates.