BRAC University Institutional Repository

Segmentation free Bangla OCR using HMM: Training and recognition

Show simple item record Hasnat, Md. Abul Habib, S. M. Murtoza Khan, Mumit 2010-12-06T10:37:04Z 2010-12-06T10:37:04Z 2007 2007
dc.description Includes bibliographical references (page 7-8).
dc.description.abstract The wide area of the application of HMM is in Speech Recognition where each spoken word is considered as a single unit to be recognized from the trained word network. Using this concept some research has been done for character recognition. In this paper, we present the training and recognition mechanism of a Hidden Markov Model (HMM) based multi font supported Optical Character Recognition (OCR) system for Bangla character. In our approach the central idea is separate HMM model for each segmented character or word. We emphasize on word level segmentation and like to consider the single character as a word when the character appears alone after segmentation process is done. The system uses HTK toolkit for data preparation, model training from multiple samples and recognition. Features of each trained character are calculated by applying Discrete Cosine Transform (DCT) to each pixel value of the character image where the image is divided into several frames according to its size. The extracted features of each frame are used as discrete probability distributions that will be given as input parameter to each HMM model. In case of recognition a model for each separated character or word is build up using the same approach. This model is given to the HTK toolkit to perform the recognition using Viterbi Decoding. The experimental result shows significant performance. en_US
dc.description.statementofresponsibility Md. Abul Hasnat
dc.description.statementofresponsibility S. M. Murtoza Habib
dc.description.statementofresponsibility Mumit Khan
dc.language.iso en en_US
dc.publisher BRAC University en_US
dc.subject Optical character recognition (OCR) en_US
dc.subject Hidden Markov Model (HMM) en_US
dc.subject HTK en_US
dc.subject Discrete cosine transform (DCT) en_US
dc.title Segmentation free Bangla OCR using HMM: Training and recognition en_US
dc.type Article en_US
dc.contributor.department Center for Research on Bangla language processing (CRBLP), BRAC University

Files in this item

This item appears in the following Collection(s)

Show simple item record

Policy Guidelines

Search BRACU Repository

Advanced Search


My Account