Skip navigation
Please use this identifier to cite or link to this item: http://repository.iitr.ac.in/handle/123456789/15643
Title: A Novel Approach of Bangla Handwritten Text Recognition Using HMM
Authors: Pratim Roy, Partha
Dey P.
Roy S.
Pal U.
Kimura F.
Published in: Proceedings of International Conference on Frontiers in Handwriting Recognition, ICFHR
Abstract: This paper presents a novel approach for offline Bangla (Bengali) handwritten word recognition by Hidden Markov Model (HMM). Due to the presence of complex features such as headline, vowels, modifiers, etc., character segmentation in Bangla script is not easy. Also, the position of vowels and compound characters make the segmentation task of words into characters very complex. To take care of these problems we propose a novel method considering a zone-wise break up of words and next perform HMM based recognition. In particular, the word image is segmented into 3 zones, upper, middle and lower, respectively. The components in middle zone are modeled using HMM. By this zone segmentation approach we reduce the number of distinct component classes compared to total number of classes in Bangla character set. Once the middle zone portion is recognized, HMM based forced alignment is applied in this zone to mark the boundaries of individual components. The segmentation paths are extended later to other zones. Next, the residue components, if any, in upper and lower zones in their respective boundary are combined to achieve the final word level recognition. We have performed a preliminary experiment on a dataset of 10,120 Bangla handwritten words and found that the proposed approach outperforms the custom way of HMM based recognition. © 2014 IEEE.
Citation: Proceedings of International Conference on Frontiers in Handwriting Recognition, ICFHR, (2014), 661- 666
URI: https://doi.org/10.1109/ICFHR.2014.116
http://repository.iitr.ac.in/handle/123456789/15643
Issue Date: 2014
Publisher: Institute of Electrical and Electronics Engineers Inc.
Keywords: Bangla Character Recognition
Handwriting Recognition
HMM
Indian Script Recognition
ISBN: 9.78148E+12
ISSN: 21676445
Author Scopus IDs: 56880478500
56868240500
57199785269
57200742116
55247906100
Author Affiliations: Roy, P.P., CVPR Unit, Indian Statistical Institute, Kolkata, India
Dey, P., Dept. of CSE, Institute of Engineering and Management, Kolkata, India
Roy, S., Tata Consultancy Services, Kolkata, India
Pal, U., CVPR Unit, Indian Statistical Institute, Kolkata, India
Kimura, F., Graduate School of Engg., Mie University, Mie, Japan
Appears in Collections:Conference Publications [CS]

Files in This Item:
There are no files associated with this item.
Show full item record


Items in Repository are protected by copyright, with all rights reserved, unless otherwise indicated.