Skip navigation
Please use this identifier to cite or link to this item:
Title: Handwritten word spotting in Indic scripts using foreground and background information
Authors: Das A.
Bhunia A.K.
Pratim Roy, Partha
Pal U.
Published in: Proceedings of 3rd IAPR Asian Conference on Pattern Recognition, ACPR 2015
Abstract: In this paper we present a line based word spotting system based on Hidden Markov Model for offline Indic scripts such as Bangla (Bengali) and Devanagari. We propose a novel approach of combining foreground and background information of text line images for keyword-spotting by character filler models. The candidate keywords are searched from a line without segmenting character or words. A significant improvement in performance is noted by using both foreground and background information than anyone alone. Pyramid Histogram of Oriented Gradient (PHOG) feature has been used in our word spotting framework and it outperforms other existing features of word spotting. The framework of combining foreground and background information has been evaluated in IAM dataset (English script) to show the robustness of the proposed approach. © 2015 IEEE.
Citation: Proceedings of 3rd IAPR Asian Conference on Pattern Recognition, ACPR 2015, (2016), 426- 430
Issue Date: 2016
Publisher: Institute of Electrical and Electronics Engineers Inc.
Keywords: Data mining
Hidden Markov models
Image segmentation
Markov processes
Pattern recognition
Speech recognition
Background information
Filler models
Handwritten words
Keyword spotting
Pyramid histogram of oriented gradient (PHOG)
Text lines
Word Spotting
Information use
ISBN: 9.78148E+12
Author Scopus IDs: 57207436443
Author Affiliations: Das, A., Dept. of ECE, IEM Kolkata, India
Bhunia, A.K., Dept. of ECE, IEM Kolkata, India
Roy, P.P., Dept. of CSE, IIT Roorkee, India
Pal, U., CVPR Unit, ISI Kolkata, India
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.