Loading…

A Discriminative Approach to On-Line Handwriting Recognition Using Bi-character Models

Unconstrained on-line handwriting recognition is typically approached within the framework of generative HMM-based classifiers. In this paper, we introduce a novel discriminative method that relies, in contrast, on explicit grapheme segmentation and SVM-based character recognition. In addition to si...

Full description

Saved in:
Bibliographic Details
Main Authors: Prum, S., Visani, M., Fischer, A., Ogier, J. M.
Format: Conference Proceeding
Language:English
Subjects:
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by
cites
container_end_page 368
container_issue
container_start_page 364
container_title
container_volume
creator Prum, S.
Visani, M.
Fischer, A.
Ogier, J. M.
description Unconstrained on-line handwriting recognition is typically approached within the framework of generative HMM-based classifiers. In this paper, we introduce a novel discriminative method that relies, in contrast, on explicit grapheme segmentation and SVM-based character recognition. In addition to single character recognition with rejection, bi-characters are recognized in order to refine the recognition hypotheses. In particular, bi-character recognition is able to cope with the problem of shared character parts. Whole word recognition is achieved with an efficient dynamic programming method similar to the Viterbi algorithm. In an experimental evaluation on the Unipen-ICROW-03 database, we demonstrate improvements in recognition accuracy of up to 8% for a lexicon of 20,000 words with the proposed method when compared with an HMM-based baseline system. The computational speed is on par with the baseline system.
doi_str_mv 10.1109/ICDAR.2013.80
format conference_proceeding
fullrecord <record><control><sourceid>ieee_CHZPO</sourceid><recordid>TN_cdi_ieee_primary_6628645</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>6628645</ieee_id><sourcerecordid>6628645</sourcerecordid><originalsourceid>FETCH-LOGICAL-i175t-e5a101e8d79b3b472bfa2c3a665a884483c29e36ee7b9f30106a272aaca5a5e33</originalsourceid><addsrcrecordid>eNotj81Kw0AYRUdRsNYuXbmZF5g6P5m_ZUyrLVQKxbotXyZf2pE6CUlQfHtbdHUvh8uBS8i94FMhuH9cFrN8M5VcqKnjF2TirePWeJ15780lGUllPZMi41dkJLTkTCujbsht339wLs6jEXnP6Sz2oYufMcEQv5Dmbds1EA50aOg6sVVMSBeQqu8uDjHt6QZDs0-n3iS67c_kKbJwgA7CgB19bSo89nfkuoZjj5P_HJPt8_ytWLDV-mVZ5CsWhdUDQw2CC3SV9aUqMyvLGmRQYIwG57LMqSA9KoNoS18rLrgBaSVAAA0alRqThz9vRMRde7oB3c_OGOlMptUvqDdSYQ</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>A Discriminative Approach to On-Line Handwriting Recognition Using Bi-character Models</title><source>IEEE Xplore All Conference Series</source><creator>Prum, S. ; Visani, M. ; Fischer, A. ; Ogier, J. M.</creator><creatorcontrib>Prum, S. ; Visani, M. ; Fischer, A. ; Ogier, J. M.</creatorcontrib><description>Unconstrained on-line handwriting recognition is typically approached within the framework of generative HMM-based classifiers. In this paper, we introduce a novel discriminative method that relies, in contrast, on explicit grapheme segmentation and SVM-based character recognition. In addition to single character recognition with rejection, bi-characters are recognized in order to refine the recognition hypotheses. In particular, bi-character recognition is able to cope with the problem of shared character parts. Whole word recognition is achieved with an efficient dynamic programming method similar to the Viterbi algorithm. In an experimental evaluation on the Unipen-ICROW-03 database, we demonstrate improvements in recognition accuracy of up to 8% for a lexicon of 20,000 words with the proposed method when compared with an HMM-based baseline system. The computational speed is on par with the baseline system.</description><identifier>ISSN: 1520-5363</identifier><identifier>EISSN: 2379-2140</identifier><identifier>EISBN: 9780769549996</identifier><identifier>EISBN: 0769549993</identifier><identifier>DOI: 10.1109/ICDAR.2013.80</identifier><identifier>CODEN: IEEPAD</identifier><language>eng</language><publisher>IEEE</publisher><subject>bi-character recognition ; Character recognition ; combining on-line and off-line features ; dynamic programming ; Handwriting recognition ; Hidden Markov models ; Lattices ; on-line handwriting recognition ; Shape ; support vector machine ; Support vector machines ; Thyristors</subject><ispartof>2013 12th International Conference on Document Analysis and Recognition, 2013, p.364-368</ispartof><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/6628645$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,780,784,789,790,27925,54555,54932</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/6628645$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Prum, S.</creatorcontrib><creatorcontrib>Visani, M.</creatorcontrib><creatorcontrib>Fischer, A.</creatorcontrib><creatorcontrib>Ogier, J. M.</creatorcontrib><title>A Discriminative Approach to On-Line Handwriting Recognition Using Bi-character Models</title><title>2013 12th International Conference on Document Analysis and Recognition</title><addtitle>icdar</addtitle><description>Unconstrained on-line handwriting recognition is typically approached within the framework of generative HMM-based classifiers. In this paper, we introduce a novel discriminative method that relies, in contrast, on explicit grapheme segmentation and SVM-based character recognition. In addition to single character recognition with rejection, bi-characters are recognized in order to refine the recognition hypotheses. In particular, bi-character recognition is able to cope with the problem of shared character parts. Whole word recognition is achieved with an efficient dynamic programming method similar to the Viterbi algorithm. In an experimental evaluation on the Unipen-ICROW-03 database, we demonstrate improvements in recognition accuracy of up to 8% for a lexicon of 20,000 words with the proposed method when compared with an HMM-based baseline system. The computational speed is on par with the baseline system.</description><subject>bi-character recognition</subject><subject>Character recognition</subject><subject>combining on-line and off-line features</subject><subject>dynamic programming</subject><subject>Handwriting recognition</subject><subject>Hidden Markov models</subject><subject>Lattices</subject><subject>on-line handwriting recognition</subject><subject>Shape</subject><subject>support vector machine</subject><subject>Support vector machines</subject><subject>Thyristors</subject><issn>1520-5363</issn><issn>2379-2140</issn><isbn>9780769549996</isbn><isbn>0769549993</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2013</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><recordid>eNotj81Kw0AYRUdRsNYuXbmZF5g6P5m_ZUyrLVQKxbotXyZf2pE6CUlQfHtbdHUvh8uBS8i94FMhuH9cFrN8M5VcqKnjF2TirePWeJ15780lGUllPZMi41dkJLTkTCujbsht339wLs6jEXnP6Sz2oYufMcEQv5Dmbds1EA50aOg6sVVMSBeQqu8uDjHt6QZDs0-n3iS67c_kKbJwgA7CgB19bSo89nfkuoZjj5P_HJPt8_ytWLDV-mVZ5CsWhdUDQw2CC3SV9aUqMyvLGmRQYIwG57LMqSA9KoNoS18rLrgBaSVAAA0alRqThz9vRMRde7oB3c_OGOlMptUvqDdSYQ</recordid><startdate>201308</startdate><enddate>201308</enddate><creator>Prum, S.</creator><creator>Visani, M.</creator><creator>Fischer, A.</creator><creator>Ogier, J. M.</creator><general>IEEE</general><scope>6IE</scope><scope>6IL</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIL</scope></search><sort><creationdate>201308</creationdate><title>A Discriminative Approach to On-Line Handwriting Recognition Using Bi-character Models</title><author>Prum, S. ; Visani, M. ; Fischer, A. ; Ogier, J. M.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i175t-e5a101e8d79b3b472bfa2c3a665a884483c29e36ee7b9f30106a272aaca5a5e33</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2013</creationdate><topic>bi-character recognition</topic><topic>Character recognition</topic><topic>combining on-line and off-line features</topic><topic>dynamic programming</topic><topic>Handwriting recognition</topic><topic>Hidden Markov models</topic><topic>Lattices</topic><topic>on-line handwriting recognition</topic><topic>Shape</topic><topic>support vector machine</topic><topic>Support vector machines</topic><topic>Thyristors</topic><toplevel>online_resources</toplevel><creatorcontrib>Prum, S.</creatorcontrib><creatorcontrib>Visani, M.</creatorcontrib><creatorcontrib>Fischer, A.</creatorcontrib><creatorcontrib>Ogier, J. M.</creatorcontrib><collection>IEEE Electronic Library (IEL) Conference Proceedings</collection><collection>IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume</collection><collection>IEEE Xplore All Conference Proceedings</collection><collection>IEEE Electronic Library Online</collection><collection>IEEE Proceedings Order Plans (POP All) 1998-Present</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Prum, S.</au><au>Visani, M.</au><au>Fischer, A.</au><au>Ogier, J. M.</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>A Discriminative Approach to On-Line Handwriting Recognition Using Bi-character Models</atitle><btitle>2013 12th International Conference on Document Analysis and Recognition</btitle><stitle>icdar</stitle><date>2013-08</date><risdate>2013</risdate><spage>364</spage><epage>368</epage><pages>364-368</pages><issn>1520-5363</issn><eissn>2379-2140</eissn><eisbn>9780769549996</eisbn><eisbn>0769549993</eisbn><coden>IEEPAD</coden><abstract>Unconstrained on-line handwriting recognition is typically approached within the framework of generative HMM-based classifiers. In this paper, we introduce a novel discriminative method that relies, in contrast, on explicit grapheme segmentation and SVM-based character recognition. In addition to single character recognition with rejection, bi-characters are recognized in order to refine the recognition hypotheses. In particular, bi-character recognition is able to cope with the problem of shared character parts. Whole word recognition is achieved with an efficient dynamic programming method similar to the Viterbi algorithm. In an experimental evaluation on the Unipen-ICROW-03 database, we demonstrate improvements in recognition accuracy of up to 8% for a lexicon of 20,000 words with the proposed method when compared with an HMM-based baseline system. The computational speed is on par with the baseline system.</abstract><pub>IEEE</pub><doi>10.1109/ICDAR.2013.80</doi><tpages>5</tpages></addata></record>
fulltext fulltext_linktorsrc
identifier ISSN: 1520-5363
ispartof 2013 12th International Conference on Document Analysis and Recognition, 2013, p.364-368
issn 1520-5363
2379-2140
language eng
recordid cdi_ieee_primary_6628645
source IEEE Xplore All Conference Series
subjects bi-character recognition
Character recognition
combining on-line and off-line features
dynamic programming
Handwriting recognition
Hidden Markov models
Lattices
on-line handwriting recognition
Shape
support vector machine
Support vector machines
Thyristors
title A Discriminative Approach to On-Line Handwriting Recognition Using Bi-character Models
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-24T23%3A05%3A21IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-ieee_CHZPO&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=A%20Discriminative%20Approach%20to%20On-Line%20Handwriting%20Recognition%20Using%20Bi-character%20Models&rft.btitle=2013%2012th%20International%20Conference%20on%20Document%20Analysis%20and%20Recognition&rft.au=Prum,%20S.&rft.date=2013-08&rft.spage=364&rft.epage=368&rft.pages=364-368&rft.issn=1520-5363&rft.eissn=2379-2140&rft.coden=IEEPAD&rft_id=info:doi/10.1109/ICDAR.2013.80&rft.eisbn=9780769549996&rft.eisbn_list=0769549993&rft_dat=%3Cieee_CHZPO%3E6628645%3C/ieee_CHZPO%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-i175t-e5a101e8d79b3b472bfa2c3a665a884483c29e36ee7b9f30106a272aaca5a5e33%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=6628645&rfr_iscdi=true