Dynamic and Contextual Information in HMM Modeling for Handwritten Word Recognition
This study aims at building an efficient word recognition system resulting from the combination of three handwriting recognizers. The main component of this combined system is an HMM-based recognizer which considers dynamic and contextual information for a better modeling of writing units. For model...
Gespeichert in:
| Veröffentlicht in: | IEEE transactions on pattern analysis and machine intelligence 2011-10, Vol.33 (10), p.2066-2080 |
|---|---|
| Hauptverfasser: | , , , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 2080 |
|---|---|
| container_issue | 10 |
| container_start_page | 2066 |
| container_title | IEEE transactions on pattern analysis and machine intelligence |
| container_volume | 33 |
| creator | Bianne-Bernard, A.-L Menasri, F. Mohamad, R. Al-Hajj Mokbel, C. Kermorvant, C. Likforman-Sulem, Laurence |
| description | This study aims at building an efficient word recognition system resulting from the combination of three handwriting recognizers. The main component of this combined system is an HMM-based recognizer which considers dynamic and contextual information for a better modeling of writing units. For modeling the contextual units, a state-tying process based on decision tree clustering is introduced. Decision trees are built according to a set of expert-based questions on how characters are written. Questions are divided into global questions, yielding larger clusters, and precise questions, yielding smaller ones. Such clustering enables us to reduce the total number of models and Gaussians densities by 10. We then apply this modeling to the recognition of handwritten words. Experiments are conducted on three publicly available databases based on Latin or Arabic languages: Rimes, IAM, and OpenHart. The results obtained show that contextual information embedded with dynamic modeling significantly improves recognition. |
| doi_str_mv | 10.1109/TPAMI.2011.22 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_RIE</sourceid><recordid>TN_cdi_pubmed_primary_21282849</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>5708152</ieee_id><sourcerecordid>2433293661</sourcerecordid><originalsourceid>FETCH-LOGICAL-c370t-a761fd8bd8c77dcb72c888b7f837d88a5530041272284acdcb1bf093d85070bd3</originalsourceid><addsrcrecordid>eNpd0MFrHCEUBnApKc027TGnQJBCIZfZ-nSMzjFsk-xClpY2pUdx1AmGGU11hib_fZzuNoWeBN_P58eH0DGQJQBpPt1-vdhulpQALCl9hRbQsKZinDUHaEHgnFZSUnmI3uZ8TwjUnLA36JACLbd1s0DfPz8FPXiDdbB4FcPoHsdJ93gTupgGPfoYsA94vd3ibbSu9-EOlwleF_87-XF0Af-MyeJvzsS74OcH79DrTvfZvd-fR-jH1eXtal3dfLnerC5uKsMEGSstzqGzsrXSCGFNK6iRUraik0xYKTXnjJAaqKAlqjZFQNuRhlnJiSCtZUfobLf3IcVfk8ujGnw2ru91cHHKCgQAL19xWuiH_-h9nFIo6ZSUtWRMsBlVO2RSzDm5Tj0kP-j0pICouWz1p2w1l63o7E_3S6d2cPZF_223gI97oLPRfZd0MD7_czUHxgUUd7Jz3jn3MuaCSCjZnwHHpI6F</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>884833732</pqid></control><display><type>article</type><title>Dynamic and Contextual Information in HMM Modeling for Handwritten Word Recognition</title><source>IEEE Electronic Library (IEL)</source><creator>Bianne-Bernard, A.-L ; Menasri, F. ; Mohamad, R. Al-Hajj ; Mokbel, C. ; Kermorvant, C. ; Likforman-Sulem, Laurence</creator><creatorcontrib>Bianne-Bernard, A.-L ; Menasri, F. ; Mohamad, R. Al-Hajj ; Mokbel, C. ; Kermorvant, C. ; Likforman-Sulem, Laurence</creatorcontrib><description>This study aims at building an efficient word recognition system resulting from the combination of three handwriting recognizers. The main component of this combined system is an HMM-based recognizer which considers dynamic and contextual information for a better modeling of writing units. For modeling the contextual units, a state-tying process based on decision tree clustering is introduced. Decision trees are built according to a set of expert-based questions on how characters are written. Questions are divided into global questions, yielding larger clusters, and precise questions, yielding smaller ones. Such clustering enables us to reduce the total number of models and Gaussians densities by 10. We then apply this modeling to the recognition of handwritten words. Experiments are conducted on three publicly available databases based on Latin or Arabic languages: Rimes, IAM, and OpenHart. The results obtained show that contextual information embedded with dynamic modeling significantly improves recognition.</description><identifier>ISSN: 0162-8828</identifier><identifier>EISSN: 1939-3539</identifier><identifier>EISSN: 2160-9292</identifier><identifier>DOI: 10.1109/TPAMI.2011.22</identifier><identifier>PMID: 21282849</identifier><identifier>CODEN: ITPIDJ</identifier><language>eng</language><publisher>Los Alamitos, CA: IEEE</publisher><subject>Applied sciences ; Artificial intelligence ; Computational modeling ; Computer science; control theory; systems ; Context ; Context modeling ; context-dependent HMMs ; Decision trees ; Exact sciences and technology ; Feature extraction ; Handwriting recognition ; Hidden Markov models ; Latin and Arabic handwriting recognition ; neural-network combination ; Pattern recognition. Digital image processing. Computational geometry ; Pixel ; Studies</subject><ispartof>IEEE transactions on pattern analysis and machine intelligence, 2011-10, Vol.33 (10), p.2066-2080</ispartof><rights>2015 INIST-CNRS</rights><rights>Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) Oct 2011</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c370t-a761fd8bd8c77dcb72c888b7f837d88a5530041272284acdcb1bf093d85070bd3</citedby><cites>FETCH-LOGICAL-c370t-a761fd8bd8c77dcb72c888b7f837d88a5530041272284acdcb1bf093d85070bd3</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/5708152$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>314,776,780,792,27901,27902,54733</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/5708152$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc><backlink>$$Uhttp://pascal-francis.inist.fr/vibad/index.php?action=getRecordDetail&idt=24513571$$DView record in Pascal Francis$$Hfree_for_read</backlink><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/21282849$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Bianne-Bernard, A.-L</creatorcontrib><creatorcontrib>Menasri, F.</creatorcontrib><creatorcontrib>Mohamad, R. Al-Hajj</creatorcontrib><creatorcontrib>Mokbel, C.</creatorcontrib><creatorcontrib>Kermorvant, C.</creatorcontrib><creatorcontrib>Likforman-Sulem, Laurence</creatorcontrib><title>Dynamic and Contextual Information in HMM Modeling for Handwritten Word Recognition</title><title>IEEE transactions on pattern analysis and machine intelligence</title><addtitle>TPAMI</addtitle><addtitle>IEEE Trans Pattern Anal Mach Intell</addtitle><description>This study aims at building an efficient word recognition system resulting from the combination of three handwriting recognizers. The main component of this combined system is an HMM-based recognizer which considers dynamic and contextual information for a better modeling of writing units. For modeling the contextual units, a state-tying process based on decision tree clustering is introduced. Decision trees are built according to a set of expert-based questions on how characters are written. Questions are divided into global questions, yielding larger clusters, and precise questions, yielding smaller ones. Such clustering enables us to reduce the total number of models and Gaussians densities by 10. We then apply this modeling to the recognition of handwritten words. Experiments are conducted on three publicly available databases based on Latin or Arabic languages: Rimes, IAM, and OpenHart. The results obtained show that contextual information embedded with dynamic modeling significantly improves recognition.</description><subject>Applied sciences</subject><subject>Artificial intelligence</subject><subject>Computational modeling</subject><subject>Computer science; control theory; systems</subject><subject>Context</subject><subject>Context modeling</subject><subject>context-dependent HMMs</subject><subject>Decision trees</subject><subject>Exact sciences and technology</subject><subject>Feature extraction</subject><subject>Handwriting recognition</subject><subject>Hidden Markov models</subject><subject>Latin and Arabic handwriting recognition</subject><subject>neural-network combination</subject><subject>Pattern recognition. Digital image processing. Computational geometry</subject><subject>Pixel</subject><subject>Studies</subject><issn>0162-8828</issn><issn>1939-3539</issn><issn>2160-9292</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2011</creationdate><recordtype>article</recordtype><sourceid>RIE</sourceid><recordid>eNpd0MFrHCEUBnApKc027TGnQJBCIZfZ-nSMzjFsk-xClpY2pUdx1AmGGU11hib_fZzuNoWeBN_P58eH0DGQJQBpPt1-vdhulpQALCl9hRbQsKZinDUHaEHgnFZSUnmI3uZ8TwjUnLA36JACLbd1s0DfPz8FPXiDdbB4FcPoHsdJ93gTupgGPfoYsA94vd3ibbSu9-EOlwleF_87-XF0Af-MyeJvzsS74OcH79DrTvfZvd-fR-jH1eXtal3dfLnerC5uKsMEGSstzqGzsrXSCGFNK6iRUraik0xYKTXnjJAaqKAlqjZFQNuRhlnJiSCtZUfobLf3IcVfk8ujGnw2ru91cHHKCgQAL19xWuiH_-h9nFIo6ZSUtWRMsBlVO2RSzDm5Tj0kP-j0pICouWz1p2w1l63o7E_3S6d2cPZF_223gI97oLPRfZd0MD7_czUHxgUUd7Jz3jn3MuaCSCjZnwHHpI6F</recordid><startdate>20111001</startdate><enddate>20111001</enddate><creator>Bianne-Bernard, A.-L</creator><creator>Menasri, F.</creator><creator>Mohamad, R. Al-Hajj</creator><creator>Mokbel, C.</creator><creator>Kermorvant, C.</creator><creator>Likforman-Sulem, Laurence</creator><general>IEEE</general><general>IEEE Computer Society</general><general>The Institute of Electrical and Electronics Engineers, Inc. (IEEE)</general><scope>97E</scope><scope>RIA</scope><scope>RIE</scope><scope>IQODW</scope><scope>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7SC</scope><scope>7SP</scope><scope>8FD</scope><scope>JQ2</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope><scope>7X8</scope></search><sort><creationdate>20111001</creationdate><title>Dynamic and Contextual Information in HMM Modeling for Handwritten Word Recognition</title><author>Bianne-Bernard, A.-L ; Menasri, F. ; Mohamad, R. Al-Hajj ; Mokbel, C. ; Kermorvant, C. ; Likforman-Sulem, Laurence</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c370t-a761fd8bd8c77dcb72c888b7f837d88a5530041272284acdcb1bf093d85070bd3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2011</creationdate><topic>Applied sciences</topic><topic>Artificial intelligence</topic><topic>Computational modeling</topic><topic>Computer science; control theory; systems</topic><topic>Context</topic><topic>Context modeling</topic><topic>context-dependent HMMs</topic><topic>Decision trees</topic><topic>Exact sciences and technology</topic><topic>Feature extraction</topic><topic>Handwriting recognition</topic><topic>Hidden Markov models</topic><topic>Latin and Arabic handwriting recognition</topic><topic>neural-network combination</topic><topic>Pattern recognition. Digital image processing. Computational geometry</topic><topic>Pixel</topic><topic>Studies</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Bianne-Bernard, A.-L</creatorcontrib><creatorcontrib>Menasri, F.</creatorcontrib><creatorcontrib>Mohamad, R. Al-Hajj</creatorcontrib><creatorcontrib>Mokbel, C.</creatorcontrib><creatorcontrib>Kermorvant, C.</creatorcontrib><creatorcontrib>Likforman-Sulem, Laurence</creatorcontrib><collection>IEEE All-Society Periodicals Package (ASPP) 2005-present</collection><collection>IEEE All-Society Periodicals Package (ASPP) 1998-Present</collection><collection>IEEE Electronic Library (IEL)</collection><collection>Pascal-Francis</collection><collection>PubMed</collection><collection>CrossRef</collection><collection>Computer and Information Systems Abstracts</collection><collection>Electronics & Communications Abstracts</collection><collection>Technology Research Database</collection><collection>ProQuest Computer Science Collection</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Computer and Information Systems Abstracts Academic</collection><collection>Computer and Information Systems Abstracts Professional</collection><collection>MEDLINE - Academic</collection><jtitle>IEEE transactions on pattern analysis and machine intelligence</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Bianne-Bernard, A.-L</au><au>Menasri, F.</au><au>Mohamad, R. Al-Hajj</au><au>Mokbel, C.</au><au>Kermorvant, C.</au><au>Likforman-Sulem, Laurence</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Dynamic and Contextual Information in HMM Modeling for Handwritten Word Recognition</atitle><jtitle>IEEE transactions on pattern analysis and machine intelligence</jtitle><stitle>TPAMI</stitle><addtitle>IEEE Trans Pattern Anal Mach Intell</addtitle><date>2011-10-01</date><risdate>2011</risdate><volume>33</volume><issue>10</issue><spage>2066</spage><epage>2080</epage><pages>2066-2080</pages><issn>0162-8828</issn><eissn>1939-3539</eissn><eissn>2160-9292</eissn><coden>ITPIDJ</coden><abstract>This study aims at building an efficient word recognition system resulting from the combination of three handwriting recognizers. The main component of this combined system is an HMM-based recognizer which considers dynamic and contextual information for a better modeling of writing units. For modeling the contextual units, a state-tying process based on decision tree clustering is introduced. Decision trees are built according to a set of expert-based questions on how characters are written. Questions are divided into global questions, yielding larger clusters, and precise questions, yielding smaller ones. Such clustering enables us to reduce the total number of models and Gaussians densities by 10. We then apply this modeling to the recognition of handwritten words. Experiments are conducted on three publicly available databases based on Latin or Arabic languages: Rimes, IAM, and OpenHart. The results obtained show that contextual information embedded with dynamic modeling significantly improves recognition.</abstract><cop>Los Alamitos, CA</cop><pub>IEEE</pub><pmid>21282849</pmid><doi>10.1109/TPAMI.2011.22</doi><tpages>15</tpages></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISSN: 0162-8828 |
| ispartof | IEEE transactions on pattern analysis and machine intelligence, 2011-10, Vol.33 (10), p.2066-2080 |
| issn | 0162-8828 1939-3539 2160-9292 |
| language | eng |
| recordid | cdi_pubmed_primary_21282849 |
| source | IEEE Electronic Library (IEL) |
| subjects | Applied sciences Artificial intelligence Computational modeling Computer science control theory systems Context Context modeling context-dependent HMMs Decision trees Exact sciences and technology Feature extraction Handwriting recognition Hidden Markov models Latin and Arabic handwriting recognition neural-network combination Pattern recognition. Digital image processing. Computational geometry Pixel Studies |
| title | Dynamic and Contextual Information in HMM Modeling for Handwritten Word Recognition |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-10T12%3A23%3A54IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_RIE&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Dynamic%20and%20Contextual%20Information%20in%20HMM%20Modeling%20for%20Handwritten%20Word%20Recognition&rft.jtitle=IEEE%20transactions%20on%20pattern%20analysis%20and%20machine%20intelligence&rft.au=Bianne-Bernard,%20A.-L&rft.date=2011-10-01&rft.volume=33&rft.issue=10&rft.spage=2066&rft.epage=2080&rft.pages=2066-2080&rft.issn=0162-8828&rft.eissn=1939-3539&rft.coden=ITPIDJ&rft_id=info:doi/10.1109/TPAMI.2011.22&rft_dat=%3Cproquest_RIE%3E2433293661%3C/proquest_RIE%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=884833732&rft_id=info:pmid/21282849&rft_ieee_id=5708152&rfr_iscdi=true |