Language Model Integration for the Recognition of Handwritten Medieval Documents
Building recognition systems for historical documents is a difficult task. Especially, when it comes to medieval scripts. The complexity is mainly affected by the poor quality and the small quantity of the data available. In this paper we apply an HMM based recognition system to medieval manuscripts...
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Tagungsbericht |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 215 |
|---|---|
| container_issue | |
| container_start_page | 211 |
| container_title | |
| container_volume | |
| creator | Wuthrich, M. Liwicki, M. Fischer, A. Indermuhle, E. Bunke, H. Viehhauser, G. Stolz, M. |
| description | Building recognition systems for historical documents is a difficult task. Especially, when it comes to medieval scripts. The complexity is mainly affected by the poor quality and the small quantity of the data available. In this paper we apply an HMM based recognition system to medieval manuscripts from the 13th century written in Middle High German. The recognition system, which was originally developed for modern scripts, has been adapted to medieval scripts. Beside the data processing, one of the major challenges is to create a suitable language model. Because of the lack of appropriate independent text corpora for medieval languages, the language model has to be created on the base of a rather small number of manuscripts only. Due to the small size of the corpus, optimizing the language model parameters can quickly lead to the problem of overfitting. In this paper we describe a strategy to integrate all available information into the language model and to optimize the language model parameters without suffering from this problem. |
| doi_str_mv | 10.1109/ICDAR.2009.17 |
| format | Conference Proceeding |
| fullrecord | <record><control><sourceid>ieee_6IE</sourceid><recordid>TN_cdi_ieee_primary_5277727</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>5277727</ieee_id><sourcerecordid>5277727</sourcerecordid><originalsourceid>FETCH-LOGICAL-i90t-dea316258dafe25096c5a3c892b698cc87fa5c4b04dfbdc3f8828ff0e181fb8f3</originalsourceid><addsrcrecordid>eNotzMtOAjEUgOF6SwRk6cpNX2Dw9DZtlwQvkEA0hD3ptKdjDXTMTNH49ibq6k--xU_ILYMZY2DvV4uH-XbGAeyM6TMytdqArq0Smit-TkZcaFtxJuGCjJnkUkoFAJdkxBSHSolaXJPxMLwDMGttPSKva5fbk2uRbrqAB7rKBdveldRlGrueljekW_Rdm9OvdZEuXQ5ffSoFM91gSPjpDvSh86cj5jLckKvoDgNO_zshu6fH3WJZrV-eV4v5ukoWShXQCVZzZYKLyBXY2isnvLG8qa3x3ujolJcNyBCb4EU0hpsYAZlhsTFRTMjd3zYh4v6jT0fXf-8V11pzLX4AG1tTaw</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Language Model Integration for the Recognition of Handwritten Medieval Documents</title><source>IEEE Electronic Library (IEL) Conference Proceedings</source><creator>Wuthrich, M. ; Liwicki, M. ; Fischer, A. ; Indermuhle, E. ; Bunke, H. ; Viehhauser, G. ; Stolz, M.</creator><creatorcontrib>Wuthrich, M. ; Liwicki, M. ; Fischer, A. ; Indermuhle, E. ; Bunke, H. ; Viehhauser, G. ; Stolz, M.</creatorcontrib><description>Building recognition systems for historical documents is a difficult task. Especially, when it comes to medieval scripts. The complexity is mainly affected by the poor quality and the small quantity of the data available. In this paper we apply an HMM based recognition system to medieval manuscripts from the 13th century written in Middle High German. The recognition system, which was originally developed for modern scripts, has been adapted to medieval scripts. Beside the data processing, one of the major challenges is to create a suitable language model. Because of the lack of appropriate independent text corpora for medieval languages, the language model has to be created on the base of a rather small number of manuscripts only. Due to the small size of the corpus, optimizing the language model parameters can quickly lead to the problem of overfitting. In this paper we describe a strategy to integrate all available information into the language model and to optimize the language model parameters without suffering from this problem.</description><identifier>ISSN: 1520-5363</identifier><identifier>ISBN: 1424445000</identifier><identifier>ISBN: 9781424445004</identifier><identifier>EISSN: 2379-2140</identifier><identifier>EISBN: 9780769537252</identifier><identifier>EISBN: 0769537251</identifier><identifier>DOI: 10.1109/ICDAR.2009.17</identifier><language>eng</language><publisher>IEEE</publisher><subject>Computer science ; Data processing ; Digital images ; Handwriting recognition ; Hidden Markov models ; Historical Documents ; HMM ; Language Model ; Mathematics ; Natural languages ; Overfitting ; Software libraries ; Text analysis ; Writing</subject><ispartof>2009 10th International Conference on Document Analysis and Recognition, 2009, p.211-215</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/5277727$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,776,780,785,786,2052,27902,54895</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/5277727$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Wuthrich, M.</creatorcontrib><creatorcontrib>Liwicki, M.</creatorcontrib><creatorcontrib>Fischer, A.</creatorcontrib><creatorcontrib>Indermuhle, E.</creatorcontrib><creatorcontrib>Bunke, H.</creatorcontrib><creatorcontrib>Viehhauser, G.</creatorcontrib><creatorcontrib>Stolz, M.</creatorcontrib><title>Language Model Integration for the Recognition of Handwritten Medieval Documents</title><title>2009 10th International Conference on Document Analysis and Recognition</title><addtitle>ICDAR</addtitle><description>Building recognition systems for historical documents is a difficult task. Especially, when it comes to medieval scripts. The complexity is mainly affected by the poor quality and the small quantity of the data available. In this paper we apply an HMM based recognition system to medieval manuscripts from the 13th century written in Middle High German. The recognition system, which was originally developed for modern scripts, has been adapted to medieval scripts. Beside the data processing, one of the major challenges is to create a suitable language model. Because of the lack of appropriate independent text corpora for medieval languages, the language model has to be created on the base of a rather small number of manuscripts only. Due to the small size of the corpus, optimizing the language model parameters can quickly lead to the problem of overfitting. In this paper we describe a strategy to integrate all available information into the language model and to optimize the language model parameters without suffering from this problem.</description><subject>Computer science</subject><subject>Data processing</subject><subject>Digital images</subject><subject>Handwriting recognition</subject><subject>Hidden Markov models</subject><subject>Historical Documents</subject><subject>HMM</subject><subject>Language Model</subject><subject>Mathematics</subject><subject>Natural languages</subject><subject>Overfitting</subject><subject>Software libraries</subject><subject>Text analysis</subject><subject>Writing</subject><issn>1520-5363</issn><issn>2379-2140</issn><isbn>1424445000</isbn><isbn>9781424445004</isbn><isbn>9780769537252</isbn><isbn>0769537251</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2009</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><sourceid>RIE</sourceid><recordid>eNotzMtOAjEUgOF6SwRk6cpNX2Dw9DZtlwQvkEA0hD3ptKdjDXTMTNH49ibq6k--xU_ILYMZY2DvV4uH-XbGAeyM6TMytdqArq0Smit-TkZcaFtxJuGCjJnkUkoFAJdkxBSHSolaXJPxMLwDMGttPSKva5fbk2uRbrqAB7rKBdveldRlGrueljekW_Rdm9OvdZEuXQ5ffSoFM91gSPjpDvSh86cj5jLckKvoDgNO_zshu6fH3WJZrV-eV4v5ukoWShXQCVZzZYKLyBXY2isnvLG8qa3x3ujolJcNyBCb4EU0hpsYAZlhsTFRTMjd3zYh4v6jT0fXf-8V11pzLX4AG1tTaw</recordid><startdate>200907</startdate><enddate>200907</enddate><creator>Wuthrich, M.</creator><creator>Liwicki, M.</creator><creator>Fischer, A.</creator><creator>Indermuhle, E.</creator><creator>Bunke, H.</creator><creator>Viehhauser, G.</creator><creator>Stolz, M.</creator><general>IEEE</general><scope>6IE</scope><scope>6IL</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIL</scope></search><sort><creationdate>200907</creationdate><title>Language Model Integration for the Recognition of Handwritten Medieval Documents</title><author>Wuthrich, M. ; Liwicki, M. ; Fischer, A. ; Indermuhle, E. ; Bunke, H. ; Viehhauser, G. ; Stolz, M.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i90t-dea316258dafe25096c5a3c892b698cc87fa5c4b04dfbdc3f8828ff0e181fb8f3</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2009</creationdate><topic>Computer science</topic><topic>Data processing</topic><topic>Digital images</topic><topic>Handwriting recognition</topic><topic>Hidden Markov models</topic><topic>Historical Documents</topic><topic>HMM</topic><topic>Language Model</topic><topic>Mathematics</topic><topic>Natural languages</topic><topic>Overfitting</topic><topic>Software libraries</topic><topic>Text analysis</topic><topic>Writing</topic><toplevel>online_resources</toplevel><creatorcontrib>Wuthrich, M.</creatorcontrib><creatorcontrib>Liwicki, M.</creatorcontrib><creatorcontrib>Fischer, A.</creatorcontrib><creatorcontrib>Indermuhle, E.</creatorcontrib><creatorcontrib>Bunke, H.</creatorcontrib><creatorcontrib>Viehhauser, G.</creatorcontrib><creatorcontrib>Stolz, 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 (IEL)</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>Wuthrich, M.</au><au>Liwicki, M.</au><au>Fischer, A.</au><au>Indermuhle, E.</au><au>Bunke, H.</au><au>Viehhauser, G.</au><au>Stolz, M.</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Language Model Integration for the Recognition of Handwritten Medieval Documents</atitle><btitle>2009 10th International Conference on Document Analysis and Recognition</btitle><stitle>ICDAR</stitle><date>2009-07</date><risdate>2009</risdate><spage>211</spage><epage>215</epage><pages>211-215</pages><issn>1520-5363</issn><eissn>2379-2140</eissn><isbn>1424445000</isbn><isbn>9781424445004</isbn><eisbn>9780769537252</eisbn><eisbn>0769537251</eisbn><abstract>Building recognition systems for historical documents is a difficult task. Especially, when it comes to medieval scripts. The complexity is mainly affected by the poor quality and the small quantity of the data available. In this paper we apply an HMM based recognition system to medieval manuscripts from the 13th century written in Middle High German. The recognition system, which was originally developed for modern scripts, has been adapted to medieval scripts. Beside the data processing, one of the major challenges is to create a suitable language model. Because of the lack of appropriate independent text corpora for medieval languages, the language model has to be created on the base of a rather small number of manuscripts only. Due to the small size of the corpus, optimizing the language model parameters can quickly lead to the problem of overfitting. In this paper we describe a strategy to integrate all available information into the language model and to optimize the language model parameters without suffering from this problem.</abstract><pub>IEEE</pub><doi>10.1109/ICDAR.2009.17</doi><tpages>5</tpages></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISSN: 1520-5363 |
| ispartof | 2009 10th International Conference on Document Analysis and Recognition, 2009, p.211-215 |
| issn | 1520-5363 2379-2140 |
| language | eng |
| recordid | cdi_ieee_primary_5277727 |
| source | IEEE Electronic Library (IEL) Conference Proceedings |
| subjects | Computer science Data processing Digital images Handwriting recognition Hidden Markov models Historical Documents HMM Language Model Mathematics Natural languages Overfitting Software libraries Text analysis Writing |
| title | Language Model Integration for the Recognition of Handwritten Medieval Documents |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-03T08%3A43%3A09IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-ieee_6IE&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=Language%20Model%20Integration%20for%20the%20Recognition%20of%20Handwritten%20Medieval%20Documents&rft.btitle=2009%2010th%20International%20Conference%20on%20Document%20Analysis%20and%20Recognition&rft.au=Wuthrich,%20M.&rft.date=2009-07&rft.spage=211&rft.epage=215&rft.pages=211-215&rft.issn=1520-5363&rft.eissn=2379-2140&rft.isbn=1424445000&rft.isbn_list=9781424445004&rft_id=info:doi/10.1109/ICDAR.2009.17&rft_dat=%3Cieee_6IE%3E5277727%3C/ieee_6IE%3E%3Curl%3E%3C/url%3E&rft.eisbn=9780769537252&rft.eisbn_list=0769537251&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=5277727&rfr_iscdi=true |