A robust video text extraction method based on text traversing line and stroke connectivity
Automatic video-text extraction is an important field in video content comprehension. In this paper, a robust video-text extraction method is presented which can automatically extract horizontally aligned text with different languages. First, an unsupervised paradigm based on Haar wavelets is applie...
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 | 1005 |
|---|---|
| container_issue | |
| container_start_page | 1002 |
| container_title | |
| container_volume | |
| creator | Peng Tianqiang Tian Pohuang Li Bicheng |
| description | Automatic video-text extraction is an important field in video content comprehension. In this paper, a robust video-text extraction method is presented which can automatically extract horizontally aligned text with different languages. First, an unsupervised paradigm based on Haar wavelets is applied to obtain candidate text region. Second, the traversing line with its aptitude spectrum is introduced and applied to create boundary for each text line. Last, traversing line of the maximum feature value in each refined text region is employed to seed key-points in strokes, from which region growth is performed to create binary text image. Experiments conducted with a variety of video sources show that the method is robust to text of various colors, fonts, sizes in complex image, and performs better than conventional methods. |
| doi_str_mv | 10.1109/ICOSP.2008.4697297 |
| format | Conference Proceeding |
| fullrecord | <record><control><sourceid>ieee_6IE</sourceid><recordid>TN_cdi_ieee_primary_4697297</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>4697297</ieee_id><sourcerecordid>4697297</sourcerecordid><originalsourceid>FETCH-LOGICAL-i175t-b36d21ea24c965fb600f9bcb9158b81d6c5dd6d2755408aa0da89412f626a8d3</originalsourceid><addsrcrecordid>eNpFUM1KAzEYjGjBtvYF9JIX2PX7skk2OZaitVCoYG8eSrLJarTdlU1c7Nu7asHDMAzzcxhCrhFyRNC3q8Xm6TFnACrnUpdMl2dkgpxxzrDU-vxfKLggY4aSZ4IxHJHJT0kDoiwvySzGNwAoUClZyDF5ntOutZ8x0T4439LkvxId0JkqhbahB59eW0etid7RQf_6g9v7Lobmhe5D46lpHI2pa989rdqm8UO1D-l4RUa12Uc_O_GUbO_vtouHbL1ZrhbzdRawFCmzhXQMvWG80lLUVgLU2lZWo1BWoZOVcG6IlEJwUMaAM0pzZLVk0ihXTMnN32zw3u8-unAw3XF3Oqn4BiKnWHE</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>A robust video text extraction method based on text traversing line and stroke connectivity</title><source>IEEE Electronic Library (IEL) Conference Proceedings</source><creator>Peng Tianqiang ; Tian Pohuang ; Li Bicheng</creator><creatorcontrib>Peng Tianqiang ; Tian Pohuang ; Li Bicheng</creatorcontrib><description>Automatic video-text extraction is an important field in video content comprehension. In this paper, a robust video-text extraction method is presented which can automatically extract horizontally aligned text with different languages. First, an unsupervised paradigm based on Haar wavelets is applied to obtain candidate text region. Second, the traversing line with its aptitude spectrum is introduced and applied to create boundary for each text line. Last, traversing line of the maximum feature value in each refined text region is employed to seed key-points in strokes, from which region growth is performed to create binary text image. Experiments conducted with a variety of video sources show that the method is robust to text of various colors, fonts, sizes in complex image, and performs better than conventional methods.</description><identifier>ISSN: 2164-5221</identifier><identifier>ISBN: 1424421780</identifier><identifier>ISBN: 9781424421787</identifier><identifier>EISBN: 1424421799</identifier><identifier>EISBN: 9781424421794</identifier><identifier>DOI: 10.1109/ICOSP.2008.4697297</identifier><identifier>LCCN: 2008901167</identifier><language>eng</language><publisher>IEEE</publisher><subject>Data mining ; Feature extraction ; Filters ; Image color analysis ; Image edge detection ; Indexing ; Information science ; Internet ; Robustness ; Video compression</subject><ispartof>2008 9th International Conference on Signal Processing, 2008, p.1002-1005</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/4697297$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,776,780,785,786,2052,27902,54895</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/4697297$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Peng Tianqiang</creatorcontrib><creatorcontrib>Tian Pohuang</creatorcontrib><creatorcontrib>Li Bicheng</creatorcontrib><title>A robust video text extraction method based on text traversing line and stroke connectivity</title><title>2008 9th International Conference on Signal Processing</title><addtitle>ICOSP</addtitle><description>Automatic video-text extraction is an important field in video content comprehension. In this paper, a robust video-text extraction method is presented which can automatically extract horizontally aligned text with different languages. First, an unsupervised paradigm based on Haar wavelets is applied to obtain candidate text region. Second, the traversing line with its aptitude spectrum is introduced and applied to create boundary for each text line. Last, traversing line of the maximum feature value in each refined text region is employed to seed key-points in strokes, from which region growth is performed to create binary text image. Experiments conducted with a variety of video sources show that the method is robust to text of various colors, fonts, sizes in complex image, and performs better than conventional methods.</description><subject>Data mining</subject><subject>Feature extraction</subject><subject>Filters</subject><subject>Image color analysis</subject><subject>Image edge detection</subject><subject>Indexing</subject><subject>Information science</subject><subject>Internet</subject><subject>Robustness</subject><subject>Video compression</subject><issn>2164-5221</issn><isbn>1424421780</isbn><isbn>9781424421787</isbn><isbn>1424421799</isbn><isbn>9781424421794</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2008</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><sourceid>RIE</sourceid><recordid>eNpFUM1KAzEYjGjBtvYF9JIX2PX7skk2OZaitVCoYG8eSrLJarTdlU1c7Nu7asHDMAzzcxhCrhFyRNC3q8Xm6TFnACrnUpdMl2dkgpxxzrDU-vxfKLggY4aSZ4IxHJHJT0kDoiwvySzGNwAoUClZyDF5ntOutZ8x0T4439LkvxId0JkqhbahB59eW0etid7RQf_6g9v7Lobmhe5D46lpHI2pa989rdqm8UO1D-l4RUa12Uc_O_GUbO_vtouHbL1ZrhbzdRawFCmzhXQMvWG80lLUVgLU2lZWo1BWoZOVcG6IlEJwUMaAM0pzZLVk0ihXTMnN32zw3u8-unAw3XF3Oqn4BiKnWHE</recordid><startdate>200810</startdate><enddate>200810</enddate><creator>Peng Tianqiang</creator><creator>Tian Pohuang</creator><creator>Li Bicheng</creator><general>IEEE</general><scope>6IE</scope><scope>6IL</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIL</scope></search><sort><creationdate>200810</creationdate><title>A robust video text extraction method based on text traversing line and stroke connectivity</title><author>Peng Tianqiang ; Tian Pohuang ; Li Bicheng</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i175t-b36d21ea24c965fb600f9bcb9158b81d6c5dd6d2755408aa0da89412f626a8d3</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2008</creationdate><topic>Data mining</topic><topic>Feature extraction</topic><topic>Filters</topic><topic>Image color analysis</topic><topic>Image edge detection</topic><topic>Indexing</topic><topic>Information science</topic><topic>Internet</topic><topic>Robustness</topic><topic>Video compression</topic><toplevel>online_resources</toplevel><creatorcontrib>Peng Tianqiang</creatorcontrib><creatorcontrib>Tian Pohuang</creatorcontrib><creatorcontrib>Li Bicheng</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>Peng Tianqiang</au><au>Tian Pohuang</au><au>Li Bicheng</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>A robust video text extraction method based on text traversing line and stroke connectivity</atitle><btitle>2008 9th International Conference on Signal Processing</btitle><stitle>ICOSP</stitle><date>2008-10</date><risdate>2008</risdate><spage>1002</spage><epage>1005</epage><pages>1002-1005</pages><issn>2164-5221</issn><isbn>1424421780</isbn><isbn>9781424421787</isbn><eisbn>1424421799</eisbn><eisbn>9781424421794</eisbn><abstract>Automatic video-text extraction is an important field in video content comprehension. In this paper, a robust video-text extraction method is presented which can automatically extract horizontally aligned text with different languages. First, an unsupervised paradigm based on Haar wavelets is applied to obtain candidate text region. Second, the traversing line with its aptitude spectrum is introduced and applied to create boundary for each text line. Last, traversing line of the maximum feature value in each refined text region is employed to seed key-points in strokes, from which region growth is performed to create binary text image. Experiments conducted with a variety of video sources show that the method is robust to text of various colors, fonts, sizes in complex image, and performs better than conventional methods.</abstract><pub>IEEE</pub><doi>10.1109/ICOSP.2008.4697297</doi><tpages>4</tpages></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISSN: 2164-5221 |
| ispartof | 2008 9th International Conference on Signal Processing, 2008, p.1002-1005 |
| issn | 2164-5221 |
| language | eng |
| recordid | cdi_ieee_primary_4697297 |
| source | IEEE Electronic Library (IEL) Conference Proceedings |
| subjects | Data mining Feature extraction Filters Image color analysis Image edge detection Indexing Information science Internet Robustness Video compression |
| title | A robust video text extraction method based on text traversing line and stroke connectivity |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-14T10%3A37%3A16IST&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=A%20robust%20video%20text%20extraction%20method%20based%20on%20text%20traversing%20line%20and%20stroke%20connectivity&rft.btitle=2008%209th%20International%20Conference%20on%20Signal%20Processing&rft.au=Peng%20Tianqiang&rft.date=2008-10&rft.spage=1002&rft.epage=1005&rft.pages=1002-1005&rft.issn=2164-5221&rft.isbn=1424421780&rft.isbn_list=9781424421787&rft_id=info:doi/10.1109/ICOSP.2008.4697297&rft_dat=%3Cieee_6IE%3E4697297%3C/ieee_6IE%3E%3Curl%3E%3C/url%3E&rft.eisbn=1424421799&rft.eisbn_list=9781424421794&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=4697297&rfr_iscdi=true |