Automated Information Mining on Multimedia TV News Archives
This paper addresses an integrated information mining techniques for multimedia TV-news archive. The utilizes techniques from the fields of acoustic, image, and video analysis, for information retrieval on news story title, newsman and scene identification. The goal is to construct a compact yet mea...
Gespeichert in:
| Veröffentlicht in: | Knowledge-Based Intelligent Information and Engineering Systems 2005, p.1238-1244 |
|---|---|
| Hauptverfasser: | , , , , , , , , , , , , , , , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 1244 |
|---|---|
| container_issue | |
| container_start_page | 1238 |
| container_title | Knowledge-Based Intelligent Information and Engineering Systems |
| container_volume | |
| creator | Lai, P. S. Cheng, S. S. Sun, S. Y. Huang, T. Y. Su, J. M. Xu, Y. Y. Chen, Y. H. Chuang, S. C. Tseng, C. L. Hsieh, C. L. Lu, Y. L. Shen, Y. C. Chen, J. R. Nie, J. B. Tsai, F. P. Huang, H. C. Pao, H. T. Fu, Hsin-Chia |
| description | This paper addresses an integrated information mining techniques for multimedia TV-news archive. The utilizes techniques from the fields of acoustic, image, and video analysis, for information retrieval on news story title, newsman and scene identification. The goal is to construct a compact yet meaningful abstraction of broadcast news video, allowing users to browse through large amounts of data in a non-linear fashion with flexibility and efficiency. By using acoustic analysis, the system can classify video into news versus commercials, with 90% accuracy on a data set of 400 hours TV-news recorded off the air from July 2003 to August of 2004. By applying speaker identification and/or image detection techniques, each news stories can be segmented with an accuracy of 96%. On screen captions or subtitles are recognized by OCR techniques to produce the text title of each news stories. The extracted title words can be used to link or to navigate more related News contents on the WWW. In cooperation with facial and scene analysis and recognition techniques, OCR results can provide users with multimodality query for specific news stories. Some experimental results are presented and discussed for the system reliability and performance evaluation and comparison. |
| doi_str_mv | 10.1007/11552451_171 |
| format | Article |
| fullrecord | <record><control><sourceid>springer</sourceid><recordid>TN_cdi_springer_books_10_1007_11552451_171</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>springer_books_10_1007_11552451_171</sourcerecordid><originalsourceid>FETCH-LOGICAL-s190t-86c0e17e78535868dcfd5319c99a0371d335d919980529a602bd6421f085c35b3</originalsourceid><addsrcrecordid>eNpNkE9Lw0AUxNd_YK25-QFyFqLv5eXt7sNTKVULVS_Va0iyG422iWRT_fqm6MG5zMDA8GOUukC4QgBzjcicZow5GjxQkRhLnAGhWE2HaoIaMSHK5Eid7YvUWmE6VhMgSBMxGZ2qKIR3GEVoWfRE3cx2Q7ctBu_iZVt3_Ribro0fmrZpX-N92m2GZutdU8Trl_jRf4d41ldvzZcP5-qkLjbBR38-Vc-3i_X8Plk93S3ns1USUGBIrK7Ao_HGMrHV1lW14xG6EimADDoidoIiFjiVQkNaOp2lWIPlirikqbr83Q2f_Ujl-7zsuo-QI-T7W_L_t9AP38RNaw</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Automated Information Mining on Multimedia TV News Archives</title><source>Springer Books</source><creator>Lai, P. S. ; Cheng, S. S. ; Sun, S. Y. ; Huang, T. Y. ; Su, J. M. ; Xu, Y. Y. ; Chen, Y. H. ; Chuang, S. C. ; Tseng, C. L. ; Hsieh, C. L. ; Lu, Y. L. ; Shen, Y. C. ; Chen, J. R. ; Nie, J. B. ; Tsai, F. P. ; Huang, H. C. ; Pao, H. T. ; Fu, Hsin-Chia</creator><contributor>Howlett, Robert J. ; Jain, Lakhmi C. ; Khosla, Rajiv</contributor><creatorcontrib>Lai, P. S. ; Cheng, S. S. ; Sun, S. Y. ; Huang, T. Y. ; Su, J. M. ; Xu, Y. Y. ; Chen, Y. H. ; Chuang, S. C. ; Tseng, C. L. ; Hsieh, C. L. ; Lu, Y. L. ; Shen, Y. C. ; Chen, J. R. ; Nie, J. B. ; Tsai, F. P. ; Huang, H. C. ; Pao, H. T. ; Fu, Hsin-Chia ; Howlett, Robert J. ; Jain, Lakhmi C. ; Khosla, Rajiv</creatorcontrib><description>This paper addresses an integrated information mining techniques for multimedia TV-news archive. The utilizes techniques from the fields of acoustic, image, and video analysis, for information retrieval on news story title, newsman and scene identification. The goal is to construct a compact yet meaningful abstraction of broadcast news video, allowing users to browse through large amounts of data in a non-linear fashion with flexibility and efficiency. By using acoustic analysis, the system can classify video into news versus commercials, with 90% accuracy on a data set of 400 hours TV-news recorded off the air from July 2003 to August of 2004. By applying speaker identification and/or image detection techniques, each news stories can be segmented with an accuracy of 96%. On screen captions or subtitles are recognized by OCR techniques to produce the text title of each news stories. The extracted title words can be used to link or to navigate more related News contents on the WWW. In cooperation with facial and scene analysis and recognition techniques, OCR results can provide users with multimodality query for specific news stories. Some experimental results are presented and discussed for the system reliability and performance evaluation and comparison.</description><identifier>ISSN: 0302-9743</identifier><identifier>ISBN: 3540288953</identifier><identifier>ISBN: 9783540288954</identifier><identifier>EISSN: 1611-3349</identifier><identifier>EISBN: 9783540319863</identifier><identifier>EISBN: 3540319867</identifier><identifier>DOI: 10.1007/11552451_171</identifier><language>eng</language><publisher>Berlin, Heidelberg: Springer Berlin Heidelberg</publisher><subject>News Program ; News Story ; News Video ; Semantic Label ; Video Clip</subject><ispartof>Knowledge-Based Intelligent Information and Engineering Systems, 2005, p.1238-1244</ispartof><rights>Springer-Verlag Berlin Heidelberg 2005</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://link.springer.com/content/pdf/10.1007/11552451_171$$EPDF$$P50$$Gspringer$$H</linktopdf><linktohtml>$$Uhttps://link.springer.com/10.1007/11552451_171$$EHTML$$P50$$Gspringer$$H</linktohtml><link.rule.ids>779,780,784,793,27923,38253,41440,42509</link.rule.ids></links><search><contributor>Howlett, Robert J.</contributor><contributor>Jain, Lakhmi C.</contributor><contributor>Khosla, Rajiv</contributor><creatorcontrib>Lai, P. S.</creatorcontrib><creatorcontrib>Cheng, S. S.</creatorcontrib><creatorcontrib>Sun, S. Y.</creatorcontrib><creatorcontrib>Huang, T. Y.</creatorcontrib><creatorcontrib>Su, J. M.</creatorcontrib><creatorcontrib>Xu, Y. Y.</creatorcontrib><creatorcontrib>Chen, Y. H.</creatorcontrib><creatorcontrib>Chuang, S. C.</creatorcontrib><creatorcontrib>Tseng, C. L.</creatorcontrib><creatorcontrib>Hsieh, C. L.</creatorcontrib><creatorcontrib>Lu, Y. L.</creatorcontrib><creatorcontrib>Shen, Y. C.</creatorcontrib><creatorcontrib>Chen, J. R.</creatorcontrib><creatorcontrib>Nie, J. B.</creatorcontrib><creatorcontrib>Tsai, F. P.</creatorcontrib><creatorcontrib>Huang, H. C.</creatorcontrib><creatorcontrib>Pao, H. T.</creatorcontrib><creatorcontrib>Fu, Hsin-Chia</creatorcontrib><title>Automated Information Mining on Multimedia TV News Archives</title><title>Knowledge-Based Intelligent Information and Engineering Systems</title><description>This paper addresses an integrated information mining techniques for multimedia TV-news archive. The utilizes techniques from the fields of acoustic, image, and video analysis, for information retrieval on news story title, newsman and scene identification. The goal is to construct a compact yet meaningful abstraction of broadcast news video, allowing users to browse through large amounts of data in a non-linear fashion with flexibility and efficiency. By using acoustic analysis, the system can classify video into news versus commercials, with 90% accuracy on a data set of 400 hours TV-news recorded off the air from July 2003 to August of 2004. By applying speaker identification and/or image detection techniques, each news stories can be segmented with an accuracy of 96%. On screen captions or subtitles are recognized by OCR techniques to produce the text title of each news stories. The extracted title words can be used to link or to navigate more related News contents on the WWW. In cooperation with facial and scene analysis and recognition techniques, OCR results can provide users with multimodality query for specific news stories. Some experimental results are presented and discussed for the system reliability and performance evaluation and comparison.</description><subject>News Program</subject><subject>News Story</subject><subject>News Video</subject><subject>Semantic Label</subject><subject>Video Clip</subject><issn>0302-9743</issn><issn>1611-3349</issn><isbn>3540288953</isbn><isbn>9783540288954</isbn><isbn>9783540319863</isbn><isbn>3540319867</isbn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2005</creationdate><recordtype>article</recordtype><sourceid/><recordid>eNpNkE9Lw0AUxNd_YK25-QFyFqLv5eXt7sNTKVULVS_Va0iyG422iWRT_fqm6MG5zMDA8GOUukC4QgBzjcicZow5GjxQkRhLnAGhWE2HaoIaMSHK5Eid7YvUWmE6VhMgSBMxGZ2qKIR3GEVoWfRE3cx2Q7ctBu_iZVt3_Ribro0fmrZpX-N92m2GZutdU8Trl_jRf4d41ldvzZcP5-qkLjbBR38-Vc-3i_X8Plk93S3ns1USUGBIrK7Ao_HGMrHV1lW14xG6EimADDoidoIiFjiVQkNaOp2lWIPlirikqbr83Q2f_Ujl-7zsuo-QI-T7W_L_t9AP38RNaw</recordid><startdate>2005</startdate><enddate>2005</enddate><creator>Lai, P. S.</creator><creator>Cheng, S. S.</creator><creator>Sun, S. Y.</creator><creator>Huang, T. Y.</creator><creator>Su, J. M.</creator><creator>Xu, Y. Y.</creator><creator>Chen, Y. H.</creator><creator>Chuang, S. C.</creator><creator>Tseng, C. L.</creator><creator>Hsieh, C. L.</creator><creator>Lu, Y. L.</creator><creator>Shen, Y. C.</creator><creator>Chen, J. R.</creator><creator>Nie, J. B.</creator><creator>Tsai, F. P.</creator><creator>Huang, H. C.</creator><creator>Pao, H. T.</creator><creator>Fu, Hsin-Chia</creator><general>Springer Berlin Heidelberg</general><scope/></search><sort><creationdate>2005</creationdate><title>Automated Information Mining on Multimedia TV News Archives</title><author>Lai, P. S. ; Cheng, S. S. ; Sun, S. Y. ; Huang, T. Y. ; Su, J. M. ; Xu, Y. Y. ; Chen, Y. H. ; Chuang, S. C. ; Tseng, C. L. ; Hsieh, C. L. ; Lu, Y. L. ; Shen, Y. C. ; Chen, J. R. ; Nie, J. B. ; Tsai, F. P. ; Huang, H. C. ; Pao, H. T. ; Fu, Hsin-Chia</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-s190t-86c0e17e78535868dcfd5319c99a0371d335d919980529a602bd6421f085c35b3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2005</creationdate><topic>News Program</topic><topic>News Story</topic><topic>News Video</topic><topic>Semantic Label</topic><topic>Video Clip</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Lai, P. S.</creatorcontrib><creatorcontrib>Cheng, S. S.</creatorcontrib><creatorcontrib>Sun, S. Y.</creatorcontrib><creatorcontrib>Huang, T. Y.</creatorcontrib><creatorcontrib>Su, J. M.</creatorcontrib><creatorcontrib>Xu, Y. Y.</creatorcontrib><creatorcontrib>Chen, Y. H.</creatorcontrib><creatorcontrib>Chuang, S. C.</creatorcontrib><creatorcontrib>Tseng, C. L.</creatorcontrib><creatorcontrib>Hsieh, C. L.</creatorcontrib><creatorcontrib>Lu, Y. L.</creatorcontrib><creatorcontrib>Shen, Y. C.</creatorcontrib><creatorcontrib>Chen, J. R.</creatorcontrib><creatorcontrib>Nie, J. B.</creatorcontrib><creatorcontrib>Tsai, F. P.</creatorcontrib><creatorcontrib>Huang, H. C.</creatorcontrib><creatorcontrib>Pao, H. T.</creatorcontrib><creatorcontrib>Fu, Hsin-Chia</creatorcontrib><jtitle>Knowledge-Based Intelligent Information and Engineering Systems</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Lai, P. S.</au><au>Cheng, S. S.</au><au>Sun, S. Y.</au><au>Huang, T. Y.</au><au>Su, J. M.</au><au>Xu, Y. Y.</au><au>Chen, Y. H.</au><au>Chuang, S. C.</au><au>Tseng, C. L.</au><au>Hsieh, C. L.</au><au>Lu, Y. L.</au><au>Shen, Y. C.</au><au>Chen, J. R.</au><au>Nie, J. B.</au><au>Tsai, F. P.</au><au>Huang, H. C.</au><au>Pao, H. T.</au><au>Fu, Hsin-Chia</au><au>Howlett, Robert J.</au><au>Jain, Lakhmi C.</au><au>Khosla, Rajiv</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Automated Information Mining on Multimedia TV News Archives</atitle><jtitle>Knowledge-Based Intelligent Information and Engineering Systems</jtitle><date>2005</date><risdate>2005</risdate><spage>1238</spage><epage>1244</epage><pages>1238-1244</pages><issn>0302-9743</issn><eissn>1611-3349</eissn><isbn>3540288953</isbn><isbn>9783540288954</isbn><eisbn>9783540319863</eisbn><eisbn>3540319867</eisbn><abstract>This paper addresses an integrated information mining techniques for multimedia TV-news archive. The utilizes techniques from the fields of acoustic, image, and video analysis, for information retrieval on news story title, newsman and scene identification. The goal is to construct a compact yet meaningful abstraction of broadcast news video, allowing users to browse through large amounts of data in a non-linear fashion with flexibility and efficiency. By using acoustic analysis, the system can classify video into news versus commercials, with 90% accuracy on a data set of 400 hours TV-news recorded off the air from July 2003 to August of 2004. By applying speaker identification and/or image detection techniques, each news stories can be segmented with an accuracy of 96%. On screen captions or subtitles are recognized by OCR techniques to produce the text title of each news stories. The extracted title words can be used to link or to navigate more related News contents on the WWW. In cooperation with facial and scene analysis and recognition techniques, OCR results can provide users with multimodality query for specific news stories. Some experimental results are presented and discussed for the system reliability and performance evaluation and comparison.</abstract><cop>Berlin, Heidelberg</cop><pub>Springer Berlin Heidelberg</pub><doi>10.1007/11552451_171</doi><tpages>7</tpages></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 0302-9743 |
| ispartof | Knowledge-Based Intelligent Information and Engineering Systems, 2005, p.1238-1244 |
| issn | 0302-9743 1611-3349 |
| language | eng |
| recordid | cdi_springer_books_10_1007_11552451_171 |
| source | Springer Books |
| subjects | News Program News Story News Video Semantic Label Video Clip |
| title | Automated Information Mining on Multimedia TV News Archives |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-09T17%3A51%3A11IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-springer&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Automated%20Information%20Mining%20on%20Multimedia%20TV%20News%20Archives&rft.jtitle=Knowledge-Based%20Intelligent%20Information%20and%20Engineering%20Systems&rft.au=Lai,%20P.%20S.&rft.date=2005&rft.spage=1238&rft.epage=1244&rft.pages=1238-1244&rft.issn=0302-9743&rft.eissn=1611-3349&rft.isbn=3540288953&rft.isbn_list=9783540288954&rft_id=info:doi/10.1007/11552451_171&rft_dat=%3Cspringer%3Espringer_books_10_1007_11552451_171%3C/springer%3E%3Curl%3E%3C/url%3E&rft.eisbn=9783540319863&rft.eisbn_list=3540319867&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true |