Script identification using steerable Gabor filters
Multi-channel Gabor filtering has been widely used in texture classification. In this paper, Gabor filters have been applied to the problem of script identification in printed documents. Our work is divided into two stages. Firstly, a Gabor filter bank is appropriately designed so that extracted rot...
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 | 887 Vol. 2 |
|---|---|
| container_issue | |
| container_start_page | 883 |
| container_title | |
| container_volume | |
| creator | Pan, W.M. Suen, C.Y. Bui, T.D. |
| description | Multi-channel Gabor filtering has been widely used in texture classification. In this paper, Gabor filters have been applied to the problem of script identification in printed documents. Our work is divided into two stages. Firstly, a Gabor filter bank is appropriately designed so that extracted rotation-invariant features can handle scripts that are similar in shape and even share many characters. Secondly, the steerability property of Gabor filters is exploited to reduce the high computation cost resulted from the frequent image filtering, which is a common problem encountered in Gabor filter related applications. Results from preliminary experiments are quite promising, where Chinese, Japanese, Korean and English are considered. Over 98.5 % language identification rate can be achieved while image filtering operations have been reduced by 40%. |
| doi_str_mv | 10.1109/ICDAR.2005.206 |
| format | Conference Proceeding |
| fullrecord | <record><control><sourceid>ieee_6IE</sourceid><recordid>TN_cdi_ieee_primary_1575671</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>1575671</ieee_id><sourcerecordid>1575671</sourcerecordid><originalsourceid>FETCH-LOGICAL-i175t-cae9cfb40d62773f900c8874cb8abcc047105d26b9d56d6737415251a0a010943</originalsourceid><addsrcrecordid>eNotj0tLxDAUhYMPsIzdunHTP9Dx5nFzm-VQdRwYEHyshyRNJVI7QxIX_nsLehbn2x2-w9gNhzXnYO52_f3mZS0AcCl9xiohybSCKzhntaEOSBsUSgBdsIqjgBallleszvkTlijkJFXF5KtP8VSaOIS5xDF6W-Jxbr5znD-aXEJI1k2h2Vp3TM0YpxJSvmaXo51yqP-5Yu-PD2_9U7t_3u76zb6NnLC03gbjR6dg0IJIjgbAdx0p7zrrvAdFHHAQ2pkB9aBJklpEkVuwsFxUcsVu_3ZjCOFwSvHLpp8DR0JNXP4CqlZGMQ</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Script identification using steerable Gabor filters</title><source>IEEE Electronic Library (IEL) Conference Proceedings</source><creator>Pan, W.M. ; Suen, C.Y. ; Bui, T.D.</creator><creatorcontrib>Pan, W.M. ; Suen, C.Y. ; Bui, T.D.</creatorcontrib><description>Multi-channel Gabor filtering has been widely used in texture classification. In this paper, Gabor filters have been applied to the problem of script identification in printed documents. Our work is divided into two stages. Firstly, a Gabor filter bank is appropriately designed so that extracted rotation-invariant features can handle scripts that are similar in shape and even share many characters. Secondly, the steerability property of Gabor filters is exploited to reduce the high computation cost resulted from the frequent image filtering, which is a common problem encountered in Gabor filter related applications. Results from preliminary experiments are quite promising, where Chinese, Japanese, Korean and English are considered. Over 98.5 % language identification rate can be achieved while image filtering operations have been reduced by 40%.</description><identifier>ISSN: 1520-5363</identifier><identifier>ISBN: 9780769524207</identifier><identifier>ISBN: 0769524206</identifier><identifier>EISSN: 2379-2140</identifier><identifier>DOI: 10.1109/ICDAR.2005.206</identifier><language>eng</language><publisher>IEEE</publisher><subject>Computational efficiency ; Computer science ; Feature extraction ; Filter bank ; Filtering ; Gabor filters ; Machine intelligence ; Natural languages ; Pattern recognition ; Shape</subject><ispartof>Eighth International Conference on Document Analysis and Recognition (ICDAR'05), 2005, p.883-887 Vol. 2</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/1575671$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,776,780,785,786,2052,4036,4037,27902,54895</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/1575671$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Pan, W.M.</creatorcontrib><creatorcontrib>Suen, C.Y.</creatorcontrib><creatorcontrib>Bui, T.D.</creatorcontrib><title>Script identification using steerable Gabor filters</title><title>Eighth International Conference on Document Analysis and Recognition (ICDAR'05)</title><addtitle>ICDAR</addtitle><description>Multi-channel Gabor filtering has been widely used in texture classification. In this paper, Gabor filters have been applied to the problem of script identification in printed documents. Our work is divided into two stages. Firstly, a Gabor filter bank is appropriately designed so that extracted rotation-invariant features can handle scripts that are similar in shape and even share many characters. Secondly, the steerability property of Gabor filters is exploited to reduce the high computation cost resulted from the frequent image filtering, which is a common problem encountered in Gabor filter related applications. Results from preliminary experiments are quite promising, where Chinese, Japanese, Korean and English are considered. Over 98.5 % language identification rate can be achieved while image filtering operations have been reduced by 40%.</description><subject>Computational efficiency</subject><subject>Computer science</subject><subject>Feature extraction</subject><subject>Filter bank</subject><subject>Filtering</subject><subject>Gabor filters</subject><subject>Machine intelligence</subject><subject>Natural languages</subject><subject>Pattern recognition</subject><subject>Shape</subject><issn>1520-5363</issn><issn>2379-2140</issn><isbn>9780769524207</isbn><isbn>0769524206</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2005</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><sourceid>RIE</sourceid><recordid>eNotj0tLxDAUhYMPsIzdunHTP9Dx5nFzm-VQdRwYEHyshyRNJVI7QxIX_nsLehbn2x2-w9gNhzXnYO52_f3mZS0AcCl9xiohybSCKzhntaEOSBsUSgBdsIqjgBallleszvkTlijkJFXF5KtP8VSaOIS5xDF6W-Jxbr5znD-aXEJI1k2h2Vp3TM0YpxJSvmaXo51yqP-5Yu-PD2_9U7t_3u76zb6NnLC03gbjR6dg0IJIjgbAdx0p7zrrvAdFHHAQ2pkB9aBJklpEkVuwsFxUcsVu_3ZjCOFwSvHLpp8DR0JNXP4CqlZGMQ</recordid><startdate>2005</startdate><enddate>2005</enddate><creator>Pan, W.M.</creator><creator>Suen, C.Y.</creator><creator>Bui, T.D.</creator><general>IEEE</general><scope>6IE</scope><scope>6IL</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIL</scope></search><sort><creationdate>2005</creationdate><title>Script identification using steerable Gabor filters</title><author>Pan, W.M. ; Suen, C.Y. ; Bui, T.D.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i175t-cae9cfb40d62773f900c8874cb8abcc047105d26b9d56d6737415251a0a010943</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2005</creationdate><topic>Computational efficiency</topic><topic>Computer science</topic><topic>Feature extraction</topic><topic>Filter bank</topic><topic>Filtering</topic><topic>Gabor filters</topic><topic>Machine intelligence</topic><topic>Natural languages</topic><topic>Pattern recognition</topic><topic>Shape</topic><toplevel>online_resources</toplevel><creatorcontrib>Pan, W.M.</creatorcontrib><creatorcontrib>Suen, C.Y.</creatorcontrib><creatorcontrib>Bui, T.D.</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>Pan, W.M.</au><au>Suen, C.Y.</au><au>Bui, T.D.</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Script identification using steerable Gabor filters</atitle><btitle>Eighth International Conference on Document Analysis and Recognition (ICDAR'05)</btitle><stitle>ICDAR</stitle><date>2005</date><risdate>2005</risdate><spage>883</spage><epage>887 Vol. 2</epage><pages>883-887 Vol. 2</pages><issn>1520-5363</issn><eissn>2379-2140</eissn><isbn>9780769524207</isbn><isbn>0769524206</isbn><abstract>Multi-channel Gabor filtering has been widely used in texture classification. In this paper, Gabor filters have been applied to the problem of script identification in printed documents. Our work is divided into two stages. Firstly, a Gabor filter bank is appropriately designed so that extracted rotation-invariant features can handle scripts that are similar in shape and even share many characters. Secondly, the steerability property of Gabor filters is exploited to reduce the high computation cost resulted from the frequent image filtering, which is a common problem encountered in Gabor filter related applications. Results from preliminary experiments are quite promising, where Chinese, Japanese, Korean and English are considered. Over 98.5 % language identification rate can be achieved while image filtering operations have been reduced by 40%.</abstract><pub>IEEE</pub><doi>10.1109/ICDAR.2005.206</doi></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISSN: 1520-5363 |
| ispartof | Eighth International Conference on Document Analysis and Recognition (ICDAR'05), 2005, p.883-887 Vol. 2 |
| issn | 1520-5363 2379-2140 |
| language | eng |
| recordid | cdi_ieee_primary_1575671 |
| source | IEEE Electronic Library (IEL) Conference Proceedings |
| subjects | Computational efficiency Computer science Feature extraction Filter bank Filtering Gabor filters Machine intelligence Natural languages Pattern recognition Shape |
| title | Script identification using steerable Gabor filters |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-09T19%3A27%3A17IST&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=Script%20identification%20using%20steerable%20Gabor%20filters&rft.btitle=Eighth%20International%20Conference%20on%20Document%20Analysis%20and%20Recognition%20(ICDAR'05)&rft.au=Pan,%20W.M.&rft.date=2005&rft.spage=883&rft.epage=887%20Vol.%202&rft.pages=883-887%20Vol.%202&rft.issn=1520-5363&rft.eissn=2379-2140&rft.isbn=9780769524207&rft.isbn_list=0769524206&rft_id=info:doi/10.1109/ICDAR.2005.206&rft_dat=%3Cieee_6IE%3E1575671%3C/ieee_6IE%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=1575671&rfr_iscdi=true |