Loading…
Frequency domain feature-based face recognition technique for different poses and low-resolution conditions
Pose variations are known to give real challenges in face recognition system. In this paper we proposed a method to recognize non-frontal faces with high performance by relying only on single full frontal gallery faces. By utilizing only small regions of the face or patches, we compute the Fourier c...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Conference Proceeding |
| Language: | English |
| Subjects: | |
| Online Access: | Request full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| cited_by | |
|---|---|
| cites | |
| container_end_page | 326 |
| container_issue | |
| container_start_page | 322 |
| container_title | |
| container_volume | |
| creator | Shahdi, S. O. Abu-Bakar, S. A. R. |
| description | Pose variations are known to give real challenges in face recognition system. In this paper we proposed a method to recognize non-frontal faces with high performance by relying only on single full frontal gallery faces. By utilizing only small regions of the face or patches, we compute the Fourier coefficients of these patches for each image and transform them into a single vector. Hence, instead of comparing and matching pixels values we use these vectors to form a linear relationship which is then used to estimate the frontal face vector and then compare it with the actual frontal feature vector. The results show an average performance accuracy of 90% across all pose. |
| doi_str_mv | 10.1109/IST.2011.5962222 |
| format | conference_proceeding |
| fullrecord | <record><control><sourceid>ieee_6IE</sourceid><recordid>TN_cdi_ieee_primary_5962222</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>5962222</ieee_id><sourcerecordid>5962222</sourcerecordid><originalsourceid>FETCH-LOGICAL-i90t-67cb4cb0a838eb25d02d93c7976fc4a5a4bc762161ffafebf539bbf39ebbc4343</originalsourceid><addsrcrecordid>eNpVkEtPAjEcxOsrkSB3Ey_9Aot97rZHQwRJSDzInfTxr1ahxXaJ4du7QS7OZQ6T3yQzCN1TMqWU6Mfl23rKCKVTqVs26AJNdKdoS5kSSkt2iUZMcdYIJtjVv0zIazSiUqqGKaJv0aTWTzKobTWjaoS-5gW-D5DcEfu8MzHhAKY_FGisqeBxMA5wAZffU-xjTrgH95HigOCQC_YxBCiQerzPFSo2yeNt_mkK1Lw9nACXkz-h9Q7dBLOtMDn7GK3nz-vZS7N6XSxnT6smatI3beescJYYxRVYJj1hXnPX6a4NThhphHVdy4aBIZgANkiurQ1cg7VOcMHH6OGvNgLAZl_izpTj5vwc_wUAVmCO</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Frequency domain feature-based face recognition technique for different poses and low-resolution conditions</title><source>IEEE Electronic Library (IEL) Conference Proceedings</source><creator>Shahdi, S. O. ; Abu-Bakar, S. A. R.</creator><creatorcontrib>Shahdi, S. O. ; Abu-Bakar, S. A. R.</creatorcontrib><description>Pose variations are known to give real challenges in face recognition system. In this paper we proposed a method to recognize non-frontal faces with high performance by relying only on single full frontal gallery faces. By utilizing only small regions of the face or patches, we compute the Fourier coefficients of these patches for each image and transform them into a single vector. Hence, instead of comparing and matching pixels values we use these vectors to form a linear relationship which is then used to estimate the frontal face vector and then compare it with the actual frontal feature vector. The results show an average performance accuracy of 90% across all pose.</description><identifier>ISSN: 1558-2809</identifier><identifier>ISBN: 9781612848945</identifier><identifier>ISBN: 161284894X</identifier><identifier>EISSN: 2832-4242</identifier><identifier>EISBN: 9781612848952</identifier><identifier>EISBN: 9781612848969</identifier><identifier>EISBN: 1612848958</identifier><identifier>EISBN: 1612848966</identifier><identifier>DOI: 10.1109/IST.2011.5962222</identifier><language>eng</language><publisher>IEEE</publisher><subject>Face ; Face recognition ; Feature extraction ; frequency domain ; local regions (patches) ; mapping coefficient ; Training ; varying pose ; Vectors</subject><ispartof>2011 IEEE International Conference on Imaging Systems and Techniques, 2011, p.322-326</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/5962222$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,780,784,789,790,2058,27925,54920</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/5962222$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Shahdi, S. O.</creatorcontrib><creatorcontrib>Abu-Bakar, S. A. R.</creatorcontrib><title>Frequency domain feature-based face recognition technique for different poses and low-resolution conditions</title><title>2011 IEEE International Conference on Imaging Systems and Techniques</title><addtitle>IST</addtitle><description>Pose variations are known to give real challenges in face recognition system. In this paper we proposed a method to recognize non-frontal faces with high performance by relying only on single full frontal gallery faces. By utilizing only small regions of the face or patches, we compute the Fourier coefficients of these patches for each image and transform them into a single vector. Hence, instead of comparing and matching pixels values we use these vectors to form a linear relationship which is then used to estimate the frontal face vector and then compare it with the actual frontal feature vector. The results show an average performance accuracy of 90% across all pose.</description><subject>Face</subject><subject>Face recognition</subject><subject>Feature extraction</subject><subject>frequency domain</subject><subject>local regions (patches)</subject><subject>mapping coefficient</subject><subject>Training</subject><subject>varying pose</subject><subject>Vectors</subject><issn>1558-2809</issn><issn>2832-4242</issn><isbn>9781612848945</isbn><isbn>161284894X</isbn><isbn>9781612848952</isbn><isbn>9781612848969</isbn><isbn>1612848958</isbn><isbn>1612848966</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2011</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><recordid>eNpVkEtPAjEcxOsrkSB3Ey_9Aot97rZHQwRJSDzInfTxr1ahxXaJ4du7QS7OZQ6T3yQzCN1TMqWU6Mfl23rKCKVTqVs26AJNdKdoS5kSSkt2iUZMcdYIJtjVv0zIazSiUqqGKaJv0aTWTzKobTWjaoS-5gW-D5DcEfu8MzHhAKY_FGisqeBxMA5wAZffU-xjTrgH95HigOCQC_YxBCiQerzPFSo2yeNt_mkK1Lw9nACXkz-h9Q7dBLOtMDn7GK3nz-vZS7N6XSxnT6smatI3beescJYYxRVYJj1hXnPX6a4NThhphHVdy4aBIZgANkiurQ1cg7VOcMHH6OGvNgLAZl_izpTj5vwc_wUAVmCO</recordid><startdate>201105</startdate><enddate>201105</enddate><creator>Shahdi, S. O.</creator><creator>Abu-Bakar, S. A. R.</creator><general>IEEE</general><scope>6IE</scope><scope>6IL</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIL</scope></search><sort><creationdate>201105</creationdate><title>Frequency domain feature-based face recognition technique for different poses and low-resolution conditions</title><author>Shahdi, S. O. ; Abu-Bakar, S. A. R.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i90t-67cb4cb0a838eb25d02d93c7976fc4a5a4bc762161ffafebf539bbf39ebbc4343</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2011</creationdate><topic>Face</topic><topic>Face recognition</topic><topic>Feature extraction</topic><topic>frequency domain</topic><topic>local regions (patches)</topic><topic>mapping coefficient</topic><topic>Training</topic><topic>varying pose</topic><topic>Vectors</topic><toplevel>online_resources</toplevel><creatorcontrib>Shahdi, S. O.</creatorcontrib><creatorcontrib>Abu-Bakar, S. A. R.</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/IET 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>Shahdi, S. O.</au><au>Abu-Bakar, S. A. R.</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Frequency domain feature-based face recognition technique for different poses and low-resolution conditions</atitle><btitle>2011 IEEE International Conference on Imaging Systems and Techniques</btitle><stitle>IST</stitle><date>2011-05</date><risdate>2011</risdate><spage>322</spage><epage>326</epage><pages>322-326</pages><issn>1558-2809</issn><eissn>2832-4242</eissn><isbn>9781612848945</isbn><isbn>161284894X</isbn><eisbn>9781612848952</eisbn><eisbn>9781612848969</eisbn><eisbn>1612848958</eisbn><eisbn>1612848966</eisbn><abstract>Pose variations are known to give real challenges in face recognition system. In this paper we proposed a method to recognize non-frontal faces with high performance by relying only on single full frontal gallery faces. By utilizing only small regions of the face or patches, we compute the Fourier coefficients of these patches for each image and transform them into a single vector. Hence, instead of comparing and matching pixels values we use these vectors to form a linear relationship which is then used to estimate the frontal face vector and then compare it with the actual frontal feature vector. The results show an average performance accuracy of 90% across all pose.</abstract><pub>IEEE</pub><doi>10.1109/IST.2011.5962222</doi><tpages>5</tpages></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISSN: 1558-2809 |
| ispartof | 2011 IEEE International Conference on Imaging Systems and Techniques, 2011, p.322-326 |
| issn | 1558-2809 2832-4242 |
| language | eng |
| recordid | cdi_ieee_primary_5962222 |
| source | IEEE Electronic Library (IEL) Conference Proceedings |
| subjects | Face Face recognition Feature extraction frequency domain local regions (patches) mapping coefficient Training varying pose Vectors |
| title | Frequency domain feature-based face recognition technique for different poses and low-resolution conditions |
| url | http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-01T17%3A26%3A59IST&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=Frequency%20domain%20feature-based%20face%20recognition%20technique%20for%20different%20poses%20and%20low-resolution%20conditions&rft.btitle=2011%20IEEE%20International%20Conference%20on%20Imaging%20Systems%20and%20Techniques&rft.au=Shahdi,%20S.%20O.&rft.date=2011-05&rft.spage=322&rft.epage=326&rft.pages=322-326&rft.issn=1558-2809&rft.eissn=2832-4242&rft.isbn=9781612848945&rft.isbn_list=161284894X&rft_id=info:doi/10.1109/IST.2011.5962222&rft.eisbn=9781612848952&rft.eisbn_list=9781612848969&rft.eisbn_list=1612848958&rft.eisbn_list=1612848966&rft_dat=%3Cieee_6IE%3E5962222%3C/ieee_6IE%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-i90t-67cb4cb0a838eb25d02d93c7976fc4a5a4bc762161ffafebf539bbf39ebbc4343%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=5962222&rfr_iscdi=true |