Sparse Spatial Coding: A Novel Approach to Visual Recognition

Successful image-based object recognition techniques have been constructed founded on powerful techniques such as sparse representation, in lieu of the popular vector quantization approach. However, one serious drawback of sparse space-based methods is that local features that are quite similar can...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on image processing 2014-06, Vol.23 (6), p.2719-2731
Hauptverfasser: Leivas Oliveira, Gabriel, Nascimento, Erickson R., Wilson Vieira, Antonio, Montenegro Campos, Mario Fernando
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page 2731
container_issue 6
container_start_page 2719
container_title IEEE transactions on image processing
container_volume 23
creator Leivas Oliveira, Gabriel
Nascimento, Erickson R.
Wilson Vieira, Antonio
Montenegro Campos, Mario Fernando
description Successful image-based object recognition techniques have been constructed founded on powerful techniques such as sparse representation, in lieu of the popular vector quantization approach. However, one serious drawback of sparse space-based methods is that local features that are quite similar can be quantized into quite distinct visual words. We address this problem with a novel approach for object recognition, called sparse spatial coding, which efficiently combines a sparse coding dictionary learning and spatial constraint coding stage. We performed experimental evaluation using the Caltech 101, Caltech 256, Corel 5000, and Corel 10000 data sets, which were specifically designed for object recognition evaluation. Our results show that our approach achieves high accuracy comparable with the best single feature method previously published on those databases. Our method outperformed, for the same bases, several multiple feature methods, and provided equivalent, and in few cases, slightly less accurate results than other techniques specifically designed to that end. Finally, we report state-of-the-art results for scene recognition on COsy Localization Dataset (COLD) and high performance results on the MIT-67 indoor scene recognition, thus demonstrating the generalization of our approach for such tasks.
doi_str_mv 10.1109/TIP.2014.2317988
format Article
fullrecord <record><control><sourceid>proquest_RIE</sourceid><recordid>TN_cdi_crossref_primary_10_1109_TIP_2014_2317988</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>6800007</ieee_id><sourcerecordid>3377630031</sourcerecordid><originalsourceid>FETCH-LOGICAL-c377t-e1d56af8c44b837af8d15a81118e685379cc42da485c6e8afe20a7cd9e42e4cc3</originalsourceid><addsrcrecordid>eNpd0N9LwzAQB_Agij-m74IgBRF86cylSZMIPozhLxgqOn0tMb1qpGtm0wr-92ZsKpiXO8jnjuNLyD7QIQDVp9Ob-yGjwIcsA6mVWiPboDmklHK2HnsqZCqB6y2yE8I7jVJAvkm2GJc51VRvk_PHuWkDJrF0ztTJ2JeueT1LRsmt_8Q6Gc3nrTf2Lel88uxCH8kDWv_auM75ZpdsVKYOuLeqA_J0eTEdX6eTu6ub8WiS2kzKLkUoRW4qZTl_UZmMXQnCKABQmCuRSW0tZ6XhStgclamQUSNtqZEz5NZmA3Ky3BuP-egxdMXMBYt1bRr0fShAZIJRyVke6dE_-u77tonXRcWFloxRHhVdKtv6EFqsinnrZqb9KoAWi2iLGG2xiLZYRRtHDleL-5cZlr8DP1lGcLwCJlhTV61prAt_TgmmclgsOlg6h4i_37mi8cnsGyorh50</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>1545972204</pqid></control><display><type>article</type><title>Sparse Spatial Coding: A Novel Approach to Visual Recognition</title><source>IEEE Electronic Library (IEL)</source><creator>Leivas Oliveira, Gabriel ; Nascimento, Erickson R. ; Wilson Vieira, Antonio ; Montenegro Campos, Mario Fernando</creator><creatorcontrib>Leivas Oliveira, Gabriel ; Nascimento, Erickson R. ; Wilson Vieira, Antonio ; Montenegro Campos, Mario Fernando</creatorcontrib><description>Successful image-based object recognition techniques have been constructed founded on powerful techniques such as sparse representation, in lieu of the popular vector quantization approach. However, one serious drawback of sparse space-based methods is that local features that are quite similar can be quantized into quite distinct visual words. We address this problem with a novel approach for object recognition, called sparse spatial coding, which efficiently combines a sparse coding dictionary learning and spatial constraint coding stage. We performed experimental evaluation using the Caltech 101, Caltech 256, Corel 5000, and Corel 10000 data sets, which were specifically designed for object recognition evaluation. Our results show that our approach achieves high accuracy comparable with the best single feature method previously published on those databases. Our method outperformed, for the same bases, several multiple feature methods, and provided equivalent, and in few cases, slightly less accurate results than other techniques specifically designed to that end. Finally, we report state-of-the-art results for scene recognition on COsy Localization Dataset (COLD) and high performance results on the MIT-67 indoor scene recognition, thus demonstrating the generalization of our approach for such tasks.</description><identifier>ISSN: 1057-7149</identifier><identifier>EISSN: 1941-0042</identifier><identifier>DOI: 10.1109/TIP.2014.2317988</identifier><identifier>PMID: 24760909</identifier><identifier>CODEN: IIPRE4</identifier><language>eng</language><publisher>New York, NY: IEEE</publisher><subject>Accuracy ; Applied sciences ; Coding, codes ; Dictionaries ; Encoding ; Exact sciences and technology ; Feature extraction ; Image coding ; Image processing ; Information, signal and communications theory ; Object recognition ; Pattern recognition ; Physiological psychology ; Sampling, quantization ; Signal and communications theory ; Signal processing ; Telecommunications and information theory ; Vectors</subject><ispartof>IEEE transactions on image processing, 2014-06, Vol.23 (6), p.2719-2731</ispartof><rights>2015 INIST-CNRS</rights><rights>Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) Jun 2014</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c377t-e1d56af8c44b837af8d15a81118e685379cc42da485c6e8afe20a7cd9e42e4cc3</citedby><cites>FETCH-LOGICAL-c377t-e1d56af8c44b837af8d15a81118e685379cc42da485c6e8afe20a7cd9e42e4cc3</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/6800007$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>315,781,785,797,27929,27930,54763</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/6800007$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc><backlink>$$Uhttp://pascal-francis.inist.fr/vibad/index.php?action=getRecordDetail&amp;idt=28528618$$DView record in Pascal Francis$$Hfree_for_read</backlink><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/24760909$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Leivas Oliveira, Gabriel</creatorcontrib><creatorcontrib>Nascimento, Erickson R.</creatorcontrib><creatorcontrib>Wilson Vieira, Antonio</creatorcontrib><creatorcontrib>Montenegro Campos, Mario Fernando</creatorcontrib><title>Sparse Spatial Coding: A Novel Approach to Visual Recognition</title><title>IEEE transactions on image processing</title><addtitle>TIP</addtitle><addtitle>IEEE Trans Image Process</addtitle><description>Successful image-based object recognition techniques have been constructed founded on powerful techniques such as sparse representation, in lieu of the popular vector quantization approach. However, one serious drawback of sparse space-based methods is that local features that are quite similar can be quantized into quite distinct visual words. We address this problem with a novel approach for object recognition, called sparse spatial coding, which efficiently combines a sparse coding dictionary learning and spatial constraint coding stage. We performed experimental evaluation using the Caltech 101, Caltech 256, Corel 5000, and Corel 10000 data sets, which were specifically designed for object recognition evaluation. Our results show that our approach achieves high accuracy comparable with the best single feature method previously published on those databases. Our method outperformed, for the same bases, several multiple feature methods, and provided equivalent, and in few cases, slightly less accurate results than other techniques specifically designed to that end. Finally, we report state-of-the-art results for scene recognition on COsy Localization Dataset (COLD) and high performance results on the MIT-67 indoor scene recognition, thus demonstrating the generalization of our approach for such tasks.</description><subject>Accuracy</subject><subject>Applied sciences</subject><subject>Coding, codes</subject><subject>Dictionaries</subject><subject>Encoding</subject><subject>Exact sciences and technology</subject><subject>Feature extraction</subject><subject>Image coding</subject><subject>Image processing</subject><subject>Information, signal and communications theory</subject><subject>Object recognition</subject><subject>Pattern recognition</subject><subject>Physiological psychology</subject><subject>Sampling, quantization</subject><subject>Signal and communications theory</subject><subject>Signal processing</subject><subject>Telecommunications and information theory</subject><subject>Vectors</subject><issn>1057-7149</issn><issn>1941-0042</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2014</creationdate><recordtype>article</recordtype><sourceid>RIE</sourceid><recordid>eNpd0N9LwzAQB_Agij-m74IgBRF86cylSZMIPozhLxgqOn0tMb1qpGtm0wr-92ZsKpiXO8jnjuNLyD7QIQDVp9Ob-yGjwIcsA6mVWiPboDmklHK2HnsqZCqB6y2yE8I7jVJAvkm2GJc51VRvk_PHuWkDJrF0ztTJ2JeueT1LRsmt_8Q6Gc3nrTf2Lel88uxCH8kDWv_auM75ZpdsVKYOuLeqA_J0eTEdX6eTu6ub8WiS2kzKLkUoRW4qZTl_UZmMXQnCKABQmCuRSW0tZ6XhStgclamQUSNtqZEz5NZmA3Ky3BuP-egxdMXMBYt1bRr0fShAZIJRyVke6dE_-u77tonXRcWFloxRHhVdKtv6EFqsinnrZqb9KoAWi2iLGG2xiLZYRRtHDleL-5cZlr8DP1lGcLwCJlhTV61prAt_TgmmclgsOlg6h4i_37mi8cnsGyorh50</recordid><startdate>20140601</startdate><enddate>20140601</enddate><creator>Leivas Oliveira, Gabriel</creator><creator>Nascimento, Erickson R.</creator><creator>Wilson Vieira, Antonio</creator><creator>Montenegro Campos, Mario Fernando</creator><general>IEEE</general><general>Institute of Electrical and Electronics Engineers</general><general>The Institute of Electrical and Electronics Engineers, Inc. (IEEE)</general><scope>97E</scope><scope>RIA</scope><scope>RIE</scope><scope>IQODW</scope><scope>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7SC</scope><scope>7SP</scope><scope>8FD</scope><scope>JQ2</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope><scope>7X8</scope></search><sort><creationdate>20140601</creationdate><title>Sparse Spatial Coding: A Novel Approach to Visual Recognition</title><author>Leivas Oliveira, Gabriel ; Nascimento, Erickson R. ; Wilson Vieira, Antonio ; Montenegro Campos, Mario Fernando</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c377t-e1d56af8c44b837af8d15a81118e685379cc42da485c6e8afe20a7cd9e42e4cc3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2014</creationdate><topic>Accuracy</topic><topic>Applied sciences</topic><topic>Coding, codes</topic><topic>Dictionaries</topic><topic>Encoding</topic><topic>Exact sciences and technology</topic><topic>Feature extraction</topic><topic>Image coding</topic><topic>Image processing</topic><topic>Information, signal and communications theory</topic><topic>Object recognition</topic><topic>Pattern recognition</topic><topic>Physiological psychology</topic><topic>Sampling, quantization</topic><topic>Signal and communications theory</topic><topic>Signal processing</topic><topic>Telecommunications and information theory</topic><topic>Vectors</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Leivas Oliveira, Gabriel</creatorcontrib><creatorcontrib>Nascimento, Erickson R.</creatorcontrib><creatorcontrib>Wilson Vieira, Antonio</creatorcontrib><creatorcontrib>Montenegro Campos, Mario Fernando</creatorcontrib><collection>IEEE All-Society Periodicals Package (ASPP) 2005-present</collection><collection>IEEE All-Society Periodicals Package (ASPP) 1998-Present</collection><collection>IEEE Electronic Library (IEL)</collection><collection>Pascal-Francis</collection><collection>PubMed</collection><collection>CrossRef</collection><collection>Computer and Information Systems Abstracts</collection><collection>Electronics &amp; Communications Abstracts</collection><collection>Technology Research Database</collection><collection>ProQuest Computer Science Collection</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Computer and Information Systems Abstracts – Academic</collection><collection>Computer and Information Systems Abstracts Professional</collection><collection>MEDLINE - Academic</collection><jtitle>IEEE transactions on image processing</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Leivas Oliveira, Gabriel</au><au>Nascimento, Erickson R.</au><au>Wilson Vieira, Antonio</au><au>Montenegro Campos, Mario Fernando</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Sparse Spatial Coding: A Novel Approach to Visual Recognition</atitle><jtitle>IEEE transactions on image processing</jtitle><stitle>TIP</stitle><addtitle>IEEE Trans Image Process</addtitle><date>2014-06-01</date><risdate>2014</risdate><volume>23</volume><issue>6</issue><spage>2719</spage><epage>2731</epage><pages>2719-2731</pages><issn>1057-7149</issn><eissn>1941-0042</eissn><coden>IIPRE4</coden><abstract>Successful image-based object recognition techniques have been constructed founded on powerful techniques such as sparse representation, in lieu of the popular vector quantization approach. However, one serious drawback of sparse space-based methods is that local features that are quite similar can be quantized into quite distinct visual words. We address this problem with a novel approach for object recognition, called sparse spatial coding, which efficiently combines a sparse coding dictionary learning and spatial constraint coding stage. We performed experimental evaluation using the Caltech 101, Caltech 256, Corel 5000, and Corel 10000 data sets, which were specifically designed for object recognition evaluation. Our results show that our approach achieves high accuracy comparable with the best single feature method previously published on those databases. Our method outperformed, for the same bases, several multiple feature methods, and provided equivalent, and in few cases, slightly less accurate results than other techniques specifically designed to that end. Finally, we report state-of-the-art results for scene recognition on COsy Localization Dataset (COLD) and high performance results on the MIT-67 indoor scene recognition, thus demonstrating the generalization of our approach for such tasks.</abstract><cop>New York, NY</cop><pub>IEEE</pub><pmid>24760909</pmid><doi>10.1109/TIP.2014.2317988</doi><tpages>13</tpages></addata></record>
fulltext fulltext_linktorsrc
identifier ISSN: 1057-7149
ispartof IEEE transactions on image processing, 2014-06, Vol.23 (6), p.2719-2731
issn 1057-7149
1941-0042
language eng
recordid cdi_crossref_primary_10_1109_TIP_2014_2317988
source IEEE Electronic Library (IEL)
subjects Accuracy
Applied sciences
Coding, codes
Dictionaries
Encoding
Exact sciences and technology
Feature extraction
Image coding
Image processing
Information, signal and communications theory
Object recognition
Pattern recognition
Physiological psychology
Sampling, quantization
Signal and communications theory
Signal processing
Telecommunications and information theory
Vectors
title Sparse Spatial Coding: A Novel Approach to Visual Recognition
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-12T09%3A48%3A56IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_RIE&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Sparse%20Spatial%20Coding:%20A%20Novel%20Approach%20to%20Visual%20Recognition&rft.jtitle=IEEE%20transactions%20on%20image%20processing&rft.au=Leivas%20Oliveira,%20Gabriel&rft.date=2014-06-01&rft.volume=23&rft.issue=6&rft.spage=2719&rft.epage=2731&rft.pages=2719-2731&rft.issn=1057-7149&rft.eissn=1941-0042&rft.coden=IIPRE4&rft_id=info:doi/10.1109/TIP.2014.2317988&rft_dat=%3Cproquest_RIE%3E3377630031%3C/proquest_RIE%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=1545972204&rft_id=info:pmid/24760909&rft_ieee_id=6800007&rfr_iscdi=true