Feature redundancy approach to efficient face recognition in still images

This paper proposes the use of redundant features for efficient recognition of faces in still images using a novel system framework that offers a detailed systematic workflow for solving the facial recognition problem. It accepts still frontal face images, processes and represents salient facial fea...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:SN applied sciences 2019-06, Vol.1 (6), p.543, Article 543
Hauptverfasser: Ekpenyong, Moses E., Wilson, Philip M., Brown, Aniekan S.
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue 6
container_start_page 543
container_title SN applied sciences
container_volume 1
creator Ekpenyong, Moses E.
Wilson, Philip M.
Brown, Aniekan S.
description This paper proposes the use of redundant features for efficient recognition of faces in still images using a novel system framework that offers a detailed systematic workflow for solving the facial recognition problem. It accepts still frontal face images, processes and represents salient facial features (face, eyes, nose, and mouth) using facial detection and extraction techniques. The extracted features are then modeled by an ensemble of self-organizing maps. The ensemble outputs are later reassembled into a single dataset consisting of a normalized image Euclidean distance matrix to enhance the search space for optimal convergence and classification. The feasibility of the framework is tested using an experiment facial database captured during the study, and three benchmark facial expression databases, namely the Extended Cohn–Kanade (CK+) database, the Japanese Female Facial Expressions database, and the MMI Facial Expression database. The results suggest that feature redundancy is indeed useful for efficient facial recognition, as the support vector machine classification recorded high accuracies across the various databases, with the normalized image Euclidean distance dataset producing the highest performance, when compared with the localized principal component analysis and unnormalized image Euclidean distance datasets. Furthermore, overall classification accuracy of above 99% was achieved for the experiment (nonexpressive still face) database, compared with the benchmark facial expression databases, which yielded slightly lower results. A future direction of this work is further improvement of the framework to robustly handle severe facial variations.
doi_str_mv 10.1007/s42452-019-0525-1
format Article
fullrecord <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_journals_2788456775</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2788456775</sourcerecordid><originalsourceid>FETCH-LOGICAL-c311t-d683fb248e56d47ac5e56405bced9e5a95f1387dd5c263c54428b8690df74a813</originalsourceid><addsrcrecordid>eNp1kE1LAzEYhIMoWGp_gLeA59V8brJHKVYLBS96Dtl81JSarUn20H9vlhU9eXrnMDPv8ABwi9E9Rkg8ZEYYJw3CXYM44Q2-AAvCCW1oJ_Dlr27pNVjlfEAIEdFRJukCbDdOlzE5mJwdo9XRnKE-ndKgzQcsA3TeBxNcLNBrM7nMsI-hhCHCEGEu4XiE4VPvXb4BV14fs1v93CV43zy9rV-a3evzdv24awzFuDS2ldT3hEnHW8uENrwKhnhvnO0c1x33mEphLTekpYYzRmQv2w5ZL5iWmC7B3dxbR36NLhd1GMYU60tFhJSMt0Lw6sKzy6Qh5-S8OqW6M50VRmqCpmZoqkJTEzQ1NZM5k6s37l36a_4_9A1utW5-</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2788456775</pqid></control><display><type>article</type><title>Feature redundancy approach to efficient face recognition in still images</title><source>EZB-FREE-00999 freely available EZB journals</source><creator>Ekpenyong, Moses E. ; Wilson, Philip M. ; Brown, Aniekan S.</creator><creatorcontrib>Ekpenyong, Moses E. ; Wilson, Philip M. ; Brown, Aniekan S.</creatorcontrib><description>This paper proposes the use of redundant features for efficient recognition of faces in still images using a novel system framework that offers a detailed systematic workflow for solving the facial recognition problem. It accepts still frontal face images, processes and represents salient facial features (face, eyes, nose, and mouth) using facial detection and extraction techniques. The extracted features are then modeled by an ensemble of self-organizing maps. The ensemble outputs are later reassembled into a single dataset consisting of a normalized image Euclidean distance matrix to enhance the search space for optimal convergence and classification. The feasibility of the framework is tested using an experiment facial database captured during the study, and three benchmark facial expression databases, namely the Extended Cohn–Kanade (CK+) database, the Japanese Female Facial Expressions database, and the MMI Facial Expression database. The results suggest that feature redundancy is indeed useful for efficient facial recognition, as the support vector machine classification recorded high accuracies across the various databases, with the normalized image Euclidean distance dataset producing the highest performance, when compared with the localized principal component analysis and unnormalized image Euclidean distance datasets. Furthermore, overall classification accuracy of above 99% was achieved for the experiment (nonexpressive still face) database, compared with the benchmark facial expression databases, which yielded slightly lower results. A future direction of this work is further improvement of the framework to robustly handle severe facial variations.</description><identifier>ISSN: 2523-3963</identifier><identifier>EISSN: 2523-3971</identifier><identifier>DOI: 10.1007/s42452-019-0525-1</identifier><language>eng</language><publisher>Cham: Springer International Publishing</publisher><subject>Access control ; Accuracy ; Algorithms ; Applied and Technical Physics ; Benchmarks ; Biometrics ; Chemistry/Food Science ; Classification ; Cooperation ; Datasets ; Earth Sciences ; Engineering ; Engineering: Artificial Intelligence ; Environment ; Euclidean geometry ; Face ; Face recognition ; Facial recognition technology ; Feature extraction ; Feature recognition ; Image enhancement ; Image processing ; Materials Science ; Pattern recognition ; Principal components analysis ; Psychologists ; Redundancy ; Research Article ; Self organizing maps ; Support vector machines ; Surveillance ; Workflow</subject><ispartof>SN applied sciences, 2019-06, Vol.1 (6), p.543, Article 543</ispartof><rights>Springer Nature Switzerland AG 2019</rights><rights>Springer Nature Switzerland AG 2019.</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><cites>FETCH-LOGICAL-c311t-d683fb248e56d47ac5e56405bced9e5a95f1387dd5c263c54428b8690df74a813</cites><orcidid>0000-0001-6774-5259</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,780,784,27924,27925</link.rule.ids></links><search><creatorcontrib>Ekpenyong, Moses E.</creatorcontrib><creatorcontrib>Wilson, Philip M.</creatorcontrib><creatorcontrib>Brown, Aniekan S.</creatorcontrib><title>Feature redundancy approach to efficient face recognition in still images</title><title>SN applied sciences</title><addtitle>SN Appl. Sci</addtitle><description>This paper proposes the use of redundant features for efficient recognition of faces in still images using a novel system framework that offers a detailed systematic workflow for solving the facial recognition problem. It accepts still frontal face images, processes and represents salient facial features (face, eyes, nose, and mouth) using facial detection and extraction techniques. The extracted features are then modeled by an ensemble of self-organizing maps. The ensemble outputs are later reassembled into a single dataset consisting of a normalized image Euclidean distance matrix to enhance the search space for optimal convergence and classification. The feasibility of the framework is tested using an experiment facial database captured during the study, and three benchmark facial expression databases, namely the Extended Cohn–Kanade (CK+) database, the Japanese Female Facial Expressions database, and the MMI Facial Expression database. The results suggest that feature redundancy is indeed useful for efficient facial recognition, as the support vector machine classification recorded high accuracies across the various databases, with the normalized image Euclidean distance dataset producing the highest performance, when compared with the localized principal component analysis and unnormalized image Euclidean distance datasets. Furthermore, overall classification accuracy of above 99% was achieved for the experiment (nonexpressive still face) database, compared with the benchmark facial expression databases, which yielded slightly lower results. A future direction of this work is further improvement of the framework to robustly handle severe facial variations.</description><subject>Access control</subject><subject>Accuracy</subject><subject>Algorithms</subject><subject>Applied and Technical Physics</subject><subject>Benchmarks</subject><subject>Biometrics</subject><subject>Chemistry/Food Science</subject><subject>Classification</subject><subject>Cooperation</subject><subject>Datasets</subject><subject>Earth Sciences</subject><subject>Engineering</subject><subject>Engineering: Artificial Intelligence</subject><subject>Environment</subject><subject>Euclidean geometry</subject><subject>Face</subject><subject>Face recognition</subject><subject>Facial recognition technology</subject><subject>Feature extraction</subject><subject>Feature recognition</subject><subject>Image enhancement</subject><subject>Image processing</subject><subject>Materials Science</subject><subject>Pattern recognition</subject><subject>Principal components analysis</subject><subject>Psychologists</subject><subject>Redundancy</subject><subject>Research Article</subject><subject>Self organizing maps</subject><subject>Support vector machines</subject><subject>Surveillance</subject><subject>Workflow</subject><issn>2523-3963</issn><issn>2523-3971</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2019</creationdate><recordtype>article</recordtype><recordid>eNp1kE1LAzEYhIMoWGp_gLeA59V8brJHKVYLBS96Dtl81JSarUn20H9vlhU9eXrnMDPv8ABwi9E9Rkg8ZEYYJw3CXYM44Q2-AAvCCW1oJ_Dlr27pNVjlfEAIEdFRJukCbDdOlzE5mJwdo9XRnKE-ndKgzQcsA3TeBxNcLNBrM7nMsI-hhCHCEGEu4XiE4VPvXb4BV14fs1v93CV43zy9rV-a3evzdv24awzFuDS2ldT3hEnHW8uENrwKhnhvnO0c1x33mEphLTekpYYzRmQv2w5ZL5iWmC7B3dxbR36NLhd1GMYU60tFhJSMt0Lw6sKzy6Qh5-S8OqW6M50VRmqCpmZoqkJTEzQ1NZM5k6s37l36a_4_9A1utW5-</recordid><startdate>20190601</startdate><enddate>20190601</enddate><creator>Ekpenyong, Moses E.</creator><creator>Wilson, Philip M.</creator><creator>Brown, Aniekan S.</creator><general>Springer International Publishing</general><general>Springer Nature B.V</general><scope>AAYXX</scope><scope>CITATION</scope><orcidid>https://orcid.org/0000-0001-6774-5259</orcidid></search><sort><creationdate>20190601</creationdate><title>Feature redundancy approach to efficient face recognition in still images</title><author>Ekpenyong, Moses E. ; Wilson, Philip M. ; Brown, Aniekan S.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c311t-d683fb248e56d47ac5e56405bced9e5a95f1387dd5c263c54428b8690df74a813</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2019</creationdate><topic>Access control</topic><topic>Accuracy</topic><topic>Algorithms</topic><topic>Applied and Technical Physics</topic><topic>Benchmarks</topic><topic>Biometrics</topic><topic>Chemistry/Food Science</topic><topic>Classification</topic><topic>Cooperation</topic><topic>Datasets</topic><topic>Earth Sciences</topic><topic>Engineering</topic><topic>Engineering: Artificial Intelligence</topic><topic>Environment</topic><topic>Euclidean geometry</topic><topic>Face</topic><topic>Face recognition</topic><topic>Facial recognition technology</topic><topic>Feature extraction</topic><topic>Feature recognition</topic><topic>Image enhancement</topic><topic>Image processing</topic><topic>Materials Science</topic><topic>Pattern recognition</topic><topic>Principal components analysis</topic><topic>Psychologists</topic><topic>Redundancy</topic><topic>Research Article</topic><topic>Self organizing maps</topic><topic>Support vector machines</topic><topic>Surveillance</topic><topic>Workflow</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Ekpenyong, Moses E.</creatorcontrib><creatorcontrib>Wilson, Philip M.</creatorcontrib><creatorcontrib>Brown, Aniekan S.</creatorcontrib><collection>CrossRef</collection><jtitle>SN applied sciences</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Ekpenyong, Moses E.</au><au>Wilson, Philip M.</au><au>Brown, Aniekan S.</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Feature redundancy approach to efficient face recognition in still images</atitle><jtitle>SN applied sciences</jtitle><stitle>SN Appl. Sci</stitle><date>2019-06-01</date><risdate>2019</risdate><volume>1</volume><issue>6</issue><spage>543</spage><pages>543-</pages><artnum>543</artnum><issn>2523-3963</issn><eissn>2523-3971</eissn><abstract>This paper proposes the use of redundant features for efficient recognition of faces in still images using a novel system framework that offers a detailed systematic workflow for solving the facial recognition problem. It accepts still frontal face images, processes and represents salient facial features (face, eyes, nose, and mouth) using facial detection and extraction techniques. The extracted features are then modeled by an ensemble of self-organizing maps. The ensemble outputs are later reassembled into a single dataset consisting of a normalized image Euclidean distance matrix to enhance the search space for optimal convergence and classification. The feasibility of the framework is tested using an experiment facial database captured during the study, and three benchmark facial expression databases, namely the Extended Cohn–Kanade (CK+) database, the Japanese Female Facial Expressions database, and the MMI Facial Expression database. The results suggest that feature redundancy is indeed useful for efficient facial recognition, as the support vector machine classification recorded high accuracies across the various databases, with the normalized image Euclidean distance dataset producing the highest performance, when compared with the localized principal component analysis and unnormalized image Euclidean distance datasets. Furthermore, overall classification accuracy of above 99% was achieved for the experiment (nonexpressive still face) database, compared with the benchmark facial expression databases, which yielded slightly lower results. A future direction of this work is further improvement of the framework to robustly handle severe facial variations.</abstract><cop>Cham</cop><pub>Springer International Publishing</pub><doi>10.1007/s42452-019-0525-1</doi><orcidid>https://orcid.org/0000-0001-6774-5259</orcidid><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier ISSN: 2523-3963
ispartof SN applied sciences, 2019-06, Vol.1 (6), p.543, Article 543
issn 2523-3963
2523-3971
language eng
recordid cdi_proquest_journals_2788456775
source EZB-FREE-00999 freely available EZB journals
subjects Access control
Accuracy
Algorithms
Applied and Technical Physics
Benchmarks
Biometrics
Chemistry/Food Science
Classification
Cooperation
Datasets
Earth Sciences
Engineering
Engineering: Artificial Intelligence
Environment
Euclidean geometry
Face
Face recognition
Facial recognition technology
Feature extraction
Feature recognition
Image enhancement
Image processing
Materials Science
Pattern recognition
Principal components analysis
Psychologists
Redundancy
Research Article
Self organizing maps
Support vector machines
Surveillance
Workflow
title Feature redundancy approach to efficient face recognition in still images
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-24T02%3A08%3A53IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Feature%20redundancy%20approach%20to%20efficient%20face%20recognition%20in%20still%20images&rft.jtitle=SN%20applied%20sciences&rft.au=Ekpenyong,%20Moses%20E.&rft.date=2019-06-01&rft.volume=1&rft.issue=6&rft.spage=543&rft.pages=543-&rft.artnum=543&rft.issn=2523-3963&rft.eissn=2523-3971&rft_id=info:doi/10.1007/s42452-019-0525-1&rft_dat=%3Cproquest_cross%3E2788456775%3C/proquest_cross%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2788456775&rft_id=info:pmid/&rfr_iscdi=true