A Multi-Scale Parallel Convolutional Neural Network Based Intelligent Human Identification Using Face Information
Intelligent human identification using face information has been the research hotspot ranging from Internet of Things (IoT) application, intelligent self-service bank, intelligent surveillance to public safety and intelligent access control. Since 2D face images are usually captured from a long dist...
Gespeichert in:
Veröffentlicht in: | JIPS(Journal of Information Processing Systems) 2018-12, Vol.14 (6), p.1494-1507 |
---|---|
Hauptverfasser: | , , , |
Format: | Artikel |
Sprache: | kor |
Schlagworte: | |
Online-Zugang: | Volltext |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
container_end_page | 1507 |
---|---|
container_issue | 6 |
container_start_page | 1494 |
container_title | JIPS(Journal of Information Processing Systems) |
container_volume | 14 |
creator | Li, Chen Liang, Mengti Song, Wei Xiao, Ke |
description | Intelligent human identification using face information has been the research hotspot ranging from Internet of Things (IoT) application, intelligent self-service bank, intelligent surveillance to public safety and intelligent access control. Since 2D face images are usually captured from a long distance in an unconstrained environment, to fully exploit this advantage and make human recognition appropriate for wider intelligent applications with higher security and convenience, the key difficulties here include gray scale change caused by illumination variance, occlusion caused by glasses, hair or scarf, self-occlusion and deformation caused by pose or expression variation. To conquer these, many solutions have been proposed. However, most of them only improve recognition performance under one influence factor, which still cannot meet the real face recognition scenario. In this paper we propose a multi-scale parallel convolutional neural network architecture to extract deep robust facial features with high discriminative ability. Abundant experiments are conducted on CMU-PIE, extended FERET and AR database. And the experiment results show that the proposed algorithm exhibits excellent discriminative ability compared with other existing algorithms. |
format | Article |
fullrecord | <record><control><sourceid>kiss_kisti</sourceid><recordid>TN_cdi_kisti_ndsl_JAKO201810866006591</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><kiss_id>3650075</kiss_id><sourcerecordid>3650075</sourcerecordid><originalsourceid>FETCH-LOGICAL-k501-6d72986303d472e95d333f75a6e6228c05f2d2b835f132a91aa8214429470d513</originalsourceid><addsrcrecordid>eNo9kEFLAzEUhIMoWGp_gZdcPC4kL5tscqzF2mq1ghV6W1432RKaZnWzq_jvbat4mmH4Zg5zRgbADGSayfU5GXBTqMxwsb4ko5T8hrFCSgVcDsjHmD71ofPZa4XB0RdsMQQX6KSJn03oO99EDPTZ9e1Juq-m3dFbTM7SeexcCH7rYkdn_R4jnduD97Wv8Nijb8nHLZ1i5Q5s3bT7U3xFLmoMyY3-dEhW07vVZJYtlvfzyXiR7STjmbIFGK0EEzYvwBlphRB1IVE5BaArJmuwsNFC1lwAGo6ogec5mLxgVnIxJDe_szufOl9Gm0L5MH5cAuOaM60UY0qaI3f9z6XyvfV7bL9LoeTxJPEDBq9fIg</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>A Multi-Scale Parallel Convolutional Neural Network Based Intelligent Human Identification Using Face Information</title><source>Elektronische Zeitschriftenbibliothek - Frei zugängliche E-Journals</source><creator>Li, Chen ; Liang, Mengti ; Song, Wei ; Xiao, Ke</creator><creatorcontrib>Li, Chen ; Liang, Mengti ; Song, Wei ; Xiao, Ke</creatorcontrib><description>Intelligent human identification using face information has been the research hotspot ranging from Internet of Things (IoT) application, intelligent self-service bank, intelligent surveillance to public safety and intelligent access control. Since 2D face images are usually captured from a long distance in an unconstrained environment, to fully exploit this advantage and make human recognition appropriate for wider intelligent applications with higher security and convenience, the key difficulties here include gray scale change caused by illumination variance, occlusion caused by glasses, hair or scarf, self-occlusion and deformation caused by pose or expression variation. To conquer these, many solutions have been proposed. However, most of them only improve recognition performance under one influence factor, which still cannot meet the real face recognition scenario. In this paper we propose a multi-scale parallel convolutional neural network architecture to extract deep robust facial features with high discriminative ability. Abundant experiments are conducted on CMU-PIE, extended FERET and AR database. And the experiment results show that the proposed algorithm exhibits excellent discriminative ability compared with other existing algorithms.</description><identifier>ISSN: 1976-913X</identifier><identifier>EISSN: 2092-805X</identifier><language>kor</language><publisher>한국정보처리학회</publisher><subject>Face Recognition ; Intelligent Human Identification ; MP-CNN ; Robust Feature</subject><ispartof>JIPS(Journal of Information Processing Systems), 2018-12, Vol.14 (6), p.1494-1507</ispartof><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>230,314,776,780,881</link.rule.ids></links><search><creatorcontrib>Li, Chen</creatorcontrib><creatorcontrib>Liang, Mengti</creatorcontrib><creatorcontrib>Song, Wei</creatorcontrib><creatorcontrib>Xiao, Ke</creatorcontrib><title>A Multi-Scale Parallel Convolutional Neural Network Based Intelligent Human Identification Using Face Information</title><title>JIPS(Journal of Information Processing Systems)</title><addtitle>JIPS(Journal of Information Processing Systems)</addtitle><description>Intelligent human identification using face information has been the research hotspot ranging from Internet of Things (IoT) application, intelligent self-service bank, intelligent surveillance to public safety and intelligent access control. Since 2D face images are usually captured from a long distance in an unconstrained environment, to fully exploit this advantage and make human recognition appropriate for wider intelligent applications with higher security and convenience, the key difficulties here include gray scale change caused by illumination variance, occlusion caused by glasses, hair or scarf, self-occlusion and deformation caused by pose or expression variation. To conquer these, many solutions have been proposed. However, most of them only improve recognition performance under one influence factor, which still cannot meet the real face recognition scenario. In this paper we propose a multi-scale parallel convolutional neural network architecture to extract deep robust facial features with high discriminative ability. Abundant experiments are conducted on CMU-PIE, extended FERET and AR database. And the experiment results show that the proposed algorithm exhibits excellent discriminative ability compared with other existing algorithms.</description><subject>Face Recognition</subject><subject>Intelligent Human Identification</subject><subject>MP-CNN</subject><subject>Robust Feature</subject><issn>1976-913X</issn><issn>2092-805X</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2018</creationdate><recordtype>article</recordtype><sourceid>JDI</sourceid><recordid>eNo9kEFLAzEUhIMoWGp_gZdcPC4kL5tscqzF2mq1ghV6W1432RKaZnWzq_jvbat4mmH4Zg5zRgbADGSayfU5GXBTqMxwsb4ko5T8hrFCSgVcDsjHmD71ofPZa4XB0RdsMQQX6KSJn03oO99EDPTZ9e1Juq-m3dFbTM7SeexcCH7rYkdn_R4jnduD97Wv8Nijb8nHLZ1i5Q5s3bT7U3xFLmoMyY3-dEhW07vVZJYtlvfzyXiR7STjmbIFGK0EEzYvwBlphRB1IVE5BaArJmuwsNFC1lwAGo6ogec5mLxgVnIxJDe_szufOl9Gm0L5MH5cAuOaM60UY0qaI3f9z6XyvfV7bL9LoeTxJPEDBq9fIg</recordid><startdate>20181231</startdate><enddate>20181231</enddate><creator>Li, Chen</creator><creator>Liang, Mengti</creator><creator>Song, Wei</creator><creator>Xiao, Ke</creator><general>한국정보처리학회</general><scope>HZB</scope><scope>Q5X</scope><scope>JDI</scope></search><sort><creationdate>20181231</creationdate><title>A Multi-Scale Parallel Convolutional Neural Network Based Intelligent Human Identification Using Face Information</title><author>Li, Chen ; Liang, Mengti ; Song, Wei ; Xiao, Ke</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-k501-6d72986303d472e95d333f75a6e6228c05f2d2b835f132a91aa8214429470d513</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>kor</language><creationdate>2018</creationdate><topic>Face Recognition</topic><topic>Intelligent Human Identification</topic><topic>MP-CNN</topic><topic>Robust Feature</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Li, Chen</creatorcontrib><creatorcontrib>Liang, Mengti</creatorcontrib><creatorcontrib>Song, Wei</creatorcontrib><creatorcontrib>Xiao, Ke</creatorcontrib><collection>Korea Information Science Society (KISS)</collection><collection>Korean Studies Information Service System (KISS) B-Type</collection><collection>KoreaScience</collection><jtitle>JIPS(Journal of Information Processing Systems)</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Li, Chen</au><au>Liang, Mengti</au><au>Song, Wei</au><au>Xiao, Ke</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>A Multi-Scale Parallel Convolutional Neural Network Based Intelligent Human Identification Using Face Information</atitle><jtitle>JIPS(Journal of Information Processing Systems)</jtitle><addtitle>JIPS(Journal of Information Processing Systems)</addtitle><date>2018-12-31</date><risdate>2018</risdate><volume>14</volume><issue>6</issue><spage>1494</spage><epage>1507</epage><pages>1494-1507</pages><issn>1976-913X</issn><eissn>2092-805X</eissn><abstract>Intelligent human identification using face information has been the research hotspot ranging from Internet of Things (IoT) application, intelligent self-service bank, intelligent surveillance to public safety and intelligent access control. Since 2D face images are usually captured from a long distance in an unconstrained environment, to fully exploit this advantage and make human recognition appropriate for wider intelligent applications with higher security and convenience, the key difficulties here include gray scale change caused by illumination variance, occlusion caused by glasses, hair or scarf, self-occlusion and deformation caused by pose or expression variation. To conquer these, many solutions have been proposed. However, most of them only improve recognition performance under one influence factor, which still cannot meet the real face recognition scenario. In this paper we propose a multi-scale parallel convolutional neural network architecture to extract deep robust facial features with high discriminative ability. Abundant experiments are conducted on CMU-PIE, extended FERET and AR database. And the experiment results show that the proposed algorithm exhibits excellent discriminative ability compared with other existing algorithms.</abstract><pub>한국정보처리학회</pub><tpages>14</tpages><oa>free_for_read</oa></addata></record> |
fulltext | fulltext |
identifier | ISSN: 1976-913X |
ispartof | JIPS(Journal of Information Processing Systems), 2018-12, Vol.14 (6), p.1494-1507 |
issn | 1976-913X 2092-805X |
language | kor |
recordid | cdi_kisti_ndsl_JAKO201810866006591 |
source | Elektronische Zeitschriftenbibliothek - Frei zugängliche E-Journals |
subjects | Face Recognition Intelligent Human Identification MP-CNN Robust Feature |
title | A Multi-Scale Parallel Convolutional Neural Network Based Intelligent Human Identification Using Face Information |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-30T02%3A34%3A08IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-kiss_kisti&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=A%20Multi-Scale%20Parallel%20Convolutional%20Neural%20Network%20Based%20Intelligent%20Human%20Identification%20Using%20Face%20Information&rft.jtitle=JIPS(Journal%20of%20Information%20Processing%20Systems)&rft.au=Li,%20Chen&rft.date=2018-12-31&rft.volume=14&rft.issue=6&rft.spage=1494&rft.epage=1507&rft.pages=1494-1507&rft.issn=1976-913X&rft.eissn=2092-805X&rft_id=info:doi/&rft_dat=%3Ckiss_kisti%3E3650075%3C/kiss_kisti%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_kiss_id=3650075&rfr_iscdi=true |