Facial expression recognition using optimized active regions View Full Text


Ontology type: schema:ScholarlyArticle      Open Access: True


Article Info

DATE

2018-12

AUTHORS

Ai Sun, Yingjian Li, Yueh-Min Huang, Qiong Li, Guangming Lu

ABSTRACT

In this paper, we report an effective facial expression recognition system for classifying six or seven basic expressions accurately. Instead of using the whole face region, we define three kinds of active regions, i.e., left eye regions, right eye regions and mouth regions. We propose a method to search optimized active regions from the three kinds of active regions. A Convolutional Neural Network (CNN) is trained for each kind of optimized active regions to extract features and classify expressions. In order to get representable features, histogram equalization, rotation correction and spatial normalization are carried out on the expression images. A decision-level fusion method is applied, by which the final result of expression recognition is obtained via majority voting of the three CNNs’ results. Experiments on both independent databases and fused database are carried out to evaluate the performance of the proposed system. Our novel method achieves higher accuracy compared to previous literature, with the added benefit of low latency for inference. More... »

PAGES

33

References to SciGraph publications

  • 2012-03. Automatic facial expression recognition: feature extraction and selection in SIGNAL, IMAGE AND VIDEO PROCESSING
  • 2004-05. Robust Real-Time Face Detection in INTERNATIONAL JOURNAL OF COMPUTER VISION
  • 2018-10-06. Facial Expression Recognition with Inconsistently Annotated Datasets in COMPUTER VISION – ECCV 2018
  • Identifiers

    URI

    http://scigraph.springernature.com/pub.10.1186/s13673-018-0156-3

    DOI

    http://dx.doi.org/10.1186/s13673-018-0156-3

    DIMENSIONS

    https://app.dimensions.ai/details/publication/pub.1107916777


    Indexing Status Check whether this publication has been indexed by Scopus and Web Of Science using the SN Indexing Status Tool
    Incoming Citations Browse incoming citations for this publication using opencitations.net

    JSON-LD is the canonical representation for SciGraph data.

    TIP: You can open this SciGraph record using an external JSON-LD service: JSON-LD Playground Google SDTT

    [
      {
        "@context": "https://springernature.github.io/scigraph/jsonld/sgcontext.json", 
        "about": [
          {
            "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/0801", 
            "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
            "name": "Artificial Intelligence and Image Processing", 
            "type": "DefinedTerm"
          }, 
          {
            "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/08", 
            "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
            "name": "Information and Computing Sciences", 
            "type": "DefinedTerm"
          }
        ], 
        "author": [
          {
            "affiliation": {
              "alternateName": "National Cheng Kung University", 
              "id": "https://www.grid.ac/institutes/grid.64523.36", 
              "name": [
                "Department of Engineering Science, National Cheng Kung University, Tainan, Taiwan"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Sun", 
            "givenName": "Ai", 
            "id": "sg:person.013722753401.35", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013722753401.35"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Harbin Institute of Technology", 
              "id": "https://www.grid.ac/institutes/grid.19373.3f", 
              "name": [
                "School of Computer Science and Technology, Harbin Institute of Technology (Shenzhen), Shenzhen, China"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Li", 
            "givenName": "Yingjian", 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "National Cheng Kung University", 
              "id": "https://www.grid.ac/institutes/grid.64523.36", 
              "name": [
                "Department of Engineering Science, National Cheng Kung University, Tainan, Taiwan"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Huang", 
            "givenName": "Yueh-Min", 
            "id": "sg:person.07472307645.25", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.07472307645.25"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Harbin Institute of Technology", 
              "id": "https://www.grid.ac/institutes/grid.19373.3f", 
              "name": [
                "School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Li", 
            "givenName": "Qiong", 
            "id": "sg:person.016400453677.62", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016400453677.62"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Harbin Institute of Technology", 
              "id": "https://www.grid.ac/institutes/grid.19373.3f", 
              "name": [
                "School of Computer Science and Technology, Harbin Institute of Technology (Shenzhen), Shenzhen, China"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Lu", 
            "givenName": "Guangming", 
            "type": "Person"
          }
        ], 
        "citation": [
          {
            "id": "sg:pub.10.1023/b:visi.0000013087.49260.fb", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1001944608", 
              "https://doi.org/10.1023/b:visi.0000013087.49260.fb"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/j.patcog.2016.07.026", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1002713133"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1145/2043674.2043723", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1016238969"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/j.patcog.2007.02.021", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1026418119"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/s1077-3142(03)00081-x", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1028049386"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/s1077-3142(03)00081-x", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1028049386"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/s11760-010-0177-5", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1033898562", 
              "https://doi.org/10.1007/s11760-010-0177-5"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/0169-7439(87)80084-9", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1042687678"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/j.eswa.2012.07.074", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1043267745"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1037/0033-2909.115.2.288", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1046870290"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/j.imavis.2008.08.005", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1047925989"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/j.neucom.2015.10.139", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1052842820"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/mcg.2012.41", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1061391950"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/t-affc.2010.1", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1061446947"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/t-affc.2011.13", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1061446964"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/taffc.2014.2346515", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1061486973"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/taffc.2014.2386334", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1061486981"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/taffc.2015.2446462", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1061487015"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/taffc.2016.2593719", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1061487080"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/tcyb.2014.2354351", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1061579797"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/tip.2012.2235848", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1061643448"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/tip.2012.2235848", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1061643448"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/tip.2012.2235848", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1061643448"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/tmm.2010.2060716", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1061697759"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/tpami.2005.93", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1061742948"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/tpami.2007.1110", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1061743235"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/tsmcb.2004.825931", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1061796303"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/tsmcb.2005.859075", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1061796558"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.4218/etrij.10.1510.0132", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1072378768"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/j.neucom.2017.08.043", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1091499366"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/afgr.1998.670990", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1093464914"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/mlsp.2004.1423017", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1093635197"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/wacv.2016.7477450", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1093795554"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/cgiv.2016.33", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1093923455"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/cvpr.2014.233", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1093956274"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/icosp.2012.6491797", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1094163014"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/amfg.2003.1240820", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1094172500"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/cvpr.2005.297", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1094248762"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/cvpr.2005.457", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1094277104"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/cvpr.2005.457", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1094277104"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/afgr.2000.840611", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1094698009"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/rcar.2016.7784056", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1094752703"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/afgr.1998.670949", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1094774708"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/cvprw.2010.5543262", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1094866068"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/icme.2005.1521424", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1094872563"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/fcv.2015.7103729", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1095095853"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/confluence.2017.7943228", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1095190028"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/iccsp.2016.7754178", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1095257512"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/icip.2005.1530069", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1095302795"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/fg.2017.23", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1095474554"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/cvprw.2006.85", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1095752754"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-030-01261-8_14", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1107502664", 
              "https://doi.org/10.1007/978-3-030-01261-8_14"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-030-01261-8_14", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1107502664", 
              "https://doi.org/10.1007/978-3-030-01261-8_14"
            ], 
            "type": "CreativeWork"
          }
        ], 
        "datePublished": "2018-12", 
        "datePublishedReg": "2018-12-01", 
        "description": "In this paper, we report an effective facial expression recognition system for classifying six or seven basic expressions accurately. Instead of using the whole face region, we define three kinds of active regions, i.e., left eye regions, right eye regions and mouth regions. We propose a method to search optimized active regions from the three kinds of active regions. A Convolutional Neural Network (CNN) is trained for each kind of optimized active regions to extract features and classify expressions. In order to get representable features, histogram equalization, rotation correction and spatial normalization are carried out on the expression images. A decision-level fusion method is applied, by which the final result of expression recognition is obtained via majority voting of the three CNNs\u2019 results. Experiments on both independent databases and fused database are carried out to evaluate the performance of the proposed system. Our novel method achieves higher accuracy compared to previous literature, with the added benefit of low latency for inference.", 
        "genre": "research_article", 
        "id": "sg:pub.10.1186/s13673-018-0156-3", 
        "inLanguage": [
          "en"
        ], 
        "isAccessibleForFree": true, 
        "isPartOf": [
          {
            "id": "sg:journal.1136381", 
            "issn": [
              "2192-1962", 
              "2192-1962"
            ], 
            "name": "Human-centric Computing and Information Sciences", 
            "type": "Periodical"
          }, 
          {
            "issueNumber": "1", 
            "type": "PublicationIssue"
          }, 
          {
            "type": "PublicationVolume", 
            "volumeNumber": "8"
          }
        ], 
        "name": "Facial expression recognition using optimized active regions", 
        "pagination": "33", 
        "productId": [
          {
            "name": "readcube_id", 
            "type": "PropertyValue", 
            "value": [
              "7b197a1785d8035ed5a2a8ac94798a395eb50af55a844345833bb9b6f4dfcd30"
            ]
          }, 
          {
            "name": "doi", 
            "type": "PropertyValue", 
            "value": [
              "10.1186/s13673-018-0156-3"
            ]
          }, 
          {
            "name": "dimensions_id", 
            "type": "PropertyValue", 
            "value": [
              "pub.1107916777"
            ]
          }
        ], 
        "sameAs": [
          "https://doi.org/10.1186/s13673-018-0156-3", 
          "https://app.dimensions.ai/details/publication/pub.1107916777"
        ], 
        "sdDataset": "articles", 
        "sdDatePublished": "2019-04-10T21:55", 
        "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
        "sdPublisher": {
          "name": "Springer Nature - SN SciGraph project", 
          "type": "Organization"
        }, 
        "sdSource": "s3://com-uberresearch-data-dimensions-target-20181106-alternative/cleanup/v134/2549eaecd7973599484d7c17b260dba0a4ecb94b/merge/v9/a6c9fde33151104705d4d7ff012ea9563521a3ce/jats-lookup/v90/0000000001_0000000264/records_8687_00000610.jsonl", 
        "type": "ScholarlyArticle", 
        "url": "https://link.springer.com/10.1186%2Fs13673-018-0156-3"
      }
    ]
     

    Download the RDF metadata as:  json-ld nt turtle xml License info

    HOW TO GET THIS DATA PROGRAMMATICALLY:

    JSON-LD is a popular format for linked data which is fully compatible with JSON.

    curl -H 'Accept: application/ld+json' 'https://scigraph.springernature.com/pub.10.1186/s13673-018-0156-3'

    N-Triples is a line-based linked data format ideal for batch operations.

    curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1186/s13673-018-0156-3'

    Turtle is a human-readable linked data format.

    curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1186/s13673-018-0156-3'

    RDF/XML is a standard XML format for linked data.

    curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1186/s13673-018-0156-3'


     

    This table displays all metadata directly associated to this object as RDF triples.

    237 TRIPLES      21 PREDICATES      75 URIs      19 LITERALS      7 BLANK NODES

    Subject Predicate Object
    1 sg:pub.10.1186/s13673-018-0156-3 schema:about anzsrc-for:08
    2 anzsrc-for:0801
    3 schema:author N03dc9863ae6d4e32804b581bace628fa
    4 schema:citation sg:pub.10.1007/978-3-030-01261-8_14
    5 sg:pub.10.1007/s11760-010-0177-5
    6 sg:pub.10.1023/b:visi.0000013087.49260.fb
    7 https://doi.org/10.1016/0169-7439(87)80084-9
    8 https://doi.org/10.1016/j.eswa.2012.07.074
    9 https://doi.org/10.1016/j.imavis.2008.08.005
    10 https://doi.org/10.1016/j.neucom.2015.10.139
    11 https://doi.org/10.1016/j.neucom.2017.08.043
    12 https://doi.org/10.1016/j.patcog.2007.02.021
    13 https://doi.org/10.1016/j.patcog.2016.07.026
    14 https://doi.org/10.1016/s1077-3142(03)00081-x
    15 https://doi.org/10.1037/0033-2909.115.2.288
    16 https://doi.org/10.1109/afgr.1998.670949
    17 https://doi.org/10.1109/afgr.1998.670990
    18 https://doi.org/10.1109/afgr.2000.840611
    19 https://doi.org/10.1109/amfg.2003.1240820
    20 https://doi.org/10.1109/cgiv.2016.33
    21 https://doi.org/10.1109/confluence.2017.7943228
    22 https://doi.org/10.1109/cvpr.2005.297
    23 https://doi.org/10.1109/cvpr.2005.457
    24 https://doi.org/10.1109/cvpr.2014.233
    25 https://doi.org/10.1109/cvprw.2006.85
    26 https://doi.org/10.1109/cvprw.2010.5543262
    27 https://doi.org/10.1109/fcv.2015.7103729
    28 https://doi.org/10.1109/fg.2017.23
    29 https://doi.org/10.1109/iccsp.2016.7754178
    30 https://doi.org/10.1109/icip.2005.1530069
    31 https://doi.org/10.1109/icme.2005.1521424
    32 https://doi.org/10.1109/icosp.2012.6491797
    33 https://doi.org/10.1109/mcg.2012.41
    34 https://doi.org/10.1109/mlsp.2004.1423017
    35 https://doi.org/10.1109/rcar.2016.7784056
    36 https://doi.org/10.1109/t-affc.2010.1
    37 https://doi.org/10.1109/t-affc.2011.13
    38 https://doi.org/10.1109/taffc.2014.2346515
    39 https://doi.org/10.1109/taffc.2014.2386334
    40 https://doi.org/10.1109/taffc.2015.2446462
    41 https://doi.org/10.1109/taffc.2016.2593719
    42 https://doi.org/10.1109/tcyb.2014.2354351
    43 https://doi.org/10.1109/tip.2012.2235848
    44 https://doi.org/10.1109/tmm.2010.2060716
    45 https://doi.org/10.1109/tpami.2005.93
    46 https://doi.org/10.1109/tpami.2007.1110
    47 https://doi.org/10.1109/tsmcb.2004.825931
    48 https://doi.org/10.1109/tsmcb.2005.859075
    49 https://doi.org/10.1109/wacv.2016.7477450
    50 https://doi.org/10.1145/2043674.2043723
    51 https://doi.org/10.4218/etrij.10.1510.0132
    52 schema:datePublished 2018-12
    53 schema:datePublishedReg 2018-12-01
    54 schema:description In this paper, we report an effective facial expression recognition system for classifying six or seven basic expressions accurately. Instead of using the whole face region, we define three kinds of active regions, i.e., left eye regions, right eye regions and mouth regions. We propose a method to search optimized active regions from the three kinds of active regions. A Convolutional Neural Network (CNN) is trained for each kind of optimized active regions to extract features and classify expressions. In order to get representable features, histogram equalization, rotation correction and spatial normalization are carried out on the expression images. A decision-level fusion method is applied, by which the final result of expression recognition is obtained via majority voting of the three CNNs’ results. Experiments on both independent databases and fused database are carried out to evaluate the performance of the proposed system. Our novel method achieves higher accuracy compared to previous literature, with the added benefit of low latency for inference.
    55 schema:genre research_article
    56 schema:inLanguage en
    57 schema:isAccessibleForFree true
    58 schema:isPartOf N0cc24004f8f14a61aa3b6d13596feaff
    59 N37766e6e0ef547628c7985e624bf2f41
    60 sg:journal.1136381
    61 schema:name Facial expression recognition using optimized active regions
    62 schema:pagination 33
    63 schema:productId N47d09bf29559431b97b22ccf7f1e8dc2
    64 N835fca7750b74ae096148711990932e1
    65 Nf74fc088ba2c4d099e3fb613b99e12da
    66 schema:sameAs https://app.dimensions.ai/details/publication/pub.1107916777
    67 https://doi.org/10.1186/s13673-018-0156-3
    68 schema:sdDatePublished 2019-04-10T21:55
    69 schema:sdLicense https://scigraph.springernature.com/explorer/license/
    70 schema:sdPublisher N3d4d9af74d2f485fb61ac994e2e2d5c0
    71 schema:url https://link.springer.com/10.1186%2Fs13673-018-0156-3
    72 sgo:license sg:explorer/license/
    73 sgo:sdDataset articles
    74 rdf:type schema:ScholarlyArticle
    75 N03dc9863ae6d4e32804b581bace628fa rdf:first sg:person.013722753401.35
    76 rdf:rest N760eadd3db1c4ae8a8d995edaa574f9b
    77 N0cc24004f8f14a61aa3b6d13596feaff schema:issueNumber 1
    78 rdf:type schema:PublicationIssue
    79 N37766e6e0ef547628c7985e624bf2f41 schema:volumeNumber 8
    80 rdf:type schema:PublicationVolume
    81 N3d4d9af74d2f485fb61ac994e2e2d5c0 schema:name Springer Nature - SN SciGraph project
    82 rdf:type schema:Organization
    83 N458a9871a8bb462c8942971bc5977e9b rdf:first sg:person.016400453677.62
    84 rdf:rest Nf2f41bc3eb4f48ddb32f1436f84e40f2
    85 N47d09bf29559431b97b22ccf7f1e8dc2 schema:name readcube_id
    86 schema:value 7b197a1785d8035ed5a2a8ac94798a395eb50af55a844345833bb9b6f4dfcd30
    87 rdf:type schema:PropertyValue
    88 N6c3307c06ef547238bd247faf57d9103 schema:affiliation https://www.grid.ac/institutes/grid.19373.3f
    89 schema:familyName Lu
    90 schema:givenName Guangming
    91 rdf:type schema:Person
    92 N760eadd3db1c4ae8a8d995edaa574f9b rdf:first N8349128b0c784476a6a354aab6212409
    93 rdf:rest N8bfa5949a6a148abaf92ab084e16603f
    94 N8349128b0c784476a6a354aab6212409 schema:affiliation https://www.grid.ac/institutes/grid.19373.3f
    95 schema:familyName Li
    96 schema:givenName Yingjian
    97 rdf:type schema:Person
    98 N835fca7750b74ae096148711990932e1 schema:name doi
    99 schema:value 10.1186/s13673-018-0156-3
    100 rdf:type schema:PropertyValue
    101 N8bfa5949a6a148abaf92ab084e16603f rdf:first sg:person.07472307645.25
    102 rdf:rest N458a9871a8bb462c8942971bc5977e9b
    103 Nf2f41bc3eb4f48ddb32f1436f84e40f2 rdf:first N6c3307c06ef547238bd247faf57d9103
    104 rdf:rest rdf:nil
    105 Nf74fc088ba2c4d099e3fb613b99e12da schema:name dimensions_id
    106 schema:value pub.1107916777
    107 rdf:type schema:PropertyValue
    108 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
    109 schema:name Information and Computing Sciences
    110 rdf:type schema:DefinedTerm
    111 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
    112 schema:name Artificial Intelligence and Image Processing
    113 rdf:type schema:DefinedTerm
    114 sg:journal.1136381 schema:issn 2192-1962
    115 schema:name Human-centric Computing and Information Sciences
    116 rdf:type schema:Periodical
    117 sg:person.013722753401.35 schema:affiliation https://www.grid.ac/institutes/grid.64523.36
    118 schema:familyName Sun
    119 schema:givenName Ai
    120 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013722753401.35
    121 rdf:type schema:Person
    122 sg:person.016400453677.62 schema:affiliation https://www.grid.ac/institutes/grid.19373.3f
    123 schema:familyName Li
    124 schema:givenName Qiong
    125 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016400453677.62
    126 rdf:type schema:Person
    127 sg:person.07472307645.25 schema:affiliation https://www.grid.ac/institutes/grid.64523.36
    128 schema:familyName Huang
    129 schema:givenName Yueh-Min
    130 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.07472307645.25
    131 rdf:type schema:Person
    132 sg:pub.10.1007/978-3-030-01261-8_14 schema:sameAs https://app.dimensions.ai/details/publication/pub.1107502664
    133 https://doi.org/10.1007/978-3-030-01261-8_14
    134 rdf:type schema:CreativeWork
    135 sg:pub.10.1007/s11760-010-0177-5 schema:sameAs https://app.dimensions.ai/details/publication/pub.1033898562
    136 https://doi.org/10.1007/s11760-010-0177-5
    137 rdf:type schema:CreativeWork
    138 sg:pub.10.1023/b:visi.0000013087.49260.fb schema:sameAs https://app.dimensions.ai/details/publication/pub.1001944608
    139 https://doi.org/10.1023/b:visi.0000013087.49260.fb
    140 rdf:type schema:CreativeWork
    141 https://doi.org/10.1016/0169-7439(87)80084-9 schema:sameAs https://app.dimensions.ai/details/publication/pub.1042687678
    142 rdf:type schema:CreativeWork
    143 https://doi.org/10.1016/j.eswa.2012.07.074 schema:sameAs https://app.dimensions.ai/details/publication/pub.1043267745
    144 rdf:type schema:CreativeWork
    145 https://doi.org/10.1016/j.imavis.2008.08.005 schema:sameAs https://app.dimensions.ai/details/publication/pub.1047925989
    146 rdf:type schema:CreativeWork
    147 https://doi.org/10.1016/j.neucom.2015.10.139 schema:sameAs https://app.dimensions.ai/details/publication/pub.1052842820
    148 rdf:type schema:CreativeWork
    149 https://doi.org/10.1016/j.neucom.2017.08.043 schema:sameAs https://app.dimensions.ai/details/publication/pub.1091499366
    150 rdf:type schema:CreativeWork
    151 https://doi.org/10.1016/j.patcog.2007.02.021 schema:sameAs https://app.dimensions.ai/details/publication/pub.1026418119
    152 rdf:type schema:CreativeWork
    153 https://doi.org/10.1016/j.patcog.2016.07.026 schema:sameAs https://app.dimensions.ai/details/publication/pub.1002713133
    154 rdf:type schema:CreativeWork
    155 https://doi.org/10.1016/s1077-3142(03)00081-x schema:sameAs https://app.dimensions.ai/details/publication/pub.1028049386
    156 rdf:type schema:CreativeWork
    157 https://doi.org/10.1037/0033-2909.115.2.288 schema:sameAs https://app.dimensions.ai/details/publication/pub.1046870290
    158 rdf:type schema:CreativeWork
    159 https://doi.org/10.1109/afgr.1998.670949 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094774708
    160 rdf:type schema:CreativeWork
    161 https://doi.org/10.1109/afgr.1998.670990 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093464914
    162 rdf:type schema:CreativeWork
    163 https://doi.org/10.1109/afgr.2000.840611 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094698009
    164 rdf:type schema:CreativeWork
    165 https://doi.org/10.1109/amfg.2003.1240820 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094172500
    166 rdf:type schema:CreativeWork
    167 https://doi.org/10.1109/cgiv.2016.33 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093923455
    168 rdf:type schema:CreativeWork
    169 https://doi.org/10.1109/confluence.2017.7943228 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095190028
    170 rdf:type schema:CreativeWork
    171 https://doi.org/10.1109/cvpr.2005.297 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094248762
    172 rdf:type schema:CreativeWork
    173 https://doi.org/10.1109/cvpr.2005.457 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094277104
    174 rdf:type schema:CreativeWork
    175 https://doi.org/10.1109/cvpr.2014.233 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093956274
    176 rdf:type schema:CreativeWork
    177 https://doi.org/10.1109/cvprw.2006.85 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095752754
    178 rdf:type schema:CreativeWork
    179 https://doi.org/10.1109/cvprw.2010.5543262 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094866068
    180 rdf:type schema:CreativeWork
    181 https://doi.org/10.1109/fcv.2015.7103729 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095095853
    182 rdf:type schema:CreativeWork
    183 https://doi.org/10.1109/fg.2017.23 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095474554
    184 rdf:type schema:CreativeWork
    185 https://doi.org/10.1109/iccsp.2016.7754178 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095257512
    186 rdf:type schema:CreativeWork
    187 https://doi.org/10.1109/icip.2005.1530069 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095302795
    188 rdf:type schema:CreativeWork
    189 https://doi.org/10.1109/icme.2005.1521424 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094872563
    190 rdf:type schema:CreativeWork
    191 https://doi.org/10.1109/icosp.2012.6491797 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094163014
    192 rdf:type schema:CreativeWork
    193 https://doi.org/10.1109/mcg.2012.41 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061391950
    194 rdf:type schema:CreativeWork
    195 https://doi.org/10.1109/mlsp.2004.1423017 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093635197
    196 rdf:type schema:CreativeWork
    197 https://doi.org/10.1109/rcar.2016.7784056 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094752703
    198 rdf:type schema:CreativeWork
    199 https://doi.org/10.1109/t-affc.2010.1 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061446947
    200 rdf:type schema:CreativeWork
    201 https://doi.org/10.1109/t-affc.2011.13 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061446964
    202 rdf:type schema:CreativeWork
    203 https://doi.org/10.1109/taffc.2014.2346515 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061486973
    204 rdf:type schema:CreativeWork
    205 https://doi.org/10.1109/taffc.2014.2386334 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061486981
    206 rdf:type schema:CreativeWork
    207 https://doi.org/10.1109/taffc.2015.2446462 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061487015
    208 rdf:type schema:CreativeWork
    209 https://doi.org/10.1109/taffc.2016.2593719 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061487080
    210 rdf:type schema:CreativeWork
    211 https://doi.org/10.1109/tcyb.2014.2354351 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061579797
    212 rdf:type schema:CreativeWork
    213 https://doi.org/10.1109/tip.2012.2235848 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061643448
    214 rdf:type schema:CreativeWork
    215 https://doi.org/10.1109/tmm.2010.2060716 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061697759
    216 rdf:type schema:CreativeWork
    217 https://doi.org/10.1109/tpami.2005.93 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061742948
    218 rdf:type schema:CreativeWork
    219 https://doi.org/10.1109/tpami.2007.1110 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061743235
    220 rdf:type schema:CreativeWork
    221 https://doi.org/10.1109/tsmcb.2004.825931 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061796303
    222 rdf:type schema:CreativeWork
    223 https://doi.org/10.1109/tsmcb.2005.859075 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061796558
    224 rdf:type schema:CreativeWork
    225 https://doi.org/10.1109/wacv.2016.7477450 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093795554
    226 rdf:type schema:CreativeWork
    227 https://doi.org/10.1145/2043674.2043723 schema:sameAs https://app.dimensions.ai/details/publication/pub.1016238969
    228 rdf:type schema:CreativeWork
    229 https://doi.org/10.4218/etrij.10.1510.0132 schema:sameAs https://app.dimensions.ai/details/publication/pub.1072378768
    230 rdf:type schema:CreativeWork
    231 https://www.grid.ac/institutes/grid.19373.3f schema:alternateName Harbin Institute of Technology
    232 schema:name School of Computer Science and Technology, Harbin Institute of Technology (Shenzhen), Shenzhen, China
    233 School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China
    234 rdf:type schema:Organization
    235 https://www.grid.ac/institutes/grid.64523.36 schema:alternateName National Cheng Kung University
    236 schema:name Department of Engineering Science, National Cheng Kung University, Tainan, Taiwan
    237 rdf:type schema:Organization
     




    Preview window. Press ESC to close (or click here)


    ...