Segmentation and Normalization of Human Ears Using Cascaded Pose Regression View Full Text


Ontology type: schema:Chapter     


Chapter Info

DATE

2014

AUTHORS

Anika Pflug , Christoph Busch

ABSTRACT

Being an emerging biometric characteristic, automated ear recognition is making its way into forensic image analysis for law enforcement in the last decades. One of the most important challenges for this application is to deal with loosely constrained acquisition scenarios and large databases of reference samples. The research community has come up with a variety of feature extraction methods that are capable of handling occlusions and blur. However, these methods require the images to be geometrically normalized, which is mostly done manually at the moment. In this work, we propose a segmentation and normalization method for ear images that is using cascaded pose regression (CPR). We show that CPR returns accurate rotation and scale estimates, even for full profile images, where the ear has not been segmented yet. We show that the segmentation accuracy of CPR outperforms state of the art detection methods and that CPR improves the recognition rate of an ear recognition system that uses state of the art appearance features. More... »

PAGES

261-272

References to SciGraph publications

  • 2009. Normalizing Human Ear in Proportion to Size and Rotation in EMERGING INTELLIGENT COMPUTING TECHNOLOGY AND APPLICATIONS
  • 1997. Kernel principal component analysis in ARTIFICIAL NEURAL NETWORKS — ICANN'97
  • Book

    TITLE

    Secure IT Systems

    ISBN

    978-3-319-11598-6
    978-3-319-11599-3

    Identifiers

    URI

    http://scigraph.springernature.com/pub.10.1007/978-3-319-11599-3_16

    DOI

    http://dx.doi.org/10.1007/978-3-319-11599-3_16

    DIMENSIONS

    https://app.dimensions.ai/details/publication/pub.1010559835


    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": {
              "name": [
                "University of Applied Sciences Darmstadt - CASED, Haardtring 100, 64295\u00a0Darmstadt, Germany"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Pflug", 
            "givenName": "Anika", 
            "id": "sg:person.07433647331.65", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.07433647331.65"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "name": [
                "University of Applied Sciences Darmstadt - CASED, Haardtring 100, 64295\u00a0Darmstadt, Germany"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Busch", 
            "givenName": "Christoph", 
            "id": "sg:person.011143356603.69", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.011143356603.69"
            ], 
            "type": "Person"
          }
        ], 
        "citation": [
          {
            "id": "sg:pub.10.1007/978-3-642-04070-2_5", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1027468771", 
              "https://doi.org/10.1007/978-3-642-04070-2_5"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/s1355-0306(01)71885-0", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1039073519"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/bfb0020217", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1052658614", 
              "https://doi.org/10.1007/bfb0020217"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1049/iet-bmt.2011.0003", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1056818613"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/tpami.2002.1017623", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1061742396"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/tpami.2009.23", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1061743773"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.14257/ijsip.2013.6.5.05", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1067240553"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.14257/ijsip.2013.6.5.05", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1067240553"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/cvpr.2005.177", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1093997066"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/iccv.2013.243", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1094024488"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/ccst.2012.6393543", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1094517254"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/iccv.2013.191", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1094564562"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/cvpr.2010.5540094", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1095128699"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/icpr.2008.4761847", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1095608368"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/ccst.2012.6393542", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1095718416"
            ], 
            "type": "CreativeWork"
          }
        ], 
        "datePublished": "2014", 
        "datePublishedReg": "2014-01-01", 
        "description": "Being an emerging biometric characteristic, automated ear recognition is making its way into forensic image analysis for law enforcement in the last decades. One of the most important challenges for this application is to deal with loosely constrained acquisition scenarios and large databases of reference samples. The research community has come up with a variety of feature extraction methods that are capable of handling occlusions and blur. However, these methods require the images to be geometrically normalized, which is mostly done manually at the moment. In this work, we propose a segmentation and normalization method for ear images that is using cascaded pose regression (CPR). We show that CPR returns accurate rotation and scale estimates, even for full profile images, where the ear has not been segmented yet. We show that the segmentation accuracy of CPR outperforms state of the art detection methods and that CPR improves the recognition rate of an ear recognition system that uses state of the art appearance features.", 
        "editor": [
          {
            "familyName": "Bernsmed", 
            "givenName": "Karin", 
            "type": "Person"
          }, 
          {
            "familyName": "Fischer-H\u00fcbner", 
            "givenName": "Simone", 
            "type": "Person"
          }
        ], 
        "genre": "chapter", 
        "id": "sg:pub.10.1007/978-3-319-11599-3_16", 
        "inLanguage": [
          "en"
        ], 
        "isAccessibleForFree": false, 
        "isPartOf": {
          "isbn": [
            "978-3-319-11598-6", 
            "978-3-319-11599-3"
          ], 
          "name": "Secure IT Systems", 
          "type": "Book"
        }, 
        "name": "Segmentation and Normalization of Human Ears Using Cascaded Pose Regression", 
        "pagination": "261-272", 
        "productId": [
          {
            "name": "doi", 
            "type": "PropertyValue", 
            "value": [
              "10.1007/978-3-319-11599-3_16"
            ]
          }, 
          {
            "name": "readcube_id", 
            "type": "PropertyValue", 
            "value": [
              "324ec50e2c34a21cd1629da1460b38d6e0c2d07df942f727b50b206776050ca1"
            ]
          }, 
          {
            "name": "dimensions_id", 
            "type": "PropertyValue", 
            "value": [
              "pub.1010559835"
            ]
          }
        ], 
        "publisher": {
          "location": "Cham", 
          "name": "Springer International Publishing", 
          "type": "Organisation"
        }, 
        "sameAs": [
          "https://doi.org/10.1007/978-3-319-11599-3_16", 
          "https://app.dimensions.ai/details/publication/pub.1010559835"
        ], 
        "sdDataset": "chapters", 
        "sdDatePublished": "2019-04-15T22:53", 
        "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_8695_00000249.jsonl", 
        "type": "Chapter", 
        "url": "http://link.springer.com/10.1007/978-3-319-11599-3_16"
      }
    ]
     

    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.10.1007/978-3-319-11599-3_16'

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

    curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/978-3-319-11599-3_16'

    Turtle is a human-readable linked data format.

    curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/978-3-319-11599-3_16'

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

    curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/978-3-319-11599-3_16'


     

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

    122 TRIPLES      23 PREDICATES      41 URIs      20 LITERALS      8 BLANK NODES

    Subject Predicate Object
    1 sg:pub.10.1007/978-3-319-11599-3_16 schema:about anzsrc-for:08
    2 anzsrc-for:0801
    3 schema:author Nd4e366f1aab74d92a3a07e36f7975fb4
    4 schema:citation sg:pub.10.1007/978-3-642-04070-2_5
    5 sg:pub.10.1007/bfb0020217
    6 https://doi.org/10.1016/s1355-0306(01)71885-0
    7 https://doi.org/10.1049/iet-bmt.2011.0003
    8 https://doi.org/10.1109/ccst.2012.6393542
    9 https://doi.org/10.1109/ccst.2012.6393543
    10 https://doi.org/10.1109/cvpr.2005.177
    11 https://doi.org/10.1109/cvpr.2010.5540094
    12 https://doi.org/10.1109/iccv.2013.191
    13 https://doi.org/10.1109/iccv.2013.243
    14 https://doi.org/10.1109/icpr.2008.4761847
    15 https://doi.org/10.1109/tpami.2002.1017623
    16 https://doi.org/10.1109/tpami.2009.23
    17 https://doi.org/10.14257/ijsip.2013.6.5.05
    18 schema:datePublished 2014
    19 schema:datePublishedReg 2014-01-01
    20 schema:description Being an emerging biometric characteristic, automated ear recognition is making its way into forensic image analysis for law enforcement in the last decades. One of the most important challenges for this application is to deal with loosely constrained acquisition scenarios and large databases of reference samples. The research community has come up with a variety of feature extraction methods that are capable of handling occlusions and blur. However, these methods require the images to be geometrically normalized, which is mostly done manually at the moment. In this work, we propose a segmentation and normalization method for ear images that is using cascaded pose regression (CPR). We show that CPR returns accurate rotation and scale estimates, even for full profile images, where the ear has not been segmented yet. We show that the segmentation accuracy of CPR outperforms state of the art detection methods and that CPR improves the recognition rate of an ear recognition system that uses state of the art appearance features.
    21 schema:editor N0cd3d8e51be245949ada12dd3739463c
    22 schema:genre chapter
    23 schema:inLanguage en
    24 schema:isAccessibleForFree false
    25 schema:isPartOf Ne513e51ab8c44e4cb7ef5441516d9590
    26 schema:name Segmentation and Normalization of Human Ears Using Cascaded Pose Regression
    27 schema:pagination 261-272
    28 schema:productId N73e537750dac436789bdcdc3dc9bc10a
    29 Nc7221b2db30c4bfd8446a6c204844492
    30 Nc9ee3a4e38924c47bc79635977f74fb7
    31 schema:publisher Nc6e4c18deed14bda923317b662c6caca
    32 schema:sameAs https://app.dimensions.ai/details/publication/pub.1010559835
    33 https://doi.org/10.1007/978-3-319-11599-3_16
    34 schema:sdDatePublished 2019-04-15T22:53
    35 schema:sdLicense https://scigraph.springernature.com/explorer/license/
    36 schema:sdPublisher Nfa40801e012345a99ef9ddb38f447a23
    37 schema:url http://link.springer.com/10.1007/978-3-319-11599-3_16
    38 sgo:license sg:explorer/license/
    39 sgo:sdDataset chapters
    40 rdf:type schema:Chapter
    41 N0cd3d8e51be245949ada12dd3739463c rdf:first Ned7f0f46da7349dc8235c80cbfe322f6
    42 rdf:rest N5baa9b4812d84880989137d9cb0edc9f
    43 N5baa9b4812d84880989137d9cb0edc9f rdf:first N675c09c859f94f9aafb9a36183dbfab1
    44 rdf:rest rdf:nil
    45 N675c09c859f94f9aafb9a36183dbfab1 schema:familyName Fischer-Hübner
    46 schema:givenName Simone
    47 rdf:type schema:Person
    48 N73e537750dac436789bdcdc3dc9bc10a schema:name dimensions_id
    49 schema:value pub.1010559835
    50 rdf:type schema:PropertyValue
    51 N75d251c70b754a29817e0ce4509303ce schema:name University of Applied Sciences Darmstadt - CASED, Haardtring 100, 64295 Darmstadt, Germany
    52 rdf:type schema:Organization
    53 Na95aceda0a854498ae99753df4227d05 schema:name University of Applied Sciences Darmstadt - CASED, Haardtring 100, 64295 Darmstadt, Germany
    54 rdf:type schema:Organization
    55 Nafdeff5606324a699ec21a85b2fd4145 rdf:first sg:person.011143356603.69
    56 rdf:rest rdf:nil
    57 Nc6e4c18deed14bda923317b662c6caca schema:location Cham
    58 schema:name Springer International Publishing
    59 rdf:type schema:Organisation
    60 Nc7221b2db30c4bfd8446a6c204844492 schema:name doi
    61 schema:value 10.1007/978-3-319-11599-3_16
    62 rdf:type schema:PropertyValue
    63 Nc9ee3a4e38924c47bc79635977f74fb7 schema:name readcube_id
    64 schema:value 324ec50e2c34a21cd1629da1460b38d6e0c2d07df942f727b50b206776050ca1
    65 rdf:type schema:PropertyValue
    66 Nd4e366f1aab74d92a3a07e36f7975fb4 rdf:first sg:person.07433647331.65
    67 rdf:rest Nafdeff5606324a699ec21a85b2fd4145
    68 Ne513e51ab8c44e4cb7ef5441516d9590 schema:isbn 978-3-319-11598-6
    69 978-3-319-11599-3
    70 schema:name Secure IT Systems
    71 rdf:type schema:Book
    72 Ned7f0f46da7349dc8235c80cbfe322f6 schema:familyName Bernsmed
    73 schema:givenName Karin
    74 rdf:type schema:Person
    75 Nfa40801e012345a99ef9ddb38f447a23 schema:name Springer Nature - SN SciGraph project
    76 rdf:type schema:Organization
    77 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
    78 schema:name Information and Computing Sciences
    79 rdf:type schema:DefinedTerm
    80 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
    81 schema:name Artificial Intelligence and Image Processing
    82 rdf:type schema:DefinedTerm
    83 sg:person.011143356603.69 schema:affiliation Na95aceda0a854498ae99753df4227d05
    84 schema:familyName Busch
    85 schema:givenName Christoph
    86 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.011143356603.69
    87 rdf:type schema:Person
    88 sg:person.07433647331.65 schema:affiliation N75d251c70b754a29817e0ce4509303ce
    89 schema:familyName Pflug
    90 schema:givenName Anika
    91 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.07433647331.65
    92 rdf:type schema:Person
    93 sg:pub.10.1007/978-3-642-04070-2_5 schema:sameAs https://app.dimensions.ai/details/publication/pub.1027468771
    94 https://doi.org/10.1007/978-3-642-04070-2_5
    95 rdf:type schema:CreativeWork
    96 sg:pub.10.1007/bfb0020217 schema:sameAs https://app.dimensions.ai/details/publication/pub.1052658614
    97 https://doi.org/10.1007/bfb0020217
    98 rdf:type schema:CreativeWork
    99 https://doi.org/10.1016/s1355-0306(01)71885-0 schema:sameAs https://app.dimensions.ai/details/publication/pub.1039073519
    100 rdf:type schema:CreativeWork
    101 https://doi.org/10.1049/iet-bmt.2011.0003 schema:sameAs https://app.dimensions.ai/details/publication/pub.1056818613
    102 rdf:type schema:CreativeWork
    103 https://doi.org/10.1109/ccst.2012.6393542 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095718416
    104 rdf:type schema:CreativeWork
    105 https://doi.org/10.1109/ccst.2012.6393543 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094517254
    106 rdf:type schema:CreativeWork
    107 https://doi.org/10.1109/cvpr.2005.177 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093997066
    108 rdf:type schema:CreativeWork
    109 https://doi.org/10.1109/cvpr.2010.5540094 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095128699
    110 rdf:type schema:CreativeWork
    111 https://doi.org/10.1109/iccv.2013.191 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094564562
    112 rdf:type schema:CreativeWork
    113 https://doi.org/10.1109/iccv.2013.243 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094024488
    114 rdf:type schema:CreativeWork
    115 https://doi.org/10.1109/icpr.2008.4761847 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095608368
    116 rdf:type schema:CreativeWork
    117 https://doi.org/10.1109/tpami.2002.1017623 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061742396
    118 rdf:type schema:CreativeWork
    119 https://doi.org/10.1109/tpami.2009.23 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061743773
    120 rdf:type schema:CreativeWork
    121 https://doi.org/10.14257/ijsip.2013.6.5.05 schema:sameAs https://app.dimensions.ai/details/publication/pub.1067240553
    122 rdf:type schema:CreativeWork
     




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


    ...