Detecting Morphed Face Images Using Facial Landmarks View Full Text


Ontology type: schema:Chapter     


Chapter Info

DATE

2018

AUTHORS

Ulrich Scherhag , Dhanesh Budhrani , Marta Gomez-Barrero , Christoph Busch

ABSTRACT

With the widespread deployment of automatic biometric recognition systems, some security issues have been unveiled. In particular, face recognition systems have been recently shown to be vulnerable to attacks carried out with morphed face images. Such synthetic images can be defined as the fusion of the face images of two (or more) different subjects. The associated risk lies on the ability of multiple subjects to be positively verified with a single enrolled morphed face image. As common texture based features have limited capabilities to tackle this problem, we propose a novel method for morphed face image detection, based on the computation of the differences between the landmarks of a probe bona fide (i.e., captured under supervision) image of the attacker, and the landmarks of the enrolled image (i.e., the suspected morphed image). In this work, a new database is created for the experiments, comprising both bona fide and morphed images created with two different morphing methods. The experiments show that for the detection task, the proposed algorithm achieves Equal Error Rates at 32.7%. More... »

PAGES

444-452

References to SciGraph publications

  • 2016. On the Effects of Image Alterations on Face Recognition Accuracy in FACE RECOGNITION ACROSS THE IMAGING SPECTRUM
  • Book

    TITLE

    Image and Signal Processing

    ISBN

    978-3-319-94210-0
    978-3-319-94211-7

    Author Affiliations

    Identifiers

    URI

    http://scigraph.springernature.com/pub.10.1007/978-3-319-94211-7_48

    DOI

    http://dx.doi.org/10.1007/978-3-319-94211-7_48

    DIMENSIONS

    https://app.dimensions.ai/details/publication/pub.1105208858


    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": [
                "Hochschule Darmstadt"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Scherhag", 
            "givenName": "Ulrich", 
            "id": "sg:person.014330132754.68", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.014330132754.68"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Technical University of Denmark", 
              "id": "https://www.grid.ac/institutes/grid.5170.3", 
              "name": [
                "Danmarks Tekniske Universitet"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Budhrani", 
            "givenName": "Dhanesh", 
            "id": "sg:person.013072664073.18", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013072664073.18"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "name": [
                "Hochschule Darmstadt"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Gomez-Barrero", 
            "givenName": "Marta", 
            "id": "sg:person.07603622077.06", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.07603622077.06"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "name": [
                "Hochschule Darmstadt"
              ], 
              "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": "https://doi.org/10.1016/j.cviu.2005.10.002", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1038756518"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-319-28501-6_9", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1053582678", 
              "https://doi.org/10.1007/978-3-319-28501-6_9"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1145/3082031.3083244", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1090368592"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/tifs.2017.2777340", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1092962108"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/btas.2016.7791169", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1093331378"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.23919/biosig.2017.8053499", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1093434826"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/btas.2014.6996240", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1093614459"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/iwbf.2017.7935079", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1094842882"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/iwbf.2017.7935087", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1095273224"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/das.2018.11", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1105109000"
            ], 
            "type": "CreativeWork"
          }
        ], 
        "datePublished": "2018", 
        "datePublishedReg": "2018-01-01", 
        "description": "With the widespread deployment of automatic biometric recognition systems, some security issues have been unveiled. In particular, face recognition systems have been recently shown to be vulnerable to attacks carried out with morphed face images. Such synthetic images can be defined as the fusion of the face images of two (or more) different subjects. The associated risk lies on the ability of multiple subjects to be positively verified with a single enrolled morphed face image. As common texture based features have limited capabilities to tackle this problem, we propose a novel method for morphed face image detection, based on the computation of the differences between the landmarks of a probe bona fide (i.e., captured under supervision) image of the attacker, and the landmarks of the enrolled image (i.e., the suspected morphed image). In this work, a new database is created for the experiments, comprising both bona fide and morphed images created with two different morphing methods. The experiments show that for the detection task, the proposed algorithm achieves Equal Error Rates at 32.7%.", 
        "editor": [
          {
            "familyName": "Mansouri", 
            "givenName": "Alamin", 
            "type": "Person"
          }, 
          {
            "familyName": "El Moataz", 
            "givenName": "Abderrahim", 
            "type": "Person"
          }, 
          {
            "familyName": "Nouboud", 
            "givenName": "Fathallah", 
            "type": "Person"
          }, 
          {
            "familyName": "Mammass", 
            "givenName": "Driss", 
            "type": "Person"
          }
        ], 
        "genre": "chapter", 
        "id": "sg:pub.10.1007/978-3-319-94211-7_48", 
        "inLanguage": [
          "en"
        ], 
        "isAccessibleForFree": false, 
        "isPartOf": {
          "isbn": [
            "978-3-319-94210-0", 
            "978-3-319-94211-7"
          ], 
          "name": "Image and Signal Processing", 
          "type": "Book"
        }, 
        "name": "Detecting Morphed Face Images Using Facial Landmarks", 
        "pagination": "444-452", 
        "productId": [
          {
            "name": "doi", 
            "type": "PropertyValue", 
            "value": [
              "10.1007/978-3-319-94211-7_48"
            ]
          }, 
          {
            "name": "readcube_id", 
            "type": "PropertyValue", 
            "value": [
              "0caeaeddac0999e04cca3bff4a0d12cbf550007126fe819ec6e84d78f4633db5"
            ]
          }, 
          {
            "name": "dimensions_id", 
            "type": "PropertyValue", 
            "value": [
              "pub.1105208858"
            ]
          }
        ], 
        "publisher": {
          "location": "Cham", 
          "name": "Springer International Publishing", 
          "type": "Organisation"
        }, 
        "sameAs": [
          "https://doi.org/10.1007/978-3-319-94211-7_48", 
          "https://app.dimensions.ai/details/publication/pub.1105208858"
        ], 
        "sdDataset": "chapters", 
        "sdDatePublished": "2019-04-15T16:36", 
        "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_8675_00000432.jsonl", 
        "type": "Chapter", 
        "url": "http://link.springer.com/10.1007/978-3-319-94211-7_48"
      }
    ]
     

    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.10.1007/978-3-319-94211-7_48'

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

    curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/978-3-319-94211-7_48'

    Turtle is a human-readable linked data format.

    curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/978-3-319-94211-7_48'

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

    curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/978-3-319-94211-7_48'


     

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

    138 TRIPLES      23 PREDICATES      37 URIs      20 LITERALS      8 BLANK NODES

    Subject Predicate Object
    1 sg:pub.10.1007/978-3-319-94211-7_48 schema:about anzsrc-for:08
    2 anzsrc-for:0801
    3 schema:author N65044cabb9fa41d1b9648f3456530d1a
    4 schema:citation sg:pub.10.1007/978-3-319-28501-6_9
    5 https://doi.org/10.1016/j.cviu.2005.10.002
    6 https://doi.org/10.1109/btas.2014.6996240
    7 https://doi.org/10.1109/btas.2016.7791169
    8 https://doi.org/10.1109/das.2018.11
    9 https://doi.org/10.1109/iwbf.2017.7935079
    10 https://doi.org/10.1109/iwbf.2017.7935087
    11 https://doi.org/10.1109/tifs.2017.2777340
    12 https://doi.org/10.1145/3082031.3083244
    13 https://doi.org/10.23919/biosig.2017.8053499
    14 schema:datePublished 2018
    15 schema:datePublishedReg 2018-01-01
    16 schema:description With the widespread deployment of automatic biometric recognition systems, some security issues have been unveiled. In particular, face recognition systems have been recently shown to be vulnerable to attacks carried out with morphed face images. Such synthetic images can be defined as the fusion of the face images of two (or more) different subjects. The associated risk lies on the ability of multiple subjects to be positively verified with a single enrolled morphed face image. As common texture based features have limited capabilities to tackle this problem, we propose a novel method for morphed face image detection, based on the computation of the differences between the landmarks of a probe bona fide (i.e., captured under supervision) image of the attacker, and the landmarks of the enrolled image (i.e., the suspected morphed image). In this work, a new database is created for the experiments, comprising both bona fide and morphed images created with two different morphing methods. The experiments show that for the detection task, the proposed algorithm achieves Equal Error Rates at 32.7%.
    17 schema:editor Na468bbd40f454828a6925cc164dd083f
    18 schema:genre chapter
    19 schema:inLanguage en
    20 schema:isAccessibleForFree false
    21 schema:isPartOf Nccdb0bd8edda47d3898bcad64b3d6aa6
    22 schema:name Detecting Morphed Face Images Using Facial Landmarks
    23 schema:pagination 444-452
    24 schema:productId Na3fe6bc1f1b541ec98f9276234147d88
    25 Ncc808f56859244c6813e247a5336d50e
    26 Nd8c19b864aba4bec892c776af3605f34
    27 schema:publisher Nbe8a6cd9fc3446188ebba0624662ab3f
    28 schema:sameAs https://app.dimensions.ai/details/publication/pub.1105208858
    29 https://doi.org/10.1007/978-3-319-94211-7_48
    30 schema:sdDatePublished 2019-04-15T16:36
    31 schema:sdLicense https://scigraph.springernature.com/explorer/license/
    32 schema:sdPublisher Nd57edf48c5c847f5883bf814d8fbdb10
    33 schema:url http://link.springer.com/10.1007/978-3-319-94211-7_48
    34 sgo:license sg:explorer/license/
    35 sgo:sdDataset chapters
    36 rdf:type schema:Chapter
    37 N3049207c3f9948739c1cdd7dd6158f00 rdf:first Nad7246f7f04a424ca2cad4af60a9ce4e
    38 rdf:rest rdf:nil
    39 N65044cabb9fa41d1b9648f3456530d1a rdf:first sg:person.014330132754.68
    40 rdf:rest Nea0e262c9fba46759a8d6af9ea9025d2
    41 N6dd9b17a9b53441fa9fc9fce55e591f9 schema:name Hochschule Darmstadt
    42 rdf:type schema:Organization
    43 N770aa028515440a6ac96d7615e2a4cbf rdf:first sg:person.07603622077.06
    44 rdf:rest N8c945f06d2d6478ca502b33cb0b1bfea
    45 N7fa560b1eeac4775b2748bfe722929ac rdf:first Nb7531f42691f4b249ebf4e85c099723e
    46 rdf:rest Naa2822396f5d456bbf7b7d61accc0618
    47 N8c945f06d2d6478ca502b33cb0b1bfea rdf:first sg:person.011143356603.69
    48 rdf:rest rdf:nil
    49 N9260362badcb45bea818cc7439c5d22c schema:name Hochschule Darmstadt
    50 rdf:type schema:Organization
    51 N9f88e5b055774c4790bcd845a2e3f7b3 schema:familyName Mansouri
    52 schema:givenName Alamin
    53 rdf:type schema:Person
    54 Na3fe6bc1f1b541ec98f9276234147d88 schema:name doi
    55 schema:value 10.1007/978-3-319-94211-7_48
    56 rdf:type schema:PropertyValue
    57 Na468bbd40f454828a6925cc164dd083f rdf:first N9f88e5b055774c4790bcd845a2e3f7b3
    58 rdf:rest N7fa560b1eeac4775b2748bfe722929ac
    59 Naa2822396f5d456bbf7b7d61accc0618 rdf:first Nab54c8299fc84cb68da8b365e6fdf472
    60 rdf:rest N3049207c3f9948739c1cdd7dd6158f00
    61 Nab54c8299fc84cb68da8b365e6fdf472 schema:familyName Nouboud
    62 schema:givenName Fathallah
    63 rdf:type schema:Person
    64 Nad7246f7f04a424ca2cad4af60a9ce4e schema:familyName Mammass
    65 schema:givenName Driss
    66 rdf:type schema:Person
    67 Nb7531f42691f4b249ebf4e85c099723e schema:familyName El Moataz
    68 schema:givenName Abderrahim
    69 rdf:type schema:Person
    70 Nbdbb48ef9aa846aa8604468ccf997bce schema:name Hochschule Darmstadt
    71 rdf:type schema:Organization
    72 Nbe8a6cd9fc3446188ebba0624662ab3f schema:location Cham
    73 schema:name Springer International Publishing
    74 rdf:type schema:Organisation
    75 Ncc808f56859244c6813e247a5336d50e schema:name readcube_id
    76 schema:value 0caeaeddac0999e04cca3bff4a0d12cbf550007126fe819ec6e84d78f4633db5
    77 rdf:type schema:PropertyValue
    78 Nccdb0bd8edda47d3898bcad64b3d6aa6 schema:isbn 978-3-319-94210-0
    79 978-3-319-94211-7
    80 schema:name Image and Signal Processing
    81 rdf:type schema:Book
    82 Nd57edf48c5c847f5883bf814d8fbdb10 schema:name Springer Nature - SN SciGraph project
    83 rdf:type schema:Organization
    84 Nd8c19b864aba4bec892c776af3605f34 schema:name dimensions_id
    85 schema:value pub.1105208858
    86 rdf:type schema:PropertyValue
    87 Nea0e262c9fba46759a8d6af9ea9025d2 rdf:first sg:person.013072664073.18
    88 rdf:rest N770aa028515440a6ac96d7615e2a4cbf
    89 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
    90 schema:name Information and Computing Sciences
    91 rdf:type schema:DefinedTerm
    92 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
    93 schema:name Artificial Intelligence and Image Processing
    94 rdf:type schema:DefinedTerm
    95 sg:person.011143356603.69 schema:affiliation N9260362badcb45bea818cc7439c5d22c
    96 schema:familyName Busch
    97 schema:givenName Christoph
    98 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.011143356603.69
    99 rdf:type schema:Person
    100 sg:person.013072664073.18 schema:affiliation https://www.grid.ac/institutes/grid.5170.3
    101 schema:familyName Budhrani
    102 schema:givenName Dhanesh
    103 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013072664073.18
    104 rdf:type schema:Person
    105 sg:person.014330132754.68 schema:affiliation Nbdbb48ef9aa846aa8604468ccf997bce
    106 schema:familyName Scherhag
    107 schema:givenName Ulrich
    108 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.014330132754.68
    109 rdf:type schema:Person
    110 sg:person.07603622077.06 schema:affiliation N6dd9b17a9b53441fa9fc9fce55e591f9
    111 schema:familyName Gomez-Barrero
    112 schema:givenName Marta
    113 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.07603622077.06
    114 rdf:type schema:Person
    115 sg:pub.10.1007/978-3-319-28501-6_9 schema:sameAs https://app.dimensions.ai/details/publication/pub.1053582678
    116 https://doi.org/10.1007/978-3-319-28501-6_9
    117 rdf:type schema:CreativeWork
    118 https://doi.org/10.1016/j.cviu.2005.10.002 schema:sameAs https://app.dimensions.ai/details/publication/pub.1038756518
    119 rdf:type schema:CreativeWork
    120 https://doi.org/10.1109/btas.2014.6996240 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093614459
    121 rdf:type schema:CreativeWork
    122 https://doi.org/10.1109/btas.2016.7791169 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093331378
    123 rdf:type schema:CreativeWork
    124 https://doi.org/10.1109/das.2018.11 schema:sameAs https://app.dimensions.ai/details/publication/pub.1105109000
    125 rdf:type schema:CreativeWork
    126 https://doi.org/10.1109/iwbf.2017.7935079 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094842882
    127 rdf:type schema:CreativeWork
    128 https://doi.org/10.1109/iwbf.2017.7935087 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095273224
    129 rdf:type schema:CreativeWork
    130 https://doi.org/10.1109/tifs.2017.2777340 schema:sameAs https://app.dimensions.ai/details/publication/pub.1092962108
    131 rdf:type schema:CreativeWork
    132 https://doi.org/10.1145/3082031.3083244 schema:sameAs https://app.dimensions.ai/details/publication/pub.1090368592
    133 rdf:type schema:CreativeWork
    134 https://doi.org/10.23919/biosig.2017.8053499 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093434826
    135 rdf:type schema:CreativeWork
    136 https://www.grid.ac/institutes/grid.5170.3 schema:alternateName Technical University of Denmark
    137 schema:name Danmarks Tekniske Universitet
    138 rdf:type schema:Organization
     




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


    ...