Using Second Order Statistics to Enhance Automated Image Annotation View Full Text


Ontology type: schema:Chapter     


Chapter Info

DATE

2009

AUTHORS

Ainhoa Llorente , Stefan Rüger

ABSTRACT

We examine whether a traditional automated annotation system can be improved by using background knowledge. Traditional means any machine learning approach together with image analysis techniques. We use as a baseline for our experiments the work done by Yavlinsky et al. [1] who deployed non-parametric density estimation. We observe that probabilistic image analysis by itself is not enough to describe the rich semantics of an image. Our hypothesis is that more accurate annotations can be produced by introducing additional knowledge in the form of statistical co-occurrence of terms. This is provided by the context of images that otherwise independent keyword generation would miss. We test our algorithm with two different datasets: Corel 5k and ImageCLEF 2008. For the Corel 5k dataset, we obtain significantly better results while our algorithm appears in the top quartile of all methods submitted in ImageCLEF 2008. More... »

PAGES

570-577

References to SciGraph publications

  • 2005. Automated Image Annotation Using Global Features and Robust Nonparametric Density Estimation in IMAGE AND VIDEO RETRIEVAL
  • 2008. A New Baseline for Image Annotation in COMPUTER VISION – ECCV 2008
  • 2009. The Visual Concept Detection Task in ImageCLEF 2008 in EVALUATING SYSTEMS FOR MULTILINGUAL AND MULTIMODAL INFORMATION ACCESS
  • 2002. Object Recognition as Machine Translation: Learning a Lexicon for a Fixed Image Vocabulary in COMPUTER VISION — ECCV 2002
  • Book

    TITLE

    Advances in Information Retrieval

    ISBN

    978-3-642-00957-0
    978-3-642-00958-7

    Author Affiliations

    Identifiers

    URI

    http://scigraph.springernature.com/pub.10.1007/978-3-642-00958-7_52

    DOI

    http://dx.doi.org/10.1007/978-3-642-00958-7_52

    DIMENSIONS

    https://app.dimensions.ai/details/publication/pub.1021433401


    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": "The Open University", 
              "id": "https://www.grid.ac/institutes/grid.10837.3d", 
              "name": [
                "Knowledge Media Institute, The Open University, Walton Hall, MK7 6AA, Milton Keynes, United Kingdom"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Llorente", 
            "givenName": "Ainhoa", 
            "id": "sg:person.012775002107.61", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.012775002107.61"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "The Open University", 
              "id": "https://www.grid.ac/institutes/grid.10837.3d", 
              "name": [
                "Knowledge Media Institute, The Open University, Walton Hall, MK7 6AA, Milton Keynes, United Kingdom"
              ], 
              "type": "Organization"
            }, 
            "familyName": "R\u00fcger", 
            "givenName": "Stefan", 
            "id": "sg:person.013375677533.85", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013375677533.85"
            ], 
            "type": "Person"
          }
        ], 
        "citation": [
          {
            "id": "https://doi.org/10.1145/1282280.1282284", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1009266420"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-540-88690-7_24", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1009765396", 
              "https://doi.org/10.1007/978-3-540-88690-7_24"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-540-88690-7_24", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1009765396", 
              "https://doi.org/10.1007/978-3-540-88690-7_24"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1080/01690969108406936", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1010893796"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/11526346_54", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1012604628", 
              "https://doi.org/10.1007/11526346_54"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/11526346_54", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1012604628", 
              "https://doi.org/10.1007/11526346_54"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/j.patrec.2005.10.010", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1013701558"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1145/1027527.1027732", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1016237565"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-642-04447-2_65", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1027852860", 
              "https://doi.org/10.1007/978-3-642-04447-2_65"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1145/1178677.1178689", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1037571801"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/3-540-47979-1_7", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1040055518", 
              "https://doi.org/10.1007/3-540-47979-1_7"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1145/1282280.1282369", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1048045132"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1145/1101149.1101305", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1051369458"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1145/860435.860459", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1053524475"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.5244/c.21.60", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1099341556"
            ], 
            "type": "CreativeWork"
          }
        ], 
        "datePublished": "2009", 
        "datePublishedReg": "2009-01-01", 
        "description": "We examine whether a traditional automated annotation system can be improved by using background knowledge. Traditional means any machine learning approach together with image analysis techniques. We use as a baseline for our experiments the work done by Yavlinsky et al. [1] who deployed non-parametric density estimation. We observe that probabilistic image analysis by itself is not enough to describe the rich semantics of an image. Our hypothesis is that more accurate annotations can be produced by introducing additional knowledge in the form of statistical co-occurrence of terms. This is provided by the context of images that otherwise independent keyword generation would miss. We test our algorithm with two different datasets: Corel 5k and ImageCLEF 2008. For the Corel 5k dataset, we obtain significantly better results while our algorithm appears in the top quartile of all methods submitted in ImageCLEF 2008.", 
        "editor": [
          {
            "familyName": "Boughanem", 
            "givenName": "Mohand", 
            "type": "Person"
          }, 
          {
            "familyName": "Berrut", 
            "givenName": "Catherine", 
            "type": "Person"
          }, 
          {
            "familyName": "Mothe", 
            "givenName": "Josiane", 
            "type": "Person"
          }, 
          {
            "familyName": "Soule-Dupuy", 
            "givenName": "Chantal", 
            "type": "Person"
          }
        ], 
        "genre": "chapter", 
        "id": "sg:pub.10.1007/978-3-642-00958-7_52", 
        "inLanguage": [
          "en"
        ], 
        "isAccessibleForFree": false, 
        "isPartOf": {
          "isbn": [
            "978-3-642-00957-0", 
            "978-3-642-00958-7"
          ], 
          "name": "Advances in Information Retrieval", 
          "type": "Book"
        }, 
        "name": "Using Second Order Statistics to Enhance Automated Image Annotation", 
        "pagination": "570-577", 
        "productId": [
          {
            "name": "dimensions_id", 
            "type": "PropertyValue", 
            "value": [
              "pub.1021433401"
            ]
          }, 
          {
            "name": "doi", 
            "type": "PropertyValue", 
            "value": [
              "10.1007/978-3-642-00958-7_52"
            ]
          }, 
          {
            "name": "readcube_id", 
            "type": "PropertyValue", 
            "value": [
              "661e40d91302e3ce91884602b4cab52ae8e70cb04ccb1e7a8c891e3783745f2e"
            ]
          }
        ], 
        "publisher": {
          "location": "Berlin, Heidelberg", 
          "name": "Springer Berlin Heidelberg", 
          "type": "Organisation"
        }, 
        "sameAs": [
          "https://doi.org/10.1007/978-3-642-00958-7_52", 
          "https://app.dimensions.ai/details/publication/pub.1021433401"
        ], 
        "sdDataset": "chapters", 
        "sdDatePublished": "2019-04-16T07:10", 
        "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/v90/0000000353_0000000353/records_45339_00000000.jsonl", 
        "type": "Chapter", 
        "url": "https://link.springer.com/10.1007%2F978-3-642-00958-7_52"
      }
    ]
     

    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.10.1007/978-3-642-00958-7_52'

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

    curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/978-3-642-00958-7_52'

    Turtle is a human-readable linked data format.

    curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/978-3-642-00958-7_52'

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

    curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/978-3-642-00958-7_52'


     

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

    130 TRIPLES      23 PREDICATES      40 URIs      20 LITERALS      8 BLANK NODES

    Subject Predicate Object
    1 sg:pub.10.1007/978-3-642-00958-7_52 schema:about anzsrc-for:08
    2 anzsrc-for:0801
    3 schema:author Nd82df8dc33174f8cacee8bc6e931d054
    4 schema:citation sg:pub.10.1007/11526346_54
    5 sg:pub.10.1007/3-540-47979-1_7
    6 sg:pub.10.1007/978-3-540-88690-7_24
    7 sg:pub.10.1007/978-3-642-04447-2_65
    8 https://doi.org/10.1016/j.patrec.2005.10.010
    9 https://doi.org/10.1080/01690969108406936
    10 https://doi.org/10.1145/1027527.1027732
    11 https://doi.org/10.1145/1101149.1101305
    12 https://doi.org/10.1145/1178677.1178689
    13 https://doi.org/10.1145/1282280.1282284
    14 https://doi.org/10.1145/1282280.1282369
    15 https://doi.org/10.1145/860435.860459
    16 https://doi.org/10.5244/c.21.60
    17 schema:datePublished 2009
    18 schema:datePublishedReg 2009-01-01
    19 schema:description We examine whether a traditional automated annotation system can be improved by using background knowledge. Traditional means any machine learning approach together with image analysis techniques. We use as a baseline for our experiments the work done by Yavlinsky et al. [1] who deployed non-parametric density estimation. We observe that probabilistic image analysis by itself is not enough to describe the rich semantics of an image. Our hypothesis is that more accurate annotations can be produced by introducing additional knowledge in the form of statistical co-occurrence of terms. This is provided by the context of images that otherwise independent keyword generation would miss. We test our algorithm with two different datasets: Corel 5k and ImageCLEF 2008. For the Corel 5k dataset, we obtain significantly better results while our algorithm appears in the top quartile of all methods submitted in ImageCLEF 2008.
    20 schema:editor Na39a3c86933643f68985be3336ad931f
    21 schema:genre chapter
    22 schema:inLanguage en
    23 schema:isAccessibleForFree false
    24 schema:isPartOf N422845d826124ff6be8152494bb31d97
    25 schema:name Using Second Order Statistics to Enhance Automated Image Annotation
    26 schema:pagination 570-577
    27 schema:productId N4d08c2fd69324149992516a90a75d5a1
    28 Nabbbd070a8ca4bdfb60f0e9e763fe57a
    29 Nf21fc092316649d8a44dbeb2018e5ece
    30 schema:publisher N4b5b2482f77041cfbdd8f9fd5417c992
    31 schema:sameAs https://app.dimensions.ai/details/publication/pub.1021433401
    32 https://doi.org/10.1007/978-3-642-00958-7_52
    33 schema:sdDatePublished 2019-04-16T07:10
    34 schema:sdLicense https://scigraph.springernature.com/explorer/license/
    35 schema:sdPublisher N7dbcb4900e764b85918aa6125bdbccbf
    36 schema:url https://link.springer.com/10.1007%2F978-3-642-00958-7_52
    37 sgo:license sg:explorer/license/
    38 sgo:sdDataset chapters
    39 rdf:type schema:Chapter
    40 N065d2ea89f9c48a59d3a9d28fc2e7f0f rdf:first N392c890655804a1dafbc3114e670ed31
    41 rdf:rest N7e4e6bf392ac41e2bd6db26fb3f0f4e2
    42 N30a39b4ff5d04c04abfa111d948aab25 rdf:first sg:person.013375677533.85
    43 rdf:rest rdf:nil
    44 N392c890655804a1dafbc3114e670ed31 schema:familyName Berrut
    45 schema:givenName Catherine
    46 rdf:type schema:Person
    47 N413ba60f151741a1b0ec79c11f30465d schema:familyName Soule-Dupuy
    48 schema:givenName Chantal
    49 rdf:type schema:Person
    50 N422845d826124ff6be8152494bb31d97 schema:isbn 978-3-642-00957-0
    51 978-3-642-00958-7
    52 schema:name Advances in Information Retrieval
    53 rdf:type schema:Book
    54 N4b5b2482f77041cfbdd8f9fd5417c992 schema:location Berlin, Heidelberg
    55 schema:name Springer Berlin Heidelberg
    56 rdf:type schema:Organisation
    57 N4d08c2fd69324149992516a90a75d5a1 schema:name doi
    58 schema:value 10.1007/978-3-642-00958-7_52
    59 rdf:type schema:PropertyValue
    60 N5ffbde9ad4e84826a5fc293f6b38cc88 schema:familyName Mothe
    61 schema:givenName Josiane
    62 rdf:type schema:Person
    63 N7dbcb4900e764b85918aa6125bdbccbf schema:name Springer Nature - SN SciGraph project
    64 rdf:type schema:Organization
    65 N7e4e6bf392ac41e2bd6db26fb3f0f4e2 rdf:first N5ffbde9ad4e84826a5fc293f6b38cc88
    66 rdf:rest N972017ea5e464e7f93b67172bdaf5cd4
    67 N93a87b4f92a940b789e7116d63a4e222 schema:familyName Boughanem
    68 schema:givenName Mohand
    69 rdf:type schema:Person
    70 N972017ea5e464e7f93b67172bdaf5cd4 rdf:first N413ba60f151741a1b0ec79c11f30465d
    71 rdf:rest rdf:nil
    72 Na39a3c86933643f68985be3336ad931f rdf:first N93a87b4f92a940b789e7116d63a4e222
    73 rdf:rest N065d2ea89f9c48a59d3a9d28fc2e7f0f
    74 Nabbbd070a8ca4bdfb60f0e9e763fe57a schema:name readcube_id
    75 schema:value 661e40d91302e3ce91884602b4cab52ae8e70cb04ccb1e7a8c891e3783745f2e
    76 rdf:type schema:PropertyValue
    77 Nd82df8dc33174f8cacee8bc6e931d054 rdf:first sg:person.012775002107.61
    78 rdf:rest N30a39b4ff5d04c04abfa111d948aab25
    79 Nf21fc092316649d8a44dbeb2018e5ece schema:name dimensions_id
    80 schema:value pub.1021433401
    81 rdf:type schema:PropertyValue
    82 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
    83 schema:name Information and Computing Sciences
    84 rdf:type schema:DefinedTerm
    85 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
    86 schema:name Artificial Intelligence and Image Processing
    87 rdf:type schema:DefinedTerm
    88 sg:person.012775002107.61 schema:affiliation https://www.grid.ac/institutes/grid.10837.3d
    89 schema:familyName Llorente
    90 schema:givenName Ainhoa
    91 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.012775002107.61
    92 rdf:type schema:Person
    93 sg:person.013375677533.85 schema:affiliation https://www.grid.ac/institutes/grid.10837.3d
    94 schema:familyName Rüger
    95 schema:givenName Stefan
    96 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013375677533.85
    97 rdf:type schema:Person
    98 sg:pub.10.1007/11526346_54 schema:sameAs https://app.dimensions.ai/details/publication/pub.1012604628
    99 https://doi.org/10.1007/11526346_54
    100 rdf:type schema:CreativeWork
    101 sg:pub.10.1007/3-540-47979-1_7 schema:sameAs https://app.dimensions.ai/details/publication/pub.1040055518
    102 https://doi.org/10.1007/3-540-47979-1_7
    103 rdf:type schema:CreativeWork
    104 sg:pub.10.1007/978-3-540-88690-7_24 schema:sameAs https://app.dimensions.ai/details/publication/pub.1009765396
    105 https://doi.org/10.1007/978-3-540-88690-7_24
    106 rdf:type schema:CreativeWork
    107 sg:pub.10.1007/978-3-642-04447-2_65 schema:sameAs https://app.dimensions.ai/details/publication/pub.1027852860
    108 https://doi.org/10.1007/978-3-642-04447-2_65
    109 rdf:type schema:CreativeWork
    110 https://doi.org/10.1016/j.patrec.2005.10.010 schema:sameAs https://app.dimensions.ai/details/publication/pub.1013701558
    111 rdf:type schema:CreativeWork
    112 https://doi.org/10.1080/01690969108406936 schema:sameAs https://app.dimensions.ai/details/publication/pub.1010893796
    113 rdf:type schema:CreativeWork
    114 https://doi.org/10.1145/1027527.1027732 schema:sameAs https://app.dimensions.ai/details/publication/pub.1016237565
    115 rdf:type schema:CreativeWork
    116 https://doi.org/10.1145/1101149.1101305 schema:sameAs https://app.dimensions.ai/details/publication/pub.1051369458
    117 rdf:type schema:CreativeWork
    118 https://doi.org/10.1145/1178677.1178689 schema:sameAs https://app.dimensions.ai/details/publication/pub.1037571801
    119 rdf:type schema:CreativeWork
    120 https://doi.org/10.1145/1282280.1282284 schema:sameAs https://app.dimensions.ai/details/publication/pub.1009266420
    121 rdf:type schema:CreativeWork
    122 https://doi.org/10.1145/1282280.1282369 schema:sameAs https://app.dimensions.ai/details/publication/pub.1048045132
    123 rdf:type schema:CreativeWork
    124 https://doi.org/10.1145/860435.860459 schema:sameAs https://app.dimensions.ai/details/publication/pub.1053524475
    125 rdf:type schema:CreativeWork
    126 https://doi.org/10.5244/c.21.60 schema:sameAs https://app.dimensions.ai/details/publication/pub.1099341556
    127 rdf:type schema:CreativeWork
    128 https://www.grid.ac/institutes/grid.10837.3d schema:alternateName The Open University
    129 schema:name Knowledge Media Institute, The Open University, Walton Hall, MK7 6AA, Milton Keynes, United Kingdom
    130 rdf:type schema:Organization
     




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


    ...