Approximation of Linear Discriminant Analysis for Word Dependent Visual Features Selection View Full Text


Ontology type: schema:Chapter      Open Access: True


Chapter Info

DATE

2005

AUTHORS

Hervé Glotin , Sabrina Tollari , Pascale Giraudet

ABSTRACT

To automatically determine a set of keywords that describes the content of a given image is a difficult problem, because of (i) the huge dimension number of the visual space and (ii) the unsolved object segmentation problem. Therefore, in order to solve matter (i), we present a novel method based on an Approximation of Linear Discriminant Analysis (ALDA) from the theoretical and practical point of view. Application of ALDA is more generic than usual LDA because it doesn’t require explicit class labelling of each training sample, and however allows efficient estimation of the visual features discrimination power. This is particularly interesting because of (ii) and the expensive manually object segmentation and labelling tasks on large visual database. In first step of ALDA, for each word wk, the train set is split in two, according if images are labelled or not by wk. Then, under weak assumptions, we show theoretically that Between and Within variances of these two sets are giving good estimates of the best discriminative features for wk. Experimentations are conducted on COREL database, showing an efficient word adaptive feature selection, and a great enhancement (+37%) of an image Hierarchical Ascendant Classification (HAC) for which ALDA saves also computational cost reducing by 90% the visual features space. More... »

PAGES

170-177

References to SciGraph publications

Book

TITLE

Advanced Concepts for Intelligent Vision Systems

ISBN

978-3-540-29032-2
978-3-540-32046-3

Author Affiliations

Identifiers

URI

http://scigraph.springernature.com/pub.10.1007/11558484_22

DOI

http://dx.doi.org/10.1007/11558484_22

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1036773073


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": [
            "Laboratoire Sciences de l\u2019Information et des Syst\u00e8mes-LSIS CNRS UMR6168"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Glotin", 
        "givenName": "Herv\u00e9", 
        "id": "sg:person.016622300103.82", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016622300103.82"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "name": [
            "Laboratoire Sciences de l\u2019Information et des Syst\u00e8mes-LSIS CNRS UMR6168"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Tollari", 
        "givenName": "Sabrina", 
        "id": "sg:person.014463616133.55", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.014463616133.55"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Universite De Toulon Et Du Var", 
          "id": "https://www.grid.ac/institutes/grid.12611.35", 
          "name": [
            "D\u00e9partement de Biologie, Universit\u00e9 du Sud Toulon-Var, F-83957 cedex, La Garde, France"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Giraudet", 
        "givenName": "Pascale", 
        "id": "sg:person.011351743502.63", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.011351743502.63"
        ], 
        "type": "Person"
      }
    ], 
    "citation": [
      {
        "id": "sg:pub.10.1007/s11042-005-6543-6", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1013027935", 
          "https://doi.org/10.1007/s11042-005-6543-6"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1145/1039470.1039483", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1015156204"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1145/957013.957070", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1015373141"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/3-540-45479-9_5", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1042422709", 
          "https://doi.org/10.1007/3-540-45479-9_5"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/34.868688", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061157130"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/cvpr.2003.1211532", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1093220608"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/afgr.2002.1004154", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1094335951"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/mmsp.2001.962801", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1095507139"
        ], 
        "type": "CreativeWork"
      }
    ], 
    "datePublished": "2005", 
    "datePublishedReg": "2005-01-01", 
    "description": "To automatically determine a set of keywords that describes the content of a given image is a difficult problem, because of (i) the huge dimension number of the visual space and (ii) the unsolved object segmentation problem. Therefore, in order to solve matter (i), we present a novel method based on an Approximation of Linear Discriminant Analysis (ALDA) from the theoretical and practical point of view. Application of ALDA is more generic than usual LDA because it doesn\u2019t require explicit class labelling of each training sample, and however allows efficient estimation of the visual features discrimination power. This is particularly interesting because of (ii) and the expensive manually object segmentation and labelling tasks on large visual database. In first step of ALDA, for each word wk, the train set is split in two, according if images are labelled or not by wk. Then, under weak assumptions, we show theoretically that Between and Within variances of these two sets are giving good estimates of the best discriminative features for wk. Experimentations are conducted on COREL database, showing an efficient word adaptive feature selection, and a great enhancement (+37%) of an image Hierarchical Ascendant Classification (HAC) for which ALDA saves also computational cost reducing by 90% the visual features space.", 
    "editor": [
      {
        "familyName": "Blanc-Talon", 
        "givenName": "Jacques", 
        "type": "Person"
      }, 
      {
        "familyName": "Philips", 
        "givenName": "Wilfried", 
        "type": "Person"
      }, 
      {
        "familyName": "Popescu", 
        "givenName": "Dan", 
        "type": "Person"
      }, 
      {
        "familyName": "Scheunders", 
        "givenName": "Paul", 
        "type": "Person"
      }
    ], 
    "genre": "chapter", 
    "id": "sg:pub.10.1007/11558484_22", 
    "inLanguage": [
      "en"
    ], 
    "isAccessibleForFree": true, 
    "isPartOf": {
      "isbn": [
        "978-3-540-29032-2", 
        "978-3-540-32046-3"
      ], 
      "name": "Advanced Concepts for Intelligent Vision Systems", 
      "type": "Book"
    }, 
    "name": "Approximation of Linear Discriminant Analysis for Word Dependent Visual Features Selection", 
    "pagination": "170-177", 
    "productId": [
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1036773073"
        ]
      }, 
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1007/11558484_22"
        ]
      }, 
      {
        "name": "readcube_id", 
        "type": "PropertyValue", 
        "value": [
          "af2c4e37645a4cccccdadf18d04c157c1058f0455538c5db0f081fc66b1ade38"
        ]
      }
    ], 
    "publisher": {
      "location": "Berlin, Heidelberg", 
      "name": "Springer Berlin Heidelberg", 
      "type": "Organisation"
    }, 
    "sameAs": [
      "https://doi.org/10.1007/11558484_22", 
      "https://app.dimensions.ai/details/publication/pub.1036773073"
    ], 
    "sdDataset": "chapters", 
    "sdDatePublished": "2019-04-16T07:30", 
    "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/v90/0000000356_0000000356/records_57883_00000000.jsonl", 
    "type": "Chapter", 
    "url": "https://link.springer.com/10.1007%2F11558484_22"
  }
]
 

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.10.1007/11558484_22'

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

curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/11558484_22'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/11558484_22'

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

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/11558484_22'


 

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

124 TRIPLES      23 PREDICATES      35 URIs      20 LITERALS      8 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1007/11558484_22 schema:about anzsrc-for:08
2 anzsrc-for:0801
3 schema:author N57b4adeabd2b445f82ff3042c95c1a2e
4 schema:citation sg:pub.10.1007/3-540-45479-9_5
5 sg:pub.10.1007/s11042-005-6543-6
6 https://doi.org/10.1109/34.868688
7 https://doi.org/10.1109/afgr.2002.1004154
8 https://doi.org/10.1109/cvpr.2003.1211532
9 https://doi.org/10.1109/mmsp.2001.962801
10 https://doi.org/10.1145/1039470.1039483
11 https://doi.org/10.1145/957013.957070
12 schema:datePublished 2005
13 schema:datePublishedReg 2005-01-01
14 schema:description To automatically determine a set of keywords that describes the content of a given image is a difficult problem, because of (i) the huge dimension number of the visual space and (ii) the unsolved object segmentation problem. Therefore, in order to solve matter (i), we present a novel method based on an Approximation of Linear Discriminant Analysis (ALDA) from the theoretical and practical point of view. Application of ALDA is more generic than usual LDA because it doesn’t require explicit class labelling of each training sample, and however allows efficient estimation of the visual features discrimination power. This is particularly interesting because of (ii) and the expensive manually object segmentation and labelling tasks on large visual database. In first step of ALDA, for each word wk, the train set is split in two, according if images are labelled or not by wk. Then, under weak assumptions, we show theoretically that Between and Within variances of these two sets are giving good estimates of the best discriminative features for wk. Experimentations are conducted on COREL database, showing an efficient word adaptive feature selection, and a great enhancement (+37%) of an image Hierarchical Ascendant Classification (HAC) for which ALDA saves also computational cost reducing by 90% the visual features space.
15 schema:editor N4aa01bd082f743c18d6d303fa2f4e60a
16 schema:genre chapter
17 schema:inLanguage en
18 schema:isAccessibleForFree true
19 schema:isPartOf N016ab6b75d714030868fc51f89af0e89
20 schema:name Approximation of Linear Discriminant Analysis for Word Dependent Visual Features Selection
21 schema:pagination 170-177
22 schema:productId N1232bea27fe94a4f87b9b7b3600ac604
23 N2c150a490afa4ed4abef36da02079903
24 N39e9bb62f99e4152b556196e4338825f
25 schema:publisher Nd32ebd0553ca4b03b99918d7d66d33e1
26 schema:sameAs https://app.dimensions.ai/details/publication/pub.1036773073
27 https://doi.org/10.1007/11558484_22
28 schema:sdDatePublished 2019-04-16T07:30
29 schema:sdLicense https://scigraph.springernature.com/explorer/license/
30 schema:sdPublisher N80ccc82e41c441289f48e0b8097281c8
31 schema:url https://link.springer.com/10.1007%2F11558484_22
32 sgo:license sg:explorer/license/
33 sgo:sdDataset chapters
34 rdf:type schema:Chapter
35 N016ab6b75d714030868fc51f89af0e89 schema:isbn 978-3-540-29032-2
36 978-3-540-32046-3
37 schema:name Advanced Concepts for Intelligent Vision Systems
38 rdf:type schema:Book
39 N02b1661f8050450598b4ebf94d56ffb1 schema:familyName Philips
40 schema:givenName Wilfried
41 rdf:type schema:Person
42 N0c633ad43926402cbc7ece7199af599c schema:name Laboratoire Sciences de l’Information et des Systèmes-LSIS CNRS UMR6168
43 rdf:type schema:Organization
44 N0f05bed2a78843d39081dadbb508ff23 schema:familyName Scheunders
45 schema:givenName Paul
46 rdf:type schema:Person
47 N1232bea27fe94a4f87b9b7b3600ac604 schema:name doi
48 schema:value 10.1007/11558484_22
49 rdf:type schema:PropertyValue
50 N1c11203262d74eefaafa25b86ca083db rdf:first sg:person.011351743502.63
51 rdf:rest rdf:nil
52 N1d88f47dde6d405d8ea342530f60e040 rdf:first sg:person.014463616133.55
53 rdf:rest N1c11203262d74eefaafa25b86ca083db
54 N2c150a490afa4ed4abef36da02079903 schema:name dimensions_id
55 schema:value pub.1036773073
56 rdf:type schema:PropertyValue
57 N39e9bb62f99e4152b556196e4338825f schema:name readcube_id
58 schema:value af2c4e37645a4cccccdadf18d04c157c1058f0455538c5db0f081fc66b1ade38
59 rdf:type schema:PropertyValue
60 N46dc548af5c24326809d3ead40b29f74 schema:familyName Blanc-Talon
61 schema:givenName Jacques
62 rdf:type schema:Person
63 N4942175b74644af397bbd2a67e28b438 schema:familyName Popescu
64 schema:givenName Dan
65 rdf:type schema:Person
66 N4aa01bd082f743c18d6d303fa2f4e60a rdf:first N46dc548af5c24326809d3ead40b29f74
67 rdf:rest N632395f9c8de4328a5a626d930da11f7
68 N57b4adeabd2b445f82ff3042c95c1a2e rdf:first sg:person.016622300103.82
69 rdf:rest N1d88f47dde6d405d8ea342530f60e040
70 N632395f9c8de4328a5a626d930da11f7 rdf:first N02b1661f8050450598b4ebf94d56ffb1
71 rdf:rest N7012dc7c182d49a4875b556e2b81e036
72 N7012dc7c182d49a4875b556e2b81e036 rdf:first N4942175b74644af397bbd2a67e28b438
73 rdf:rest Nfe071c47019647efabb2ad1c47537d5c
74 N80ccc82e41c441289f48e0b8097281c8 schema:name Springer Nature - SN SciGraph project
75 rdf:type schema:Organization
76 Nd32ebd0553ca4b03b99918d7d66d33e1 schema:location Berlin, Heidelberg
77 schema:name Springer Berlin Heidelberg
78 rdf:type schema:Organisation
79 Nedb4e008195b420791d44f1198ad55b0 schema:name Laboratoire Sciences de l’Information et des Systèmes-LSIS CNRS UMR6168
80 rdf:type schema:Organization
81 Nfe071c47019647efabb2ad1c47537d5c rdf:first N0f05bed2a78843d39081dadbb508ff23
82 rdf:rest rdf:nil
83 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
84 schema:name Information and Computing Sciences
85 rdf:type schema:DefinedTerm
86 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
87 schema:name Artificial Intelligence and Image Processing
88 rdf:type schema:DefinedTerm
89 sg:person.011351743502.63 schema:affiliation https://www.grid.ac/institutes/grid.12611.35
90 schema:familyName Giraudet
91 schema:givenName Pascale
92 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.011351743502.63
93 rdf:type schema:Person
94 sg:person.014463616133.55 schema:affiliation N0c633ad43926402cbc7ece7199af599c
95 schema:familyName Tollari
96 schema:givenName Sabrina
97 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.014463616133.55
98 rdf:type schema:Person
99 sg:person.016622300103.82 schema:affiliation Nedb4e008195b420791d44f1198ad55b0
100 schema:familyName Glotin
101 schema:givenName Hervé
102 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016622300103.82
103 rdf:type schema:Person
104 sg:pub.10.1007/3-540-45479-9_5 schema:sameAs https://app.dimensions.ai/details/publication/pub.1042422709
105 https://doi.org/10.1007/3-540-45479-9_5
106 rdf:type schema:CreativeWork
107 sg:pub.10.1007/s11042-005-6543-6 schema:sameAs https://app.dimensions.ai/details/publication/pub.1013027935
108 https://doi.org/10.1007/s11042-005-6543-6
109 rdf:type schema:CreativeWork
110 https://doi.org/10.1109/34.868688 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061157130
111 rdf:type schema:CreativeWork
112 https://doi.org/10.1109/afgr.2002.1004154 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094335951
113 rdf:type schema:CreativeWork
114 https://doi.org/10.1109/cvpr.2003.1211532 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093220608
115 rdf:type schema:CreativeWork
116 https://doi.org/10.1109/mmsp.2001.962801 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095507139
117 rdf:type schema:CreativeWork
118 https://doi.org/10.1145/1039470.1039483 schema:sameAs https://app.dimensions.ai/details/publication/pub.1015156204
119 rdf:type schema:CreativeWork
120 https://doi.org/10.1145/957013.957070 schema:sameAs https://app.dimensions.ai/details/publication/pub.1015373141
121 rdf:type schema:CreativeWork
122 https://www.grid.ac/institutes/grid.12611.35 schema:alternateName Universite De Toulon Et Du Var
123 schema:name Département de Biologie, Université du Sud Toulon-Var, F-83957 cedex, La Garde, France
124 rdf:type schema:Organization
 




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


...