A Probabilistic Model for Face Transformation with Application to Person Identification View Full Text


Ontology type: schema:ScholarlyArticle      Open Access: True


Article Info

DATE

2004-04-21

AUTHORS

Florent Perronnin, Jean-Luc Dugelay, Kenneth Rose

ABSTRACT

A novel approach for content-based image retrieval and its specialization to face recognition are described. While most face recognition techniques aim at modeling faces, our goal is to model the transformation between face images of the same person. As a global face transformation may be too complex to be modeled directly, it is approximated by a collection of local transformations with a constraint that imposes consistency between neighboring transformations. Local transformations and neighborhood constraints are embedded within a probabilistic framework using two-dimensional hidden Markov models (2D HMMs). We further introduce a new efficient technique, called turbo-HMM (T-HMM) for approximating intractable 2D HMMs. Experimental results on a face identification task show that our novel approach compares favorably to the popular eigenfaces and fisherfaces algorithms. More... »

PAGES

821283

Identifiers

URI

http://scigraph.springernature.com/pub.10.1155/s1110865704308012

DOI

http://dx.doi.org/10.1155/s1110865704308012

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1063207865


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/2008/08", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Information and Computing Sciences", 
        "type": "DefinedTerm"
      }, 
      {
        "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"
      }
    ], 
    "author": [
      {
        "affiliation": {
          "alternateName": "Multimedia Communications Department, Institut Eur\u00e9com, BP 193, 06904, Sophia Antipolis Cedex, France", 
          "id": "http://www.grid.ac/institutes/grid.28848.3e", 
          "name": [
            "Multimedia Communications Department, Institut Eur\u00e9com, BP 193, 06904, Sophia Antipolis Cedex, France"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Perronnin", 
        "givenName": "Florent", 
        "id": "sg:person.01320142425.13", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01320142425.13"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Multimedia Communications Department, Institut Eur\u00e9com, BP 193, 06904, Sophia Antipolis Cedex, France", 
          "id": "http://www.grid.ac/institutes/grid.28848.3e", 
          "name": [
            "Multimedia Communications Department, Institut Eur\u00e9com, BP 193, 06904, Sophia Antipolis Cedex, France"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Dugelay", 
        "givenName": "Jean-Luc", 
        "id": "sg:person.015053427343.37", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.015053427343.37"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Department of Electrical and Computer Engineering, University of California, 93106-9560, Santa Barbara, CA, USA", 
          "id": "http://www.grid.ac/institutes/grid.133342.4", 
          "name": [
            "Department of Electrical and Computer Engineering, University of California, 93106-9560, Santa Barbara, CA, USA"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Rose", 
        "givenName": "Kenneth", 
        "id": "sg:person.011715666322.11", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.011715666322.11"
        ], 
        "type": "Person"
      }
    ], 
    "datePublished": "2004-04-21", 
    "datePublishedReg": "2004-04-21", 
    "description": "A novel approach for content-based image retrieval and its specialization to face recognition are described. While most face recognition techniques aim at modeling faces, our goal is to model the transformation between face images of the same person. As a global face transformation may be too complex to be modeled directly, it is approximated by a collection of local transformations with a constraint that imposes consistency between neighboring transformations. Local transformations and neighborhood constraints are embedded within a probabilistic framework using two-dimensional hidden Markov models (2D HMMs). We further introduce a new efficient technique, called turbo-HMM (T-HMM) for approximating intractable 2D HMMs. Experimental results on a face identification task show that our novel approach compares favorably to the popular eigenfaces and fisherfaces algorithms.", 
    "genre": "article", 
    "id": "sg:pub.10.1155/s1110865704308012", 
    "inLanguage": "en", 
    "isAccessibleForFree": true, 
    "isPartOf": [
      {
        "id": "sg:journal.1371279", 
        "issn": [
          "1687-6172", 
          "1687-0433"
        ], 
        "name": "EURASIP Journal on Advances in Signal Processing", 
        "publisher": "Springer Nature", 
        "type": "Periodical"
      }, 
      {
        "issueNumber": "4", 
        "type": "PublicationIssue"
      }, 
      {
        "type": "PublicationVolume", 
        "volumeNumber": "2004"
      }
    ], 
    "keywords": [
      "content-based image retrieval", 
      "face transformation", 
      "face recognition techniques", 
      "novel approach", 
      "image retrieval", 
      "Fisherface algorithm", 
      "neighborhood constraints", 
      "person identification", 
      "modeling faces", 
      "face images", 
      "recognition techniques", 
      "new efficient technique", 
      "probabilistic framework", 
      "task show", 
      "probabilistic model", 
      "efficient technique", 
      "local transformations", 
      "Markov model", 
      "experimental results", 
      "same person", 
      "constraints", 
      "eigenfaces", 
      "algorithm", 
      "retrieval", 
      "HMM", 
      "images", 
      "technique", 
      "framework", 
      "recognition", 
      "applications", 
      "model", 
      "transformation", 
      "collection", 
      "goal", 
      "consistency", 
      "show", 
      "face", 
      "identification", 
      "results", 
      "persons", 
      "specialization", 
      "approach", 
      "most face recognition techniques", 
      "global face transformation", 
      "neighboring transformations", 
      "turbo-HMM", 
      "face identification task show", 
      "identification task show", 
      "popular eigenfaces"
    ], 
    "name": "A Probabilistic Model for Face Transformation with Application to Person Identification", 
    "pagination": "821283", 
    "productId": [
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1063207865"
        ]
      }, 
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1155/s1110865704308012"
        ]
      }
    ], 
    "sameAs": [
      "https://doi.org/10.1155/s1110865704308012", 
      "https://app.dimensions.ai/details/publication/pub.1063207865"
    ], 
    "sdDataset": "articles", 
    "sdDatePublished": "2022-01-01T18:13", 
    "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
    "sdPublisher": {
      "name": "Springer Nature - SN SciGraph project", 
      "type": "Organization"
    }, 
    "sdSource": "s3://com-springernature-scigraph/baseset/20220101/entities/gbq_results/article/article_390.jsonl", 
    "type": "ScholarlyArticle", 
    "url": "https://doi.org/10.1155/s1110865704308012"
  }
]
 

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.10.1155/s1110865704308012'

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

curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1155/s1110865704308012'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1155/s1110865704308012'

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

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1155/s1110865704308012'


 

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

124 TRIPLES      21 PREDICATES      74 URIs      66 LITERALS      6 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1155/s1110865704308012 schema:about anzsrc-for:08
2 anzsrc-for:0801
3 schema:author N08c65523a31a4f309ec155dccf29fdb0
4 schema:datePublished 2004-04-21
5 schema:datePublishedReg 2004-04-21
6 schema:description A novel approach for content-based image retrieval and its specialization to face recognition are described. While most face recognition techniques aim at modeling faces, our goal is to model the transformation between face images of the same person. As a global face transformation may be too complex to be modeled directly, it is approximated by a collection of local transformations with a constraint that imposes consistency between neighboring transformations. Local transformations and neighborhood constraints are embedded within a probabilistic framework using two-dimensional hidden Markov models (2D HMMs). We further introduce a new efficient technique, called turbo-HMM (T-HMM) for approximating intractable 2D HMMs. Experimental results on a face identification task show that our novel approach compares favorably to the popular eigenfaces and fisherfaces algorithms.
7 schema:genre article
8 schema:inLanguage en
9 schema:isAccessibleForFree true
10 schema:isPartOf N44d7e75ad52c4bb48bc184739f69c58e
11 N712d22b6d8be4f9d8463b56071ccc9bc
12 sg:journal.1371279
13 schema:keywords Fisherface algorithm
14 HMM
15 Markov model
16 algorithm
17 applications
18 approach
19 collection
20 consistency
21 constraints
22 content-based image retrieval
23 efficient technique
24 eigenfaces
25 experimental results
26 face
27 face identification task show
28 face images
29 face recognition techniques
30 face transformation
31 framework
32 global face transformation
33 goal
34 identification
35 identification task show
36 image retrieval
37 images
38 local transformations
39 model
40 modeling faces
41 most face recognition techniques
42 neighborhood constraints
43 neighboring transformations
44 new efficient technique
45 novel approach
46 person identification
47 persons
48 popular eigenfaces
49 probabilistic framework
50 probabilistic model
51 recognition
52 recognition techniques
53 results
54 retrieval
55 same person
56 show
57 specialization
58 task show
59 technique
60 transformation
61 turbo-HMM
62 schema:name A Probabilistic Model for Face Transformation with Application to Person Identification
63 schema:pagination 821283
64 schema:productId N535b5f2e39bb4f35a3b58207274b67f4
65 Nd17d3dcff671459fa0f0de7a7d0ce764
66 schema:sameAs https://app.dimensions.ai/details/publication/pub.1063207865
67 https://doi.org/10.1155/s1110865704308012
68 schema:sdDatePublished 2022-01-01T18:13
69 schema:sdLicense https://scigraph.springernature.com/explorer/license/
70 schema:sdPublisher N4d8250e9ffc24204a5523e82e296b729
71 schema:url https://doi.org/10.1155/s1110865704308012
72 sgo:license sg:explorer/license/
73 sgo:sdDataset articles
74 rdf:type schema:ScholarlyArticle
75 N08c65523a31a4f309ec155dccf29fdb0 rdf:first sg:person.01320142425.13
76 rdf:rest N8f828562c472428c89b357800d97e2d2
77 N44d7e75ad52c4bb48bc184739f69c58e schema:issueNumber 4
78 rdf:type schema:PublicationIssue
79 N4d8250e9ffc24204a5523e82e296b729 schema:name Springer Nature - SN SciGraph project
80 rdf:type schema:Organization
81 N535b5f2e39bb4f35a3b58207274b67f4 schema:name dimensions_id
82 schema:value pub.1063207865
83 rdf:type schema:PropertyValue
84 N712d22b6d8be4f9d8463b56071ccc9bc schema:volumeNumber 2004
85 rdf:type schema:PublicationVolume
86 N8a6fcb69e46e4f308c91427e21770bc4 rdf:first sg:person.011715666322.11
87 rdf:rest rdf:nil
88 N8f828562c472428c89b357800d97e2d2 rdf:first sg:person.015053427343.37
89 rdf:rest N8a6fcb69e46e4f308c91427e21770bc4
90 Nd17d3dcff671459fa0f0de7a7d0ce764 schema:name doi
91 schema:value 10.1155/s1110865704308012
92 rdf:type schema:PropertyValue
93 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
94 schema:name Information and Computing Sciences
95 rdf:type schema:DefinedTerm
96 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
97 schema:name Artificial Intelligence and Image Processing
98 rdf:type schema:DefinedTerm
99 sg:journal.1371279 schema:issn 1687-0433
100 1687-6172
101 schema:name EURASIP Journal on Advances in Signal Processing
102 schema:publisher Springer Nature
103 rdf:type schema:Periodical
104 sg:person.011715666322.11 schema:affiliation grid-institutes:grid.133342.4
105 schema:familyName Rose
106 schema:givenName Kenneth
107 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.011715666322.11
108 rdf:type schema:Person
109 sg:person.01320142425.13 schema:affiliation grid-institutes:grid.28848.3e
110 schema:familyName Perronnin
111 schema:givenName Florent
112 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01320142425.13
113 rdf:type schema:Person
114 sg:person.015053427343.37 schema:affiliation grid-institutes:grid.28848.3e
115 schema:familyName Dugelay
116 schema:givenName Jean-Luc
117 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.015053427343.37
118 rdf:type schema:Person
119 grid-institutes:grid.133342.4 schema:alternateName Department of Electrical and Computer Engineering, University of California, 93106-9560, Santa Barbara, CA, USA
120 schema:name Department of Electrical and Computer Engineering, University of California, 93106-9560, Santa Barbara, CA, USA
121 rdf:type schema:Organization
122 grid-institutes:grid.28848.3e schema:alternateName Multimedia Communications Department, Institut Eurécom, BP 193, 06904, Sophia Antipolis Cedex, France
123 schema:name Multimedia Communications Department, Institut Eurécom, BP 193, 06904, Sophia Antipolis Cedex, France
124 rdf:type schema:Organization
 




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


...