Interactive Image Segmentation Using an Adaptive GMMRF Model View Full Text


Ontology type: schema:Chapter     


Chapter Info

DATE

2004

AUTHORS

Andrew Blake , Carsten Rother , M. Brown , Patrick Perez , Philip Torr

ABSTRACT

The problem of interactive foreground/background segmentation in still images is of great practical importance in image editing. The state of the art in interactive segmentation is probably represented by the graph cut algorithm of Boykov and Jolly (ICCV 2001). Its underlying model uses both colour and contrast information, together with a strong prior for region coherence. Estimation is performed by solving a graph cut problem for which very efficient algorithms have recently been developed. However the model depends on parameters which must be set by hand and the aim of this work is for those constants to be learned from image data. First, a generative, probabilistic formulation of the model is set out in terms of a “Gaussian Mixture Markov Random Field” (GMMRF). Secondly, a pseudolikelihood algorithm is derived which jointly learns the colour mixture and coherence parameters for foreground and background respectively. Error rates for GMMRF segmentation are calculated throughout using a new image database, available on the web, with ground truth provided by a human segmenter. The graph cut algorithm, using the learned parameters, generates good object-segmentations with little interaction. However, pseudolikelihood learning proves to be frail, which limits the complexity of usable models, and hence also the achievable error rate. More... »

PAGES

428-441

References to SciGraph publications

Book

TITLE

Computer Vision - ECCV 2004

ISBN

978-3-540-21984-2
978-3-540-24670-1

Identifiers

URI

http://scigraph.springernature.com/pub.10.1007/978-3-540-24670-1_33

DOI

http://dx.doi.org/10.1007/978-3-540-24670-1_33

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1017586951


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": "Microsoft Research (United Kingdom)", 
          "id": "https://www.grid.ac/institutes/grid.24488.32", 
          "name": [
            "Microsoft Research Cambridge UK, 7 JJ Thomson Avenue, CB3 0FB, Cambridge, UK"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Blake", 
        "givenName": "Andrew", 
        "id": "sg:person.014544741617.06", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.014544741617.06"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Microsoft Research (United Kingdom)", 
          "id": "https://www.grid.ac/institutes/grid.24488.32", 
          "name": [
            "Microsoft Research Cambridge UK, 7 JJ Thomson Avenue, CB3 0FB, Cambridge, UK"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Rother", 
        "givenName": "Carsten", 
        "id": "sg:person.0621771321.07", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0621771321.07"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Microsoft Research (United Kingdom)", 
          "id": "https://www.grid.ac/institutes/grid.24488.32", 
          "name": [
            "Microsoft Research Cambridge UK, 7 JJ Thomson Avenue, CB3 0FB, Cambridge, UK"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Brown", 
        "givenName": "M.", 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Microsoft Research (United Kingdom)", 
          "id": "https://www.grid.ac/institutes/grid.24488.32", 
          "name": [
            "Microsoft Research Cambridge UK, 7 JJ Thomson Avenue, CB3 0FB, Cambridge, UK"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Perez", 
        "givenName": "Patrick", 
        "id": "sg:person.016077665647.41", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016077665647.41"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Microsoft Research (United Kingdom)", 
          "id": "https://www.grid.ac/institutes/grid.24488.32", 
          "name": [
            "Microsoft Research Cambridge UK, 7 JJ Thomson Avenue, CB3 0FB, Cambridge, UK"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Torr", 
        "givenName": "Philip", 
        "id": "sg:person.011757175441.72", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.011757175441.72"
        ], 
        "type": "Person"
      }
    ], 
    "citation": [
      {
        "id": "sg:pub.10.1023/a:1011174803800", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1034375628", 
          "https://doi.org/10.1023/a:1011174803800"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/978-3-642-97522-6", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1053595130", 
          "https://doi.org/10.1007/978-3-642-97522-6"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/978-3-642-97522-6", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1053595130", 
          "https://doi.org/10.1007/978-3-642-97522-6"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/83.753737", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061239893"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/tpami.1984.4767596", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061742090"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/cvpr.2000.855793", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1094850725"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/iccv.2001.937505", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1095383001"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/iccv.2003.1238478", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1095814952"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1111/j.2517-6161.1986.tb01412.x", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1110458509"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1111/j.2517-6161.1986.tb01412.x", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1110458509"
        ], 
        "type": "CreativeWork"
      }
    ], 
    "datePublished": "2004", 
    "datePublishedReg": "2004-01-01", 
    "description": "The problem of interactive foreground/background segmentation in still images is of great practical importance in image editing. The state of the art in interactive segmentation is probably represented by the graph cut algorithm of Boykov and Jolly (ICCV 2001). Its underlying model uses both colour and contrast information, together with a strong prior for region coherence. Estimation is performed by solving a graph cut problem for which very efficient algorithms have recently been developed. However the model depends on parameters which must be set by hand and the aim of this work is for those constants to be learned from image data. First, a generative, probabilistic formulation of the model is set out in terms of a \u201cGaussian Mixture Markov Random Field\u201d (GMMRF). Secondly, a pseudolikelihood algorithm is derived which jointly learns the colour mixture and coherence parameters for foreground and background respectively. Error rates for GMMRF segmentation are calculated throughout using a new image database, available on the web, with ground truth provided by a human segmenter. The graph cut algorithm, using the learned parameters, generates good object-segmentations with little interaction. However, pseudolikelihood learning proves to be frail, which limits the complexity of usable models, and hence also the achievable error rate.", 
    "editor": [
      {
        "familyName": "Pajdla", 
        "givenName": "Tom\u00e1s", 
        "type": "Person"
      }, 
      {
        "familyName": "Matas", 
        "givenName": "Ji\u0159\u00ed", 
        "type": "Person"
      }
    ], 
    "genre": "chapter", 
    "id": "sg:pub.10.1007/978-3-540-24670-1_33", 
    "inLanguage": [
      "en"
    ], 
    "isAccessibleForFree": false, 
    "isPartOf": {
      "isbn": [
        "978-3-540-21984-2", 
        "978-3-540-24670-1"
      ], 
      "name": "Computer Vision - ECCV 2004", 
      "type": "Book"
    }, 
    "name": "Interactive Image Segmentation Using an Adaptive GMMRF Model", 
    "pagination": "428-441", 
    "productId": [
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1017586951"
        ]
      }, 
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1007/978-3-540-24670-1_33"
        ]
      }, 
      {
        "name": "readcube_id", 
        "type": "PropertyValue", 
        "value": [
          "53ca8f1ff1b7d95ed7c2bc8ddde7e63664d2097722ce584231fa5f2bcfc86754"
        ]
      }
    ], 
    "publisher": {
      "location": "Berlin, Heidelberg", 
      "name": "Springer Berlin Heidelberg", 
      "type": "Organisation"
    }, 
    "sameAs": [
      "https://doi.org/10.1007/978-3-540-24670-1_33", 
      "https://app.dimensions.ai/details/publication/pub.1017586951"
    ], 
    "sdDataset": "chapters", 
    "sdDatePublished": "2019-04-16T08:10", 
    "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/v90/0000000360_0000000360/records_118344_00000000.jsonl", 
    "type": "Chapter", 
    "url": "https://link.springer.com/10.1007%2F978-3-540-24670-1_33"
  }
]
 

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.10.1007/978-3-540-24670-1_33'

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

curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/978-3-540-24670-1_33'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/978-3-540-24670-1_33'

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

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/978-3-540-24670-1_33'


 

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

123 TRIPLES      23 PREDICATES      35 URIs      20 LITERALS      8 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1007/978-3-540-24670-1_33 schema:about anzsrc-for:08
2 anzsrc-for:0801
3 schema:author Nd1a4dc5170b6493ca0104456199e249b
4 schema:citation sg:pub.10.1007/978-3-642-97522-6
5 sg:pub.10.1023/a:1011174803800
6 https://doi.org/10.1109/83.753737
7 https://doi.org/10.1109/cvpr.2000.855793
8 https://doi.org/10.1109/iccv.2001.937505
9 https://doi.org/10.1109/iccv.2003.1238478
10 https://doi.org/10.1109/tpami.1984.4767596
11 https://doi.org/10.1111/j.2517-6161.1986.tb01412.x
12 schema:datePublished 2004
13 schema:datePublishedReg 2004-01-01
14 schema:description The problem of interactive foreground/background segmentation in still images is of great practical importance in image editing. The state of the art in interactive segmentation is probably represented by the graph cut algorithm of Boykov and Jolly (ICCV 2001). Its underlying model uses both colour and contrast information, together with a strong prior for region coherence. Estimation is performed by solving a graph cut problem for which very efficient algorithms have recently been developed. However the model depends on parameters which must be set by hand and the aim of this work is for those constants to be learned from image data. First, a generative, probabilistic formulation of the model is set out in terms of a “Gaussian Mixture Markov Random Field” (GMMRF). Secondly, a pseudolikelihood algorithm is derived which jointly learns the colour mixture and coherence parameters for foreground and background respectively. Error rates for GMMRF segmentation are calculated throughout using a new image database, available on the web, with ground truth provided by a human segmenter. The graph cut algorithm, using the learned parameters, generates good object-segmentations with little interaction. However, pseudolikelihood learning proves to be frail, which limits the complexity of usable models, and hence also the achievable error rate.
15 schema:editor Nd4edfbf942d7442e9321457ef4fc4cea
16 schema:genre chapter
17 schema:inLanguage en
18 schema:isAccessibleForFree false
19 schema:isPartOf N8b7e009b6ef94f68b1e1e4e3fc78b196
20 schema:name Interactive Image Segmentation Using an Adaptive GMMRF Model
21 schema:pagination 428-441
22 schema:productId N46645df560e241949b5d8a7c19d67c06
23 N557c924317e24bbe92965590a6437fe1
24 N64df070a86e34075b33cf44f15c27563
25 schema:publisher Nb6c3e3b9f1ee48348eb6dff8ad5e75ca
26 schema:sameAs https://app.dimensions.ai/details/publication/pub.1017586951
27 https://doi.org/10.1007/978-3-540-24670-1_33
28 schema:sdDatePublished 2019-04-16T08:10
29 schema:sdLicense https://scigraph.springernature.com/explorer/license/
30 schema:sdPublisher Nf95d27ef55bf424c9cd34fae3babb9aa
31 schema:url https://link.springer.com/10.1007%2F978-3-540-24670-1_33
32 sgo:license sg:explorer/license/
33 sgo:sdDataset chapters
34 rdf:type schema:Chapter
35 N14b2a30ddeb14bd3ad9eaeb75842371b rdf:first sg:person.0621771321.07
36 rdf:rest N33726f78b5694d92aa507e2ee07474a4
37 N33726f78b5694d92aa507e2ee07474a4 rdf:first N6e4d562f51384364874ab363a61fa1b8
38 rdf:rest N6d841154098a46efb14488446e77804c
39 N352c1aa4a0d449a9a07886a8c12866ff schema:familyName Pajdla
40 schema:givenName Tomás
41 rdf:type schema:Person
42 N46645df560e241949b5d8a7c19d67c06 schema:name readcube_id
43 schema:value 53ca8f1ff1b7d95ed7c2bc8ddde7e63664d2097722ce584231fa5f2bcfc86754
44 rdf:type schema:PropertyValue
45 N557c924317e24bbe92965590a6437fe1 schema:name dimensions_id
46 schema:value pub.1017586951
47 rdf:type schema:PropertyValue
48 N64df070a86e34075b33cf44f15c27563 schema:name doi
49 schema:value 10.1007/978-3-540-24670-1_33
50 rdf:type schema:PropertyValue
51 N6d841154098a46efb14488446e77804c rdf:first sg:person.016077665647.41
52 rdf:rest N9514fbc2b6ec4b22b3ffd6469ea8a516
53 N6e4d562f51384364874ab363a61fa1b8 schema:affiliation https://www.grid.ac/institutes/grid.24488.32
54 schema:familyName Brown
55 schema:givenName M.
56 rdf:type schema:Person
57 N8b7e009b6ef94f68b1e1e4e3fc78b196 schema:isbn 978-3-540-21984-2
58 978-3-540-24670-1
59 schema:name Computer Vision - ECCV 2004
60 rdf:type schema:Book
61 N9514fbc2b6ec4b22b3ffd6469ea8a516 rdf:first sg:person.011757175441.72
62 rdf:rest rdf:nil
63 Naa0a1caa49ec427a815bbd3ceac58bff schema:familyName Matas
64 schema:givenName Jiří
65 rdf:type schema:Person
66 Naed3c3426b32448ea5fefbe6e7bc9d1d rdf:first Naa0a1caa49ec427a815bbd3ceac58bff
67 rdf:rest rdf:nil
68 Nb6c3e3b9f1ee48348eb6dff8ad5e75ca schema:location Berlin, Heidelberg
69 schema:name Springer Berlin Heidelberg
70 rdf:type schema:Organisation
71 Nd1a4dc5170b6493ca0104456199e249b rdf:first sg:person.014544741617.06
72 rdf:rest N14b2a30ddeb14bd3ad9eaeb75842371b
73 Nd4edfbf942d7442e9321457ef4fc4cea rdf:first N352c1aa4a0d449a9a07886a8c12866ff
74 rdf:rest Naed3c3426b32448ea5fefbe6e7bc9d1d
75 Nf95d27ef55bf424c9cd34fae3babb9aa 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.011757175441.72 schema:affiliation https://www.grid.ac/institutes/grid.24488.32
84 schema:familyName Torr
85 schema:givenName Philip
86 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.011757175441.72
87 rdf:type schema:Person
88 sg:person.014544741617.06 schema:affiliation https://www.grid.ac/institutes/grid.24488.32
89 schema:familyName Blake
90 schema:givenName Andrew
91 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.014544741617.06
92 rdf:type schema:Person
93 sg:person.016077665647.41 schema:affiliation https://www.grid.ac/institutes/grid.24488.32
94 schema:familyName Perez
95 schema:givenName Patrick
96 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016077665647.41
97 rdf:type schema:Person
98 sg:person.0621771321.07 schema:affiliation https://www.grid.ac/institutes/grid.24488.32
99 schema:familyName Rother
100 schema:givenName Carsten
101 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0621771321.07
102 rdf:type schema:Person
103 sg:pub.10.1007/978-3-642-97522-6 schema:sameAs https://app.dimensions.ai/details/publication/pub.1053595130
104 https://doi.org/10.1007/978-3-642-97522-6
105 rdf:type schema:CreativeWork
106 sg:pub.10.1023/a:1011174803800 schema:sameAs https://app.dimensions.ai/details/publication/pub.1034375628
107 https://doi.org/10.1023/a:1011174803800
108 rdf:type schema:CreativeWork
109 https://doi.org/10.1109/83.753737 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061239893
110 rdf:type schema:CreativeWork
111 https://doi.org/10.1109/cvpr.2000.855793 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094850725
112 rdf:type schema:CreativeWork
113 https://doi.org/10.1109/iccv.2001.937505 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095383001
114 rdf:type schema:CreativeWork
115 https://doi.org/10.1109/iccv.2003.1238478 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095814952
116 rdf:type schema:CreativeWork
117 https://doi.org/10.1109/tpami.1984.4767596 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061742090
118 rdf:type schema:CreativeWork
119 https://doi.org/10.1111/j.2517-6161.1986.tb01412.x schema:sameAs https://app.dimensions.ai/details/publication/pub.1110458509
120 rdf:type schema:CreativeWork
121 https://www.grid.ac/institutes/grid.24488.32 schema:alternateName Microsoft Research (United Kingdom)
122 schema:name Microsoft Research Cambridge UK, 7 JJ Thomson Avenue, CB3 0FB, Cambridge, UK
123 rdf:type schema:Organization
 




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


...