Finding pictures of objects in large collections of images View Full Text


Ontology type: schema:Chapter     


Chapter Info

DATE

1996

AUTHORS

David A. Forsyth , Jitendra Malik , Margaret M. Fleck , Hayit Greenspan , Thomas Leung , Serge Belongie , Chad Carson , Chris Bregler

ABSTRACT

Retrieving images from very large collections, using image content as a key, is becoming an important problem. Users prefer to ask for pictures using notions of content that are strongly oriented to the presence of abstractly defined objects. Computer programs that implement these queries automatically are desirable, but are hard to build because conventional object recognition techniques from computer vision cannot recognize very general objects in very general contexts.This paper describes our approach to object recognition, which is structured around a sequence of increasingly specialized grouping activities that assemble coherent regions of image that can be shown to satisfy increasingly stringent constraints. The constraints that are satisfied provide a form of object classification in quite general contexts.This view of recognition is distinguished by: far richer involvement of early visual primitives, including color and texture; hierarchical grouping and learning strategies in the classification process; the ability to deal with rather general objects in uncontrolled configurations and contexts. We illustrate these properties with four case-studies: one demonstrating the use of color and texture descriptors; one showing how trees can be described by fusing texture and geometric properties; one learning scenery concepts using grouped features; and one showing how this view of recognition yields a program that can tell, quite accurately, whether a picture contains naked people or not. More... »

PAGES

335-360

Identifiers

URI

http://scigraph.springernature.com/pub.10.1007/3-540-61750-7_36

DOI

http://dx.doi.org/10.1007/3-540-61750-7_36

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1027781561


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": "Computer Science Division, University of California at Berkeley, 94720, Berkeley, CA", 
          "id": "http://www.grid.ac/institutes/grid.47840.3f", 
          "name": [
            "Computer Science Division, University of California at Berkeley, 94720, Berkeley, CA"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Forsyth", 
        "givenName": "David A.", 
        "id": "sg:person.0717704704.38", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0717704704.38"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Computer Science Division, University of California at Berkeley, 94720, Berkeley, CA", 
          "id": "http://www.grid.ac/institutes/grid.47840.3f", 
          "name": [
            "Computer Science Division, University of California at Berkeley, 94720, Berkeley, CA"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Malik", 
        "givenName": "Jitendra", 
        "id": "sg:person.01364521761.84", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01364521761.84"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Dept. of Computer Science, University of Iowa, 52240, Iowa City, IA", 
          "id": "http://www.grid.ac/institutes/grid.214572.7", 
          "name": [
            "Dept. of Computer Science, University of Iowa, 52240, Iowa City, IA"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Fleck", 
        "givenName": "Margaret M.", 
        "id": "sg:person.013046646437.82", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013046646437.82"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Dept. of Electrical Engineering, Caltech, 91125, Pasadena, CA", 
          "id": "http://www.grid.ac/institutes/grid.20861.3d", 
          "name": [
            "Computer Science Division, University of California at Berkeley, 94720, Berkeley, CA", 
            "Dept. of Electrical Engineering, Caltech, 91125, Pasadena, CA"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Greenspan", 
        "givenName": "Hayit", 
        "id": "sg:person.0740775377.81", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0740775377.81"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Computer Science Division, University of California at Berkeley, 94720, Berkeley, CA", 
          "id": "http://www.grid.ac/institutes/grid.47840.3f", 
          "name": [
            "Computer Science Division, University of California at Berkeley, 94720, Berkeley, CA"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Leung", 
        "givenName": "Thomas", 
        "id": "sg:person.016034550437.98", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016034550437.98"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Computer Science Division, University of California at Berkeley, 94720, Berkeley, CA", 
          "id": "http://www.grid.ac/institutes/grid.47840.3f", 
          "name": [
            "Computer Science Division, University of California at Berkeley, 94720, Berkeley, CA"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Belongie", 
        "givenName": "Serge", 
        "id": "sg:person.0632735744.68", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0632735744.68"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Computer Science Division, University of California at Berkeley, 94720, Berkeley, CA", 
          "id": "http://www.grid.ac/institutes/grid.47840.3f", 
          "name": [
            "Computer Science Division, University of California at Berkeley, 94720, Berkeley, CA"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Carson", 
        "givenName": "Chad", 
        "id": "sg:person.010127057637.42", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010127057637.42"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Computer Science Division, University of California at Berkeley, 94720, Berkeley, CA", 
          "id": "http://www.grid.ac/institutes/grid.47840.3f", 
          "name": [
            "Computer Science Division, University of California at Berkeley, 94720, Berkeley, CA"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Bregler", 
        "givenName": "Chris", 
        "id": "sg:person.013255604017.26", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013255604017.26"
        ], 
        "type": "Person"
      }
    ], 
    "datePublished": "1996", 
    "datePublishedReg": "1996-01-01", 
    "description": "Retrieving images from very large collections, using image content as a key, is becoming an important problem. Users prefer to ask for pictures using notions of content that are strongly oriented to the presence of abstractly defined objects. Computer programs that implement these queries automatically are desirable, but are hard to build because conventional object recognition techniques from computer vision cannot recognize very general objects in very general contexts.This paper describes our approach to object recognition, which is structured around a sequence of increasingly specialized grouping activities that assemble coherent regions of image that can be shown to satisfy increasingly stringent constraints. The constraints that are satisfied provide a form of object classification in quite general contexts.This view of recognition is distinguished by: far richer involvement of early visual primitives, including color and texture; hierarchical grouping and learning strategies in the classification process; the ability to deal with rather general objects in uncontrolled configurations and contexts. We illustrate these properties with four case-studies: one demonstrating the use of color and texture descriptors; one showing how trees can be described by fusing texture and geometric properties; one learning scenery concepts using grouped features; and one showing how this view of recognition yields a program that can tell, quite accurately, whether a picture contains naked people or not.", 
    "editor": [
      {
        "familyName": "Ponce", 
        "givenName": "Jean", 
        "type": "Person"
      }, 
      {
        "familyName": "Zisserman", 
        "givenName": "Andrew", 
        "type": "Person"
      }, 
      {
        "familyName": "Hebert", 
        "givenName": "Martial", 
        "type": "Person"
      }
    ], 
    "genre": "chapter", 
    "id": "sg:pub.10.1007/3-540-61750-7_36", 
    "isAccessibleForFree": false, 
    "isPartOf": {
      "isbn": [
        "978-3-540-61750-1", 
        "978-3-540-70673-1"
      ], 
      "name": "Object Representation in Computer Vision II", 
      "type": "Book"
    }, 
    "keywords": [
      "object recognition techniques", 
      "large collection", 
      "general objects", 
      "computer vision", 
      "image content", 
      "object classification", 
      "visual primitives", 
      "recognition techniques", 
      "texture descriptors", 
      "classification process", 
      "rich involvement", 
      "hierarchical grouping", 
      "important problem", 
      "view of recognition", 
      "naked people", 
      "use of color", 
      "objects", 
      "images", 
      "uncontrolled configuration", 
      "computer program", 
      "coherent regions", 
      "queries", 
      "recognition", 
      "general context", 
      "primitives", 
      "users", 
      "constraints", 
      "notion of content", 
      "collection", 
      "stringent constraints", 
      "descriptors", 
      "geometric properties", 
      "vision", 
      "classification", 
      "context", 
      "key", 
      "texture", 
      "view", 
      "trees", 
      "features", 
      "concept", 
      "pictures of objects", 
      "technique", 
      "color", 
      "program", 
      "picture", 
      "grouping", 
      "notion", 
      "configuration", 
      "process", 
      "strategies", 
      "use", 
      "people", 
      "content", 
      "sequence", 
      "ability", 
      "form", 
      "properties", 
      "region", 
      "activity", 
      "presence", 
      "involvement", 
      "yield", 
      "paper", 
      "problem", 
      "approach"
    ], 
    "name": "Finding pictures of objects in large collections of images", 
    "pagination": "335-360", 
    "productId": [
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1027781561"
        ]
      }, 
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1007/3-540-61750-7_36"
        ]
      }
    ], 
    "publisher": {
      "name": "Springer Nature", 
      "type": "Organisation"
    }, 
    "sameAs": [
      "https://doi.org/10.1007/3-540-61750-7_36", 
      "https://app.dimensions.ai/details/publication/pub.1027781561"
    ], 
    "sdDataset": "chapters", 
    "sdDatePublished": "2022-12-01T06:47", 
    "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
    "sdPublisher": {
      "name": "Springer Nature - SN SciGraph project", 
      "type": "Organization"
    }, 
    "sdSource": "s3://com-springernature-scigraph/baseset/20221201/entities/gbq_results/chapter/chapter_163.jsonl", 
    "type": "Chapter", 
    "url": "https://doi.org/10.1007/3-540-61750-7_36"
  }
]
 

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.10.1007/3-540-61750-7_36'

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

curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/3-540-61750-7_36'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/3-540-61750-7_36'

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

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/3-540-61750-7_36'


 

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

191 TRIPLES      22 PREDICATES      91 URIs      84 LITERALS      7 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1007/3-540-61750-7_36 schema:about anzsrc-for:08
2 anzsrc-for:0801
3 schema:author N4f59ff8233e94c9abbab8f82a3963c70
4 schema:datePublished 1996
5 schema:datePublishedReg 1996-01-01
6 schema:description Retrieving images from very large collections, using image content as a key, is becoming an important problem. Users prefer to ask for pictures using notions of content that are strongly oriented to the presence of abstractly defined objects. Computer programs that implement these queries automatically are desirable, but are hard to build because conventional object recognition techniques from computer vision cannot recognize very general objects in very general contexts.This paper describes our approach to object recognition, which is structured around a sequence of increasingly specialized grouping activities that assemble coherent regions of image that can be shown to satisfy increasingly stringent constraints. The constraints that are satisfied provide a form of object classification in quite general contexts.This view of recognition is distinguished by: far richer involvement of early visual primitives, including color and texture; hierarchical grouping and learning strategies in the classification process; the ability to deal with rather general objects in uncontrolled configurations and contexts. We illustrate these properties with four case-studies: one demonstrating the use of color and texture descriptors; one showing how trees can be described by fusing texture and geometric properties; one learning scenery concepts using grouped features; and one showing how this view of recognition yields a program that can tell, quite accurately, whether a picture contains naked people or not.
7 schema:editor Ncfe915e6234e4e9eb46db78f62e2a2b0
8 schema:genre chapter
9 schema:isAccessibleForFree false
10 schema:isPartOf Nc4edc830470644999563a40fe9e101d0
11 schema:keywords ability
12 activity
13 approach
14 classification
15 classification process
16 coherent regions
17 collection
18 color
19 computer program
20 computer vision
21 concept
22 configuration
23 constraints
24 content
25 context
26 descriptors
27 features
28 form
29 general context
30 general objects
31 geometric properties
32 grouping
33 hierarchical grouping
34 image content
35 images
36 important problem
37 involvement
38 key
39 large collection
40 naked people
41 notion
42 notion of content
43 object classification
44 object recognition techniques
45 objects
46 paper
47 people
48 picture
49 pictures of objects
50 presence
51 primitives
52 problem
53 process
54 program
55 properties
56 queries
57 recognition
58 recognition techniques
59 region
60 rich involvement
61 sequence
62 strategies
63 stringent constraints
64 technique
65 texture
66 texture descriptors
67 trees
68 uncontrolled configuration
69 use
70 use of color
71 users
72 view
73 view of recognition
74 vision
75 visual primitives
76 yield
77 schema:name Finding pictures of objects in large collections of images
78 schema:pagination 335-360
79 schema:productId N50a3fcfacb4b4eecae95d475b40a2eeb
80 N92dc1b85e1a44019ab68faa9d276dd72
81 schema:publisher N01d732815fca47d983fc2a90742649fc
82 schema:sameAs https://app.dimensions.ai/details/publication/pub.1027781561
83 https://doi.org/10.1007/3-540-61750-7_36
84 schema:sdDatePublished 2022-12-01T06:47
85 schema:sdLicense https://scigraph.springernature.com/explorer/license/
86 schema:sdPublisher N5704aa18280243e2b6b2b5fb084f1585
87 schema:url https://doi.org/10.1007/3-540-61750-7_36
88 sgo:license sg:explorer/license/
89 sgo:sdDataset chapters
90 rdf:type schema:Chapter
91 N01d732815fca47d983fc2a90742649fc schema:name Springer Nature
92 rdf:type schema:Organisation
93 N09a555ceff0649b0b7bc0622c6e8d64f rdf:first sg:person.0740775377.81
94 rdf:rest Ncb543eecbc9a4e5dba8e76001496f3c9
95 N2915a7a60c984251996beeebd2ba8121 rdf:first sg:person.013255604017.26
96 rdf:rest rdf:nil
97 N3c2ca204210b4cb0a6abe63f32869f55 schema:familyName Ponce
98 schema:givenName Jean
99 rdf:type schema:Person
100 N466baff53ce94df2af456121f5494d0f rdf:first sg:person.0632735744.68
101 rdf:rest N7f7f523aed784a84a30ee761540a232b
102 N4f59ff8233e94c9abbab8f82a3963c70 rdf:first sg:person.0717704704.38
103 rdf:rest Nee197e6c0872418b89e4e11b5ce31f23
104 N50a3fcfacb4b4eecae95d475b40a2eeb schema:name dimensions_id
105 schema:value pub.1027781561
106 rdf:type schema:PropertyValue
107 N5704aa18280243e2b6b2b5fb084f1585 schema:name Springer Nature - SN SciGraph project
108 rdf:type schema:Organization
109 N7f7f523aed784a84a30ee761540a232b rdf:first sg:person.010127057637.42
110 rdf:rest N2915a7a60c984251996beeebd2ba8121
111 N92dc1b85e1a44019ab68faa9d276dd72 schema:name doi
112 schema:value 10.1007/3-540-61750-7_36
113 rdf:type schema:PropertyValue
114 Na14725905fa34a0fbe74492676ec6a63 schema:familyName Zisserman
115 schema:givenName Andrew
116 rdf:type schema:Person
117 Nb06ad22d6e7d4f20a8fb696130b154b2 rdf:first sg:person.013046646437.82
118 rdf:rest N09a555ceff0649b0b7bc0622c6e8d64f
119 Nc4edc830470644999563a40fe9e101d0 schema:isbn 978-3-540-61750-1
120 978-3-540-70673-1
121 schema:name Object Representation in Computer Vision II
122 rdf:type schema:Book
123 Nc81be21efc69455d928fcd4d0c4c205a rdf:first Ncf0aa06cf8eb47148b5dac316d91d544
124 rdf:rest rdf:nil
125 Ncb543eecbc9a4e5dba8e76001496f3c9 rdf:first sg:person.016034550437.98
126 rdf:rest N466baff53ce94df2af456121f5494d0f
127 Ncf0aa06cf8eb47148b5dac316d91d544 schema:familyName Hebert
128 schema:givenName Martial
129 rdf:type schema:Person
130 Ncfe915e6234e4e9eb46db78f62e2a2b0 rdf:first N3c2ca204210b4cb0a6abe63f32869f55
131 rdf:rest Ndb768226901a41e19c0e53f9164f849d
132 Ndb768226901a41e19c0e53f9164f849d rdf:first Na14725905fa34a0fbe74492676ec6a63
133 rdf:rest Nc81be21efc69455d928fcd4d0c4c205a
134 Nee197e6c0872418b89e4e11b5ce31f23 rdf:first sg:person.01364521761.84
135 rdf:rest Nb06ad22d6e7d4f20a8fb696130b154b2
136 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
137 schema:name Information and Computing Sciences
138 rdf:type schema:DefinedTerm
139 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
140 schema:name Artificial Intelligence and Image Processing
141 rdf:type schema:DefinedTerm
142 sg:person.010127057637.42 schema:affiliation grid-institutes:grid.47840.3f
143 schema:familyName Carson
144 schema:givenName Chad
145 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010127057637.42
146 rdf:type schema:Person
147 sg:person.013046646437.82 schema:affiliation grid-institutes:grid.214572.7
148 schema:familyName Fleck
149 schema:givenName Margaret M.
150 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013046646437.82
151 rdf:type schema:Person
152 sg:person.013255604017.26 schema:affiliation grid-institutes:grid.47840.3f
153 schema:familyName Bregler
154 schema:givenName Chris
155 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013255604017.26
156 rdf:type schema:Person
157 sg:person.01364521761.84 schema:affiliation grid-institutes:grid.47840.3f
158 schema:familyName Malik
159 schema:givenName Jitendra
160 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01364521761.84
161 rdf:type schema:Person
162 sg:person.016034550437.98 schema:affiliation grid-institutes:grid.47840.3f
163 schema:familyName Leung
164 schema:givenName Thomas
165 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016034550437.98
166 rdf:type schema:Person
167 sg:person.0632735744.68 schema:affiliation grid-institutes:grid.47840.3f
168 schema:familyName Belongie
169 schema:givenName Serge
170 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0632735744.68
171 rdf:type schema:Person
172 sg:person.0717704704.38 schema:affiliation grid-institutes:grid.47840.3f
173 schema:familyName Forsyth
174 schema:givenName David A.
175 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0717704704.38
176 rdf:type schema:Person
177 sg:person.0740775377.81 schema:affiliation grid-institutes:grid.20861.3d
178 schema:familyName Greenspan
179 schema:givenName Hayit
180 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0740775377.81
181 rdf:type schema:Person
182 grid-institutes:grid.20861.3d schema:alternateName Dept. of Electrical Engineering, Caltech, 91125, Pasadena, CA
183 schema:name Computer Science Division, University of California at Berkeley, 94720, Berkeley, CA
184 Dept. of Electrical Engineering, Caltech, 91125, Pasadena, CA
185 rdf:type schema:Organization
186 grid-institutes:grid.214572.7 schema:alternateName Dept. of Computer Science, University of Iowa, 52240, Iowa City, IA
187 schema:name Dept. of Computer Science, University of Iowa, 52240, Iowa City, IA
188 rdf:type schema:Organization
189 grid-institutes:grid.47840.3f schema:alternateName Computer Science Division, University of California at Berkeley, 94720, Berkeley, CA
190 schema:name Computer Science Division, University of California at Berkeley, 94720, Berkeley, CA
191 rdf:type schema:Organization
 




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


...