What Is the Set of Images of an Object Under All Possible Illumination Conditions? View Full Text


Ontology type: schema:ScholarlyArticle     


Article Info

DATE

1998-07

AUTHORS

Peter N. Belhumeur, David J. Kriegman

ABSTRACT

The appearance of an object depends on both the viewpoint from which it is observed and the light sources by which it is illuminated. If the appearance of two objects is never identical for any pose or lighting conditions, then–in theory–the objects can always be distinguished or recognized. The question arises: What is the set of images of an object under all lighting conditions and pose? In this paper, we consider only the set of images of an object under variable illumination, including multiple, extended light sources and shadows. We prove that the set of n-pixel images of a convex object with a Lambertian reflectance function, illuminated by an arbitrary number of point light sources at infinity, forms a convex polyhedral cone in IRn and that the dimension of this illumination cone equals the number of distinct surface normals. Furthermore, the illumination cone can be constructed from as few as three images. In addition, the set of n-pixel images of an object of any shape and with a more general reflectance function, seen under all possible illumination conditions, still forms a convex cone in IRn. Extensions of these results to color images are presented. These results immediately suggest certain approaches to object recognition. Throughout, we present results demonstrating the illumination cone representation. More... »

PAGES

245-260

Identifiers

URI

http://scigraph.springernature.com/pub.10.1023/a:1008005721484

DOI

http://dx.doi.org/10.1023/a:1008005721484

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1051637698


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": "Center for Comp. Vision and Control, Dept. of Electrical Engineering, Yale University, 06520, New Haven, CT", 
          "id": "http://www.grid.ac/institutes/grid.47100.32", 
          "name": [
            "Center for Comp. Vision and Control, Dept. of Electrical Engineering, Yale University, 06520, New Haven, CT"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Belhumeur", 
        "givenName": "Peter N.", 
        "id": "sg:person.0617670621.20", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0617670621.20"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Center for Comp. Vision and Control, Dept. of Electrical Engineering, Yale University, 06520, New Haven, CT", 
          "id": "http://www.grid.ac/institutes/grid.47100.32", 
          "name": [
            "Center for Comp. Vision and Control, Dept. of Electrical Engineering, Yale University, 06520, New Haven, CT"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Kriegman", 
        "givenName": "David J.", 
        "id": "sg:person.010713327741.54", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010713327741.54"
        ], 
        "type": "Person"
      }
    ], 
    "citation": [
      {
        "id": "sg:pub.10.1007/bf01679684", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1004320587", 
          "https://doi.org/10.1007/bf01679684"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/bfb0015522", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1010550842", 
          "https://doi.org/10.1007/bfb0015522"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/3-540-57956-7_33", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1047239077", 
          "https://doi.org/10.1007/3-540-57956-7_33"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/bf01421486", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1020275860", 
          "https://doi.org/10.1007/bf01421486"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/3-540-61123-1_125", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1040860226", 
          "https://doi.org/10.1007/3-540-61123-1_125"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/bf00128233", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1044578666", 
          "https://doi.org/10.1007/bf00128233"
        ], 
        "type": "CreativeWork"
      }
    ], 
    "datePublished": "1998-07", 
    "datePublishedReg": "1998-07-01", 
    "description": "The appearance of an object depends on both the viewpoint from which it is observed and the light sources by which it is illuminated. If the appearance of two objects is never identical for any pose or lighting conditions, then\u2013in theory\u2013the objects can always be distinguished or recognized. The question arises: What is the set of images of an object under all lighting conditions and pose? In this paper, we consider only the set of images of an object under variable illumination, including multiple, extended light sources and shadows. We prove that the set of n-pixel images of a convex object with a Lambertian reflectance function, illuminated by an arbitrary number of point light sources at infinity, forms a convex polyhedral cone in IRn and that the dimension of this illumination cone equals the number of distinct surface normals. Furthermore, the illumination cone can be constructed from as few as three images. In addition, the set of n-pixel images of an object of any shape and with a more general reflectance function, seen under all possible illumination conditions, still forms a convex cone in IRn. Extensions of these results to color images are presented. These results immediately suggest certain approaches to object recognition. Throughout, we present results demonstrating the illumination cone representation.", 
    "genre": "article", 
    "id": "sg:pub.10.1023/a:1008005721484", 
    "isAccessibleForFree": false, 
    "isPartOf": [
      {
        "id": "sg:journal.1032807", 
        "issn": [
          "0920-5691", 
          "1573-1405"
        ], 
        "name": "International Journal of Computer Vision", 
        "publisher": "Springer Nature", 
        "type": "Periodical"
      }, 
      {
        "issueNumber": "3", 
        "type": "PublicationIssue"
      }, 
      {
        "type": "PublicationVolume", 
        "volumeNumber": "28"
      }
    ], 
    "keywords": [
      "possible illumination conditions", 
      "illumination cone", 
      "set of images", 
      "cone representation", 
      "objects", 
      "lighting conditions", 
      "certain approaches", 
      "illumination conditions", 
      "variable illumination", 
      "recognition", 
      "convex objects", 
      "representation", 
      "theory", 
      "images", 
      "dimensions", 
      "questions", 
      "results", 
      "color images", 
      "set", 
      "reflectance function", 
      "normals", 
      "viewpoint", 
      "conditions", 
      "function", 
      "surface normals", 
      "appearance", 
      "approach", 
      "source", 
      "number", 
      "IRN", 
      "addition", 
      "paper", 
      "shadow", 
      "shape", 
      "illumination", 
      "extension", 
      "point light source", 
      "light source", 
      "cone", 
      "arbitrary number", 
      "extended light source", 
      "N-pixel image", 
      "infinity", 
      "convex cone", 
      "general reflectance functions", 
      "Lambertian reflectance functions", 
      "convex polyhedral cone", 
      "polyhedral cone"
    ], 
    "name": "What Is the Set of Images of an Object Under All Possible Illumination Conditions?", 
    "pagination": "245-260", 
    "productId": [
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1051637698"
        ]
      }, 
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1023/a:1008005721484"
        ]
      }
    ], 
    "sameAs": [
      "https://doi.org/10.1023/a:1008005721484", 
      "https://app.dimensions.ai/details/publication/pub.1051637698"
    ], 
    "sdDataset": "articles", 
    "sdDatePublished": "2022-10-01T06:30", 
    "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
    "sdPublisher": {
      "name": "Springer Nature - SN SciGraph project", 
      "type": "Organization"
    }, 
    "sdSource": "s3://com-springernature-scigraph/baseset/20221001/entities/gbq_results/article/article_292.jsonl", 
    "type": "ScholarlyArticle", 
    "url": "https://doi.org/10.1023/a:1008005721484"
  }
]
 

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.10.1023/a:1008005721484'

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

curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1023/a:1008005721484'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1023/a:1008005721484'

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

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1023/a:1008005721484'


 

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

136 TRIPLES      21 PREDICATES      79 URIs      65 LITERALS      6 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1023/a:1008005721484 schema:about anzsrc-for:08
2 anzsrc-for:0801
3 schema:author N203d440aaa5c4e1f82ea8d5a62e8a484
4 schema:citation sg:pub.10.1007/3-540-57956-7_33
5 sg:pub.10.1007/3-540-61123-1_125
6 sg:pub.10.1007/bf00128233
7 sg:pub.10.1007/bf01421486
8 sg:pub.10.1007/bf01679684
9 sg:pub.10.1007/bfb0015522
10 schema:datePublished 1998-07
11 schema:datePublishedReg 1998-07-01
12 schema:description The appearance of an object depends on both the viewpoint from which it is observed and the light sources by which it is illuminated. If the appearance of two objects is never identical for any pose or lighting conditions, then–in theory–the objects can always be distinguished or recognized. The question arises: What is the set of images of an object under all lighting conditions and pose? In this paper, we consider only the set of images of an object under variable illumination, including multiple, extended light sources and shadows. We prove that the set of n-pixel images of a convex object with a Lambertian reflectance function, illuminated by an arbitrary number of point light sources at infinity, forms a convex polyhedral cone in IRn and that the dimension of this illumination cone equals the number of distinct surface normals. Furthermore, the illumination cone can be constructed from as few as three images. In addition, the set of n-pixel images of an object of any shape and with a more general reflectance function, seen under all possible illumination conditions, still forms a convex cone in IRn. Extensions of these results to color images are presented. These results immediately suggest certain approaches to object recognition. Throughout, we present results demonstrating the illumination cone representation.
13 schema:genre article
14 schema:isAccessibleForFree false
15 schema:isPartOf N59c7cd102f3c4055a5e283d99e09221f
16 Nd93d8990eff449248c4fb831a6b73f94
17 sg:journal.1032807
18 schema:keywords IRN
19 Lambertian reflectance functions
20 N-pixel image
21 addition
22 appearance
23 approach
24 arbitrary number
25 certain approaches
26 color images
27 conditions
28 cone
29 cone representation
30 convex cone
31 convex objects
32 convex polyhedral cone
33 dimensions
34 extended light source
35 extension
36 function
37 general reflectance functions
38 illumination
39 illumination conditions
40 illumination cone
41 images
42 infinity
43 light source
44 lighting conditions
45 normals
46 number
47 objects
48 paper
49 point light source
50 polyhedral cone
51 possible illumination conditions
52 questions
53 recognition
54 reflectance function
55 representation
56 results
57 set
58 set of images
59 shadow
60 shape
61 source
62 surface normals
63 theory
64 variable illumination
65 viewpoint
66 schema:name What Is the Set of Images of an Object Under All Possible Illumination Conditions?
67 schema:pagination 245-260
68 schema:productId N22e5a735cd9446c4a86bde34cf7978a9
69 N37f2633622ed4d5790daf8f1c0b089c8
70 schema:sameAs https://app.dimensions.ai/details/publication/pub.1051637698
71 https://doi.org/10.1023/a:1008005721484
72 schema:sdDatePublished 2022-10-01T06:30
73 schema:sdLicense https://scigraph.springernature.com/explorer/license/
74 schema:sdPublisher N8be4748d18cb46f3901a27f61138e10c
75 schema:url https://doi.org/10.1023/a:1008005721484
76 sgo:license sg:explorer/license/
77 sgo:sdDataset articles
78 rdf:type schema:ScholarlyArticle
79 N1dfd49d33e02459ba938f9f5157ae9f9 rdf:first sg:person.010713327741.54
80 rdf:rest rdf:nil
81 N203d440aaa5c4e1f82ea8d5a62e8a484 rdf:first sg:person.0617670621.20
82 rdf:rest N1dfd49d33e02459ba938f9f5157ae9f9
83 N22e5a735cd9446c4a86bde34cf7978a9 schema:name dimensions_id
84 schema:value pub.1051637698
85 rdf:type schema:PropertyValue
86 N37f2633622ed4d5790daf8f1c0b089c8 schema:name doi
87 schema:value 10.1023/a:1008005721484
88 rdf:type schema:PropertyValue
89 N59c7cd102f3c4055a5e283d99e09221f schema:volumeNumber 28
90 rdf:type schema:PublicationVolume
91 N8be4748d18cb46f3901a27f61138e10c schema:name Springer Nature - SN SciGraph project
92 rdf:type schema:Organization
93 Nd93d8990eff449248c4fb831a6b73f94 schema:issueNumber 3
94 rdf:type schema:PublicationIssue
95 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
96 schema:name Information and Computing Sciences
97 rdf:type schema:DefinedTerm
98 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
99 schema:name Artificial Intelligence and Image Processing
100 rdf:type schema:DefinedTerm
101 sg:journal.1032807 schema:issn 0920-5691
102 1573-1405
103 schema:name International Journal of Computer Vision
104 schema:publisher Springer Nature
105 rdf:type schema:Periodical
106 sg:person.010713327741.54 schema:affiliation grid-institutes:grid.47100.32
107 schema:familyName Kriegman
108 schema:givenName David J.
109 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010713327741.54
110 rdf:type schema:Person
111 sg:person.0617670621.20 schema:affiliation grid-institutes:grid.47100.32
112 schema:familyName Belhumeur
113 schema:givenName Peter N.
114 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.0617670621.20
115 rdf:type schema:Person
116 sg:pub.10.1007/3-540-57956-7_33 schema:sameAs https://app.dimensions.ai/details/publication/pub.1047239077
117 https://doi.org/10.1007/3-540-57956-7_33
118 rdf:type schema:CreativeWork
119 sg:pub.10.1007/3-540-61123-1_125 schema:sameAs https://app.dimensions.ai/details/publication/pub.1040860226
120 https://doi.org/10.1007/3-540-61123-1_125
121 rdf:type schema:CreativeWork
122 sg:pub.10.1007/bf00128233 schema:sameAs https://app.dimensions.ai/details/publication/pub.1044578666
123 https://doi.org/10.1007/bf00128233
124 rdf:type schema:CreativeWork
125 sg:pub.10.1007/bf01421486 schema:sameAs https://app.dimensions.ai/details/publication/pub.1020275860
126 https://doi.org/10.1007/bf01421486
127 rdf:type schema:CreativeWork
128 sg:pub.10.1007/bf01679684 schema:sameAs https://app.dimensions.ai/details/publication/pub.1004320587
129 https://doi.org/10.1007/bf01679684
130 rdf:type schema:CreativeWork
131 sg:pub.10.1007/bfb0015522 schema:sameAs https://app.dimensions.ai/details/publication/pub.1010550842
132 https://doi.org/10.1007/bfb0015522
133 rdf:type schema:CreativeWork
134 grid-institutes:grid.47100.32 schema:alternateName Center for Comp. Vision and Control, Dept. of Electrical Engineering, Yale University, 06520, New Haven, CT
135 schema:name Center for Comp. Vision and Control, Dept. of Electrical Engineering, Yale University, 06520, New Haven, CT
136 rdf:type schema:Organization
 




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


...