Representing and Recognizing the Visual Appearance of Materials using Three-dimensional Textons View Full Text


Ontology type: schema:ScholarlyArticle     


Article Info

DATE

2001-06

AUTHORS

Thomas Leung, Jitendra Malik

ABSTRACT

We study the recognition of surfaces made from different materials such as concrete, rug, marble, or leather on the basis of their textural appearance. Such natural textures arise from spatial variation of two surface attributes: (1) reflectance and (2) surface normal. In this paper, we provide a unified model to address both these aspects of natural texture. The main idea is to construct a vocabulary of prototype tiny surface patches with associated local geometric and photometric properties. We call these 3D textons. Examples might be ridges, grooves, spots or stripes or combinations thereof. Associated with each texton is an appearance vector, which characterizes the local irradiance distribution, represented as a set of linear Gaussian derivative filter outputs, under different lighting and viewing conditions.Given a large collection of images of different materials, a clustering approach is used to acquire a small (on the order of 100) 3D texton vocabulary. Given a few (1 to 4) images of any material, it can be characterized using these textons. We demonstrate the application of this representation for recognition of the material viewed under novel lighting and viewing conditions. We also illustrate how the 3D texton model can be used to predict the appearance of materials under novel conditions. More... »

PAGES

29-44

References to SciGraph publications

Identifiers

URI

http://scigraph.springernature.com/pub.10.1023/a:1011126920638

DOI

http://dx.doi.org/10.1023/a:1011126920638

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1046312359


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, 94720-1776, Berkeley, CA, USA", 
          "id": "http://www.grid.ac/institutes/grid.47840.3f", 
          "name": [
            "Computer Science Division, University of California at Berkeley, 94720-1776, Berkeley, CA, USA"
          ], 
          "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, 94720-1776, Berkeley, CA, USA", 
          "id": "http://www.grid.ac/institutes/grid.47840.3f", 
          "name": [
            "Computer Science Division, University of California at Berkeley, 94720-1776, Berkeley, CA, USA"
          ], 
          "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"
      }
    ], 
    "citation": [
      {
        "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.10.1023/a:1008005721484", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1051637698", 
          "https://doi.org/10.1023/a:1008005721484"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1023/a:1007975506780", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1029643449", 
          "https://doi.org/10.1023/a:1007975506780"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1023/a:1007925832420", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1005653889", 
          "https://doi.org/10.1023/a:1007925832420"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1038/290091a0", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1040887630", 
          "https://doi.org/10.1038/290091a0"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/bf00204594", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1017610398", 
          "https://doi.org/10.1007/bf00204594"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1023/a:1008061730969", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1042600859", 
          "https://doi.org/10.1023/a:1008061730969"
        ], 
        "type": "CreativeWork"
      }
    ], 
    "datePublished": "2001-06", 
    "datePublishedReg": "2001-06-01", 
    "description": "We study the recognition of surfaces made from different materials such as concrete, rug, marble, or leather on the basis of their textural appearance. Such natural textures arise from spatial variation of two surface attributes: (1) reflectance and (2) surface normal. In this paper, we provide a unified model to address both these aspects of natural texture. The main idea is to construct a vocabulary of prototype tiny surface patches with associated local geometric and photometric properties. We call these 3D textons. Examples might be ridges, grooves, spots or stripes or combinations thereof. Associated with each texton is an appearance vector, which characterizes the local irradiance distribution, represented as a set of linear Gaussian derivative filter outputs, under different lighting and viewing conditions.Given a large collection of images of different materials, a clustering approach is used to acquire a small (on the order of 100) 3D texton vocabulary. Given a few (1 to 4) images of any material, it can be characterized using these textons. We demonstrate the application of this representation for recognition of the material viewed under novel lighting and viewing conditions. We also illustrate how the 3D texton model can be used to predict the appearance of materials under novel conditions.", 
    "genre": "article", 
    "id": "sg:pub.10.1023/a:1011126920638", 
    "isAccessibleForFree": false, 
    "isPartOf": [
      {
        "id": "sg:journal.1032807", 
        "issn": [
          "0920-5691", 
          "1573-1405"
        ], 
        "name": "International Journal of Computer Vision", 
        "publisher": "Springer Nature", 
        "type": "Periodical"
      }, 
      {
        "issueNumber": "1", 
        "type": "PublicationIssue"
      }, 
      {
        "type": "PublicationVolume", 
        "volumeNumber": "43"
      }
    ], 
    "keywords": [
      "different materials", 
      "filter output", 
      "novel lighting", 
      "materials", 
      "irradiance distribution", 
      "recognition of surfaces", 
      "surface attributes", 
      "surface", 
      "appearance of materials", 
      "lighting", 
      "spatial variation", 
      "texture", 
      "surface patches", 
      "unified model", 
      "different lighting", 
      "conditions", 
      "main idea", 
      "reflectance", 
      "natural textures", 
      "properties", 
      "model", 
      "appearance vectors", 
      "applications", 
      "groove", 
      "visual appearance", 
      "images", 
      "leather", 
      "output", 
      "marble", 
      "stripes", 
      "distribution", 
      "variation", 
      "textural appearance", 
      "example", 
      "spots", 
      "combination", 
      "approach", 
      "novel conditions", 
      "photometric properties", 
      "ridge", 
      "appearance", 
      "vector", 
      "textons", 
      "patches", 
      "set", 
      "basis", 
      "aspects", 
      "attributes", 
      "representation", 
      "idea", 
      "recognition", 
      "rugs", 
      "collection", 
      "large collection", 
      "vocabulary", 
      "paper"
    ], 
    "name": "Representing and Recognizing the Visual Appearance of Materials using Three-dimensional Textons", 
    "pagination": "29-44", 
    "productId": [
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1046312359"
        ]
      }, 
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1023/a:1011126920638"
        ]
      }
    ], 
    "sameAs": [
      "https://doi.org/10.1023/a:1011126920638", 
      "https://app.dimensions.ai/details/publication/pub.1046312359"
    ], 
    "sdDataset": "articles", 
    "sdDatePublished": "2022-08-04T16:52", 
    "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
    "sdPublisher": {
      "name": "Springer Nature - SN SciGraph project", 
      "type": "Organization"
    }, 
    "sdSource": "s3://com-springernature-scigraph/baseset/20220804/entities/gbq_results/article/article_314.jsonl", 
    "type": "ScholarlyArticle", 
    "url": "https://doi.org/10.1023/a:1011126920638"
  }
]
 

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:1011126920638'

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:1011126920638'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1023/a:1011126920638'

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

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1023/a:1011126920638'


 

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

148 TRIPLES      21 PREDICATES      88 URIs      73 LITERALS      6 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1023/a:1011126920638 schema:about anzsrc-for:08
2 anzsrc-for:0801
3 schema:author N29ad34e358f6496e8c25086535ec051a
4 schema:citation sg:pub.10.1007/bf00204594
5 sg:pub.10.1007/bf01421486
6 sg:pub.10.1023/a:1007925832420
7 sg:pub.10.1023/a:1007975506780
8 sg:pub.10.1023/a:1008005721484
9 sg:pub.10.1023/a:1008061730969
10 sg:pub.10.1038/290091a0
11 schema:datePublished 2001-06
12 schema:datePublishedReg 2001-06-01
13 schema:description We study the recognition of surfaces made from different materials such as concrete, rug, marble, or leather on the basis of their textural appearance. Such natural textures arise from spatial variation of two surface attributes: (1) reflectance and (2) surface normal. In this paper, we provide a unified model to address both these aspects of natural texture. The main idea is to construct a vocabulary of prototype tiny surface patches with associated local geometric and photometric properties. We call these 3D textons. Examples might be ridges, grooves, spots or stripes or combinations thereof. Associated with each texton is an appearance vector, which characterizes the local irradiance distribution, represented as a set of linear Gaussian derivative filter outputs, under different lighting and viewing conditions.Given a large collection of images of different materials, a clustering approach is used to acquire a small (on the order of 100) 3D texton vocabulary. Given a few (1 to 4) images of any material, it can be characterized using these textons. We demonstrate the application of this representation for recognition of the material viewed under novel lighting and viewing conditions. We also illustrate how the 3D texton model can be used to predict the appearance of materials under novel conditions.
14 schema:genre article
15 schema:isAccessibleForFree false
16 schema:isPartOf N7c3f64995ea741eea90f6d90b7e49e1e
17 Na92aa84b3f764c5bb9d1a2c1bf62963b
18 sg:journal.1032807
19 schema:keywords appearance
20 appearance of materials
21 appearance vectors
22 applications
23 approach
24 aspects
25 attributes
26 basis
27 collection
28 combination
29 conditions
30 different lighting
31 different materials
32 distribution
33 example
34 filter output
35 groove
36 idea
37 images
38 irradiance distribution
39 large collection
40 leather
41 lighting
42 main idea
43 marble
44 materials
45 model
46 natural textures
47 novel conditions
48 novel lighting
49 output
50 paper
51 patches
52 photometric properties
53 properties
54 recognition
55 recognition of surfaces
56 reflectance
57 representation
58 ridge
59 rugs
60 set
61 spatial variation
62 spots
63 stripes
64 surface
65 surface attributes
66 surface patches
67 textons
68 textural appearance
69 texture
70 unified model
71 variation
72 vector
73 visual appearance
74 vocabulary
75 schema:name Representing and Recognizing the Visual Appearance of Materials using Three-dimensional Textons
76 schema:pagination 29-44
77 schema:productId N516fc4d096594a0480a0dc3c07a73f96
78 N956eace9dcee4896a0217d17908c4527
79 schema:sameAs https://app.dimensions.ai/details/publication/pub.1046312359
80 https://doi.org/10.1023/a:1011126920638
81 schema:sdDatePublished 2022-08-04T16:52
82 schema:sdLicense https://scigraph.springernature.com/explorer/license/
83 schema:sdPublisher N3a1b5061f5e74a028b5f3d677b3e7176
84 schema:url https://doi.org/10.1023/a:1011126920638
85 sgo:license sg:explorer/license/
86 sgo:sdDataset articles
87 rdf:type schema:ScholarlyArticle
88 N29ad34e358f6496e8c25086535ec051a rdf:first sg:person.016034550437.98
89 rdf:rest N568fc07d74804b3e9e4f8d8bae30d777
90 N3a1b5061f5e74a028b5f3d677b3e7176 schema:name Springer Nature - SN SciGraph project
91 rdf:type schema:Organization
92 N516fc4d096594a0480a0dc3c07a73f96 schema:name dimensions_id
93 schema:value pub.1046312359
94 rdf:type schema:PropertyValue
95 N568fc07d74804b3e9e4f8d8bae30d777 rdf:first sg:person.01364521761.84
96 rdf:rest rdf:nil
97 N7c3f64995ea741eea90f6d90b7e49e1e schema:volumeNumber 43
98 rdf:type schema:PublicationVolume
99 N956eace9dcee4896a0217d17908c4527 schema:name doi
100 schema:value 10.1023/a:1011126920638
101 rdf:type schema:PropertyValue
102 Na92aa84b3f764c5bb9d1a2c1bf62963b schema:issueNumber 1
103 rdf:type schema:PublicationIssue
104 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
105 schema:name Information and Computing Sciences
106 rdf:type schema:DefinedTerm
107 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
108 schema:name Artificial Intelligence and Image Processing
109 rdf:type schema:DefinedTerm
110 sg:journal.1032807 schema:issn 0920-5691
111 1573-1405
112 schema:name International Journal of Computer Vision
113 schema:publisher Springer Nature
114 rdf:type schema:Periodical
115 sg:person.01364521761.84 schema:affiliation grid-institutes:grid.47840.3f
116 schema:familyName Malik
117 schema:givenName Jitendra
118 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01364521761.84
119 rdf:type schema:Person
120 sg:person.016034550437.98 schema:affiliation grid-institutes:grid.47840.3f
121 schema:familyName Leung
122 schema:givenName Thomas
123 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016034550437.98
124 rdf:type schema:Person
125 sg:pub.10.1007/bf00204594 schema:sameAs https://app.dimensions.ai/details/publication/pub.1017610398
126 https://doi.org/10.1007/bf00204594
127 rdf:type schema:CreativeWork
128 sg:pub.10.1007/bf01421486 schema:sameAs https://app.dimensions.ai/details/publication/pub.1020275860
129 https://doi.org/10.1007/bf01421486
130 rdf:type schema:CreativeWork
131 sg:pub.10.1023/a:1007925832420 schema:sameAs https://app.dimensions.ai/details/publication/pub.1005653889
132 https://doi.org/10.1023/a:1007925832420
133 rdf:type schema:CreativeWork
134 sg:pub.10.1023/a:1007975506780 schema:sameAs https://app.dimensions.ai/details/publication/pub.1029643449
135 https://doi.org/10.1023/a:1007975506780
136 rdf:type schema:CreativeWork
137 sg:pub.10.1023/a:1008005721484 schema:sameAs https://app.dimensions.ai/details/publication/pub.1051637698
138 https://doi.org/10.1023/a:1008005721484
139 rdf:type schema:CreativeWork
140 sg:pub.10.1023/a:1008061730969 schema:sameAs https://app.dimensions.ai/details/publication/pub.1042600859
141 https://doi.org/10.1023/a:1008061730969
142 rdf:type schema:CreativeWork
143 sg:pub.10.1038/290091a0 schema:sameAs https://app.dimensions.ai/details/publication/pub.1040887630
144 https://doi.org/10.1038/290091a0
145 rdf:type schema:CreativeWork
146 grid-institutes:grid.47840.3f schema:alternateName Computer Science Division, University of California at Berkeley, 94720-1776, Berkeley, CA, USA
147 schema:name Computer Science Division, University of California at Berkeley, 94720-1776, Berkeley, CA, USA
148 rdf:type schema:Organization
 




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


...