Ontology type: schema:ScholarlyArticle
1990-01
AUTHORS ABSTRACTTHE visual recognition of three-dimensional (3-D) objects on the basis of their shape poses at least two difficult problems. First, there is the problem of variable illumination, which can be addressed by working with relatively stable features such as intensity edges rather than the raw intensity images1,2. Second, there is the problem of the initially unknown pose of the object relative to the viewer. In one approach to this problem, a hypothesis is first made about the viewpoint, then the appearance of a model object from such a viewpoint is computed and compared with the actual image3–7. Such recognition schemes generally employ 3-D models of objects, but the automatic learning of 3-D models is itself a difficult problem8,9. To address this problem in computational vision, we have developed a scheme, based on the theory of approximation of multivariate functions, that learns from a small set of perspective views a function mapping any viewpoint to a standard view. A network equivalent to this scheme will thus 'recognize' the object on which it was trained from any viewpoint. More... »
PAGES263-266
http://scigraph.springernature.com/pub.10.1038/343263a0
DOIhttp://dx.doi.org/10.1038/343263a0
DIMENSIONShttps://app.dimensions.ai/details/publication/pub.1000677865
PUBMEDhttps://www.ncbi.nlm.nih.gov/pubmed/2300170
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/2008/17",
"inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/",
"name": "Psychology and Cognitive 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"
},
{
"id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/1701",
"inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/",
"name": "Psychology",
"type": "DefinedTerm"
},
{
"inDefinedTermSet": "https://www.nlm.nih.gov/mesh/",
"name": "Artificial Intelligence",
"type": "DefinedTerm"
},
{
"inDefinedTermSet": "https://www.nlm.nih.gov/mesh/",
"name": "Humans",
"type": "DefinedTerm"
},
{
"inDefinedTermSet": "https://www.nlm.nih.gov/mesh/",
"name": "Learning",
"type": "DefinedTerm"
},
{
"inDefinedTermSet": "https://www.nlm.nih.gov/mesh/",
"name": "Models, Psychological",
"type": "DefinedTerm"
},
{
"inDefinedTermSet": "https://www.nlm.nih.gov/mesh/",
"name": "Space Perception",
"type": "DefinedTerm"
}
],
"author": [
{
"affiliation": {
"alternateName": "Artificial Intelligence Laboratory, Center for Biological Information Processing, Massachusetts Institute of Technology, 02139, Cambridge, Massachusetts, USA",
"id": "http://www.grid.ac/institutes/grid.116068.8",
"name": [
"Artificial Intelligence Laboratory, Center for Biological Information Processing, Massachusetts Institute of Technology, 02139, Cambridge, Massachusetts, USA"
],
"type": "Organization"
},
"familyName": "Poggio",
"givenName": "T.",
"id": "sg:person.01143125037.55",
"sameAs": [
"https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01143125037.55"
],
"type": "Person"
},
{
"affiliation": {
"alternateName": "Artificial Intelligence Laboratory, Center for Biological Information Processing, Massachusetts Institute of Technology, 02139, Cambridge, Massachusetts, USA",
"id": "http://www.grid.ac/institutes/grid.116068.8",
"name": [
"Artificial Intelligence Laboratory, Center for Biological Information Processing, Massachusetts Institute of Technology, 02139, Cambridge, Massachusetts, USA"
],
"type": "Organization"
},
"familyName": "Edelman",
"givenName": "S.",
"id": "sg:person.01246441464.22",
"sameAs": [
"https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01246441464.22"
],
"type": "Person"
}
],
"citation": [
{
"id": "sg:pub.10.1038/323533a0",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1018367015",
"https://doi.org/10.1038/323533a0"
],
"type": "CreativeWork"
},
{
"id": "sg:pub.10.1007/bf00239352",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1004161796",
"https://doi.org/10.1007/bf00239352"
],
"type": "CreativeWork"
},
{
"id": "sg:pub.10.1007/bf00337644",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1024974725",
"https://doi.org/10.1007/bf00337644"
],
"type": "CreativeWork"
},
{
"id": "sg:pub.10.1038/293133a0",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1039346861",
"https://doi.org/10.1038/293133a0"
],
"type": "CreativeWork"
},
{
"id": "sg:pub.10.1038/317314a0",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1016903244",
"https://doi.org/10.1038/317314a0"
],
"type": "CreativeWork"
}
],
"datePublished": "1990-01",
"datePublishedReg": "1990-01-01",
"description": "Abstract THE visual recognition of three-dimensional (3-D) objects on the basis of their shape poses at least two difficult problems. First, there is the problem of variable illumination, which can be addressed by working with relatively stable features such as intensity edges rather than the raw intensity images1,2. Second, there is the problem of the initially unknown pose of the object relative to the viewer. In one approach to this problem, a hypothesis is first made about the viewpoint, then the appearance of a model object from such a viewpoint is computed and compared with the actual image3\u20137. Such recognition schemes generally employ 3-D models of objects, but the automatic learning of 3-D models is itself a difficult problem8,9. To address this problem in computational vision, we have developed a scheme, based on the theory of approximation of multivariate functions, that learns from a small set of perspective views a function mapping any viewpoint to a standard view. A network equivalent to this scheme will thus 'recognize' the object on which it was trained from any viewpoint.",
"genre": "article",
"id": "sg:pub.10.1038/343263a0",
"isAccessibleForFree": false,
"isPartOf": [
{
"id": "sg:journal.1018957",
"issn": [
"0028-0836",
"1476-4687"
],
"name": "Nature",
"publisher": "Springer Nature",
"type": "Periodical"
},
{
"issueNumber": "6255",
"type": "PublicationIssue"
},
{
"type": "PublicationVolume",
"volumeNumber": "343"
}
],
"keywords": [
"three-dimensional objects",
"automatic learning",
"computational vision",
"unknown pose",
"recognition scheme",
"variable illumination",
"intensity edges",
"visual recognition",
"perspective view",
"small set",
"model objects",
"difficult problem",
"pose",
"theory of approximation",
"objects",
"network",
"stable features",
"raw intensities",
"scheme",
"multivariate functions",
"standard view",
"viewpoint",
"learning",
"vision",
"viewers",
"recognition",
"set",
"problem",
"model",
"view",
"features",
"approximation",
"edge",
"hypothesis",
"theory",
"illumination",
"function",
"approach",
"basis",
"appearance",
"intensity"
],
"name": "A network that learns to recognize three-dimensional objects",
"pagination": "263-266",
"productId": [
{
"name": "dimensions_id",
"type": "PropertyValue",
"value": [
"pub.1000677865"
]
},
{
"name": "doi",
"type": "PropertyValue",
"value": [
"10.1038/343263a0"
]
},
{
"name": "pubmed_id",
"type": "PropertyValue",
"value": [
"2300170"
]
}
],
"sameAs": [
"https://doi.org/10.1038/343263a0",
"https://app.dimensions.ai/details/publication/pub.1000677865"
],
"sdDataset": "articles",
"sdDatePublished": "2022-08-04T16:51",
"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_223.jsonl",
"type": "ScholarlyArticle",
"url": "https://doi.org/10.1038/343263a0"
}
]
Download the RDF metadata as: json-ld nt turtle xml License info
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.10.1038/343263a0'
N-Triples is a line-based linked data format ideal for batch operations.
curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1038/343263a0'
Turtle is a human-readable linked data format.
curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1038/343263a0'
RDF/XML is a standard XML format for linked data.
curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1038/343263a0'
This table displays all metadata directly associated to this object as RDF triples.
157 TRIPLES
21 PREDICATES
79 URIs
64 LITERALS
12 BLANK NODES