On Photometric Issues in 3D Visual Recognition from a Single 2D Image View Full Text


Ontology type: schema:ScholarlyArticle     


Article Info

DATE

1997-01

AUTHORS

Amnon Shashua

ABSTRACT

We describe the problem of recognition under changing illumination conditions and changing viewing positions from a computational and human vision perspective. On the computational side we focus on the mathematical problems of creating an equivalence class for images of the same 3D object undergoing certain groups of transformations—mostly those due to changing illumination, and briefly discuss those due to changing viewing positions. The computational treatment culminates in proposing a simple scheme for recognizing, via alignment, an image of a familiar object taken from a novel viewing position and a novel illumination condition. On the human vision aspect, the paper is motivated by empirical evidence inspired by Mooney images of faces that suggest a relatively high level of visual processing is involved in compensating for photometric sources of variability, and furthermore, that certain limitations on the admissible representations of image information may exist. The psychophysical observations and the computational results that follow agree in several important respects, such as the same (apparent) limitations on image representations. More... »

PAGES

99-122

References to SciGraph publications

  • 1994. The quadric reference surface: Applications in registering views of complex 3D objects in COMPUTER VISION — ECCV '94
  • 1989-04. On the kinetic depth effect in BIOLOGICAL CYBERNETICS
  • Identifiers

    URI

    http://scigraph.springernature.com/pub.10.1023/a:1007975506780

    DOI

    http://dx.doi.org/10.1023/a:1007975506780

    DIMENSIONS

    https://app.dimensions.ai/details/publication/pub.1029643449


    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": [
          {
            "familyName": "Shashua", 
            "givenName": "Amnon", 
            "id": "sg:person.011111040313.12", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.011111040313.12"
            ], 
            "type": "Person"
          }
        ], 
        "citation": [
          {
            "id": "sg:pub.10.1007/bf00204700", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1041438957", 
              "https://doi.org/10.1007/bf00204700"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/bfb0028372", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1052672229", 
              "https://doi.org/10.1007/bfb0028372"
            ], 
            "type": "CreativeWork"
          }
        ], 
        "datePublished": "1997-01", 
        "datePublishedReg": "1997-01-01", 
        "description": "We describe the problem of recognition under changing illumination conditions and changing viewing positions from a computational and human vision perspective. On the computational side we focus on the mathematical problems of creating an equivalence class for images of the same 3D object undergoing certain groups of transformations\u2014mostly those due to changing illumination, and briefly discuss those due to changing viewing positions. The computational treatment culminates in proposing a simple scheme for recognizing, via alignment, an image of a familiar object taken from a novel viewing position and a novel illumination condition. On the human vision aspect, the paper is motivated by empirical evidence inspired by Mooney images of faces that suggest a relatively high level of visual processing is involved in compensating for photometric sources of variability, and furthermore, that certain limitations on the admissible representations of image information may exist. The psychophysical observations and the computational results that follow agree in several important respects, such as the same (apparent) limitations on image representations.", 
        "genre": "article", 
        "id": "sg:pub.10.1023/a:1007975506780", 
        "isAccessibleForFree": false, 
        "isPartOf": [
          {
            "id": "sg:journal.1032807", 
            "issn": [
              "0920-5691", 
              "1573-1405"
            ], 
            "name": "International Journal of Computer Vision", 
            "publisher": "Springer Nature", 
            "type": "Periodical"
          }, 
          {
            "issueNumber": "1-2", 
            "type": "PublicationIssue"
          }, 
          {
            "type": "PublicationVolume", 
            "volumeNumber": "21"
          }
        ], 
        "keywords": [
          "single 2D image", 
          "same 3D object", 
          "novel illumination conditions", 
          "illumination conditions", 
          "Mooney images", 
          "familiar objects", 
          "visual processing", 
          "problem of recognition", 
          "visual recognition", 
          "vision aspects", 
          "vision perspective", 
          "image representation", 
          "image information", 
          "psychophysical observations", 
          "photometric sources", 
          "images", 
          "computational results", 
          "computational side", 
          "empirical evidence", 
          "objects", 
          "recognition", 
          "computational treatment", 
          "high levels", 
          "representation", 
          "mathematical problem", 
          "certain limitations", 
          "simple scheme", 
          "equivalence classes", 
          "same limitations", 
          "processing", 
          "face", 
          "scheme", 
          "important respects", 
          "information", 
          "limitations", 
          "perspective", 
          "certain groups", 
          "aspects", 
          "issues", 
          "alignment", 
          "evidence", 
          "problem", 
          "briefly", 
          "position", 
          "illumination", 
          "group", 
          "class", 
          "variability", 
          "conditions", 
          "levels", 
          "results", 
          "transformation", 
          "respect", 
          "source", 
          "treatment", 
          "paper", 
          "side", 
          "observations", 
          "admissible representations"
        ], 
        "name": "On Photometric Issues in 3D Visual Recognition from a Single 2D Image", 
        "pagination": "99-122", 
        "productId": [
          {
            "name": "dimensions_id", 
            "type": "PropertyValue", 
            "value": [
              "pub.1029643449"
            ]
          }, 
          {
            "name": "doi", 
            "type": "PropertyValue", 
            "value": [
              "10.1023/a:1007975506780"
            ]
          }
        ], 
        "sameAs": [
          "https://doi.org/10.1023/a:1007975506780", 
          "https://app.dimensions.ai/details/publication/pub.1029643449"
        ], 
        "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_274.jsonl", 
        "type": "ScholarlyArticle", 
        "url": "https://doi.org/10.1023/a:1007975506780"
      }
    ]
     

    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:1007975506780'

    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:1007975506780'

    Turtle is a human-readable linked data format.

    curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1023/a:1007975506780'

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

    curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1023/a:1007975506780'


     

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

    120 TRIPLES      21 PREDICATES      86 URIs      76 LITERALS      6 BLANK NODES

    Subject Predicate Object
    1 sg:pub.10.1023/a:1007975506780 schema:about anzsrc-for:08
    2 anzsrc-for:0801
    3 schema:author N9cc2f94e558a435c8a8632179d005baf
    4 schema:citation sg:pub.10.1007/bf00204700
    5 sg:pub.10.1007/bfb0028372
    6 schema:datePublished 1997-01
    7 schema:datePublishedReg 1997-01-01
    8 schema:description We describe the problem of recognition under changing illumination conditions and changing viewing positions from a computational and human vision perspective. On the computational side we focus on the mathematical problems of creating an equivalence class for images of the same 3D object undergoing certain groups of transformations—mostly those due to changing illumination, and briefly discuss those due to changing viewing positions. The computational treatment culminates in proposing a simple scheme for recognizing, via alignment, an image of a familiar object taken from a novel viewing position and a novel illumination condition. On the human vision aspect, the paper is motivated by empirical evidence inspired by Mooney images of faces that suggest a relatively high level of visual processing is involved in compensating for photometric sources of variability, and furthermore, that certain limitations on the admissible representations of image information may exist. The psychophysical observations and the computational results that follow agree in several important respects, such as the same (apparent) limitations on image representations.
    9 schema:genre article
    10 schema:isAccessibleForFree false
    11 schema:isPartOf N50c71eefe1ff4c5890a033f6d7781da8
    12 Nd3fca1ead88e47e9ae69eb6c70435750
    13 sg:journal.1032807
    14 schema:keywords Mooney images
    15 admissible representations
    16 alignment
    17 aspects
    18 briefly
    19 certain groups
    20 certain limitations
    21 class
    22 computational results
    23 computational side
    24 computational treatment
    25 conditions
    26 empirical evidence
    27 equivalence classes
    28 evidence
    29 face
    30 familiar objects
    31 group
    32 high levels
    33 illumination
    34 illumination conditions
    35 image information
    36 image representation
    37 images
    38 important respects
    39 information
    40 issues
    41 levels
    42 limitations
    43 mathematical problem
    44 novel illumination conditions
    45 objects
    46 observations
    47 paper
    48 perspective
    49 photometric sources
    50 position
    51 problem
    52 problem of recognition
    53 processing
    54 psychophysical observations
    55 recognition
    56 representation
    57 respect
    58 results
    59 same 3D object
    60 same limitations
    61 scheme
    62 side
    63 simple scheme
    64 single 2D image
    65 source
    66 transformation
    67 treatment
    68 variability
    69 vision aspects
    70 vision perspective
    71 visual processing
    72 visual recognition
    73 schema:name On Photometric Issues in 3D Visual Recognition from a Single 2D Image
    74 schema:pagination 99-122
    75 schema:productId N059e83e5894a41afba9537b2c70f07df
    76 N92714b76ab804f988a2fc4d1ab20ba98
    77 schema:sameAs https://app.dimensions.ai/details/publication/pub.1029643449
    78 https://doi.org/10.1023/a:1007975506780
    79 schema:sdDatePublished 2022-10-01T06:30
    80 schema:sdLicense https://scigraph.springernature.com/explorer/license/
    81 schema:sdPublisher Nfe086b3039cb4e449a8a38d5a8e54473
    82 schema:url https://doi.org/10.1023/a:1007975506780
    83 sgo:license sg:explorer/license/
    84 sgo:sdDataset articles
    85 rdf:type schema:ScholarlyArticle
    86 N059e83e5894a41afba9537b2c70f07df schema:name doi
    87 schema:value 10.1023/a:1007975506780
    88 rdf:type schema:PropertyValue
    89 N50c71eefe1ff4c5890a033f6d7781da8 schema:volumeNumber 21
    90 rdf:type schema:PublicationVolume
    91 N92714b76ab804f988a2fc4d1ab20ba98 schema:name dimensions_id
    92 schema:value pub.1029643449
    93 rdf:type schema:PropertyValue
    94 N9cc2f94e558a435c8a8632179d005baf rdf:first sg:person.011111040313.12
    95 rdf:rest rdf:nil
    96 Nd3fca1ead88e47e9ae69eb6c70435750 schema:issueNumber 1-2
    97 rdf:type schema:PublicationIssue
    98 Nfe086b3039cb4e449a8a38d5a8e54473 schema:name Springer Nature - SN SciGraph project
    99 rdf:type schema:Organization
    100 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
    101 schema:name Information and Computing Sciences
    102 rdf:type schema:DefinedTerm
    103 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
    104 schema:name Artificial Intelligence and Image Processing
    105 rdf:type schema:DefinedTerm
    106 sg:journal.1032807 schema:issn 0920-5691
    107 1573-1405
    108 schema:name International Journal of Computer Vision
    109 schema:publisher Springer Nature
    110 rdf:type schema:Periodical
    111 sg:person.011111040313.12 schema:familyName Shashua
    112 schema:givenName Amnon
    113 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.011111040313.12
    114 rdf:type schema:Person
    115 sg:pub.10.1007/bf00204700 schema:sameAs https://app.dimensions.ai/details/publication/pub.1041438957
    116 https://doi.org/10.1007/bf00204700
    117 rdf:type schema:CreativeWork
    118 sg:pub.10.1007/bfb0028372 schema:sameAs https://app.dimensions.ai/details/publication/pub.1052672229
    119 https://doi.org/10.1007/bfb0028372
    120 rdf:type schema:CreativeWork
     




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


    ...