View in EDS PDF Full Text

Invariant Object Recognition in the Visual System with Novel Views of 3D Objects.

Saved in:
Bibliographic Details
Title: Invariant Object Recognition in the Visual System with Novel Views of 3D Objects.
Authors: Stringer, Simon M.1, Rolls, Edmund T.1
Source: Neural Computation. Nov2002, Vol. 14 Issue 11, p2585-2596. 12p.
Subjects: Pattern perception, Biological neural networks, Paired associate learning
Abstract: To form view-invariant representations of objects, neurons in the inferior temporal cortex may associate together different views of an object, which tend to occur close together in time under natural viewing conditions. This can be achieved in neuronal network models of this process by using an associative learning rule with a short-term temporal memory trace. It is postulated that within a view, neurons learn representations that enable them to generalize within variations of that view. When three-dimensional (3D) objects are rotated within small angles (up to, e.g., 30 degrees), their surface features undergo geometric distortion due to the change of perspective. In this article, we show how trace learning could solve the problem of in-depth rotation-invariant object recognition by developing representations of the transforms that features undergo when they are on the surfaces of 3D objects. Moreover, we show that having learned how features on 3D objects transform geometrically as the object is rotated in depth, the network can correctly recognize novel 3D variations within a generic view of an object composed of a new combination of previously learned features. These results are demonstrated in simulations of a hierarchical network model (VisNet) of the visual system that show that it can develop representations useful for the recognition of 3D objects by forming perspective-invariant representations to allow generalization within a generic view. [ABSTRACT FROM AUTHOR]
Copyright of Neural Computation is the property of MIT Press and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Engineering Source
FullText Links:
  – Type: pdflink
Text:
  Availability: 0
Header DbId: egs
DbLabel: Engineering Source
An: 7675356
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Invariant Object Recognition in the Visual System with Novel Views of 3D Objects.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Stringer%2C+Simon+M%2E%22">Stringer, Simon M.</searchLink><relatesTo>1</relatesTo><br /><searchLink fieldCode="AR" term="%22Rolls%2C+Edmund+T%2E%22">Rolls, Edmund T.</searchLink><relatesTo>1</relatesTo>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22Neural+Computation%22">Neural Computation</searchLink>. Nov2002, Vol. 14 Issue 11, p2585-2596. 12p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Pattern+perception%22">Pattern perception</searchLink><br /><searchLink fieldCode="DE" term="%22Biological+neural+networks%22">Biological neural networks</searchLink><br /><searchLink fieldCode="DE" term="%22Paired+associate+learning%22">Paired associate learning</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: To form view-invariant representations of objects, neurons in the inferior temporal cortex may associate together different views of an object, which tend to occur close together in time under natural viewing conditions. This can be achieved in neuronal network models of this process by using an associative learning rule with a short-term temporal memory trace. It is postulated that within a view, neurons learn representations that enable them to generalize within variations of that view. When three-dimensional (3D) objects are rotated within small angles (up to, e.g., 30 degrees), their surface features undergo geometric distortion due to the change of perspective. In this article, we show how trace learning could solve the problem of in-depth rotation-invariant object recognition by developing representations of the transforms that features undergo when they are on the surfaces of 3D objects. Moreover, we show that having learned how features on 3D objects transform geometrically as the object is rotated in depth, the network can correctly recognize novel 3D variations within a generic view of an object composed of a new combination of previously learned features. These results are demonstrated in simulations of a hierarchical network model (VisNet) of the visual system that show that it can develop representations useful for the recognition of 3D objects by forming perspective-invariant representations to allow generalization within a generic view. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: <i>Copyright of Neural Computation is the property of MIT Press and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.)
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=7675356
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1162/089976602760407982
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 12
        StartPage: 2585
    Subjects:
      – SubjectFull: Pattern perception
        Type: general
      – SubjectFull: Biological neural networks
        Type: general
      – SubjectFull: Paired associate learning
        Type: general
    Titles:
      – TitleFull: Invariant Object Recognition in the Visual System with Novel Views of 3D Objects.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Stringer, Simon M.
      – PersonEntity:
          Name:
            NameFull: Rolls, Edmund T.
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 11
              Text: Nov2002
              Type: published
              Y: 2002
          Identifiers:
            – Type: issn-print
              Value: 08997667
          Numbering:
            – Type: volume
              Value: 14
            – Type: issue
              Value: 11
          Titles:
            – TitleFull: Neural Computation
              Type: main
ResultId 1