Model based object recognition — the role of affine invariants

https://doi.org/10.1016/0954-1810(95)00032-1Get rights and content

Abstract

This paper proposes an efficient method to recognize rigid fiat objects from its intensity images which are assumed to be arbitrarily positioned in space. The task of the recognition method is to find instances of known object models in affine images. Affine invariant shape descriptors of rigid flat objects are generated which are invariant to change in the point of view. In the proposed paradigm, the objects are described by sets of local and global features. Since we are also concerned with the recognition of partially occluded objects, the local features are given importance for obtaining descriptions of objects. The global features are useful for finding the exact match and are used for verification. The local features can be points, line segments, curve segments, etc. We restrict ourselves to points, which are referred to as interest points. The point set of the various model objects are matched simultaneously against the point set of the composite overlapping scene using a small number of corresponding points. Seven discrete moments are used here as global features which are also invariant under the affine transformation. Experiments show good performance and together with inherent parallelism of the recognition method makes the method a promising one.

References (28)

  • W.E.L. Grimson

    The combinatorics of object recognition in cluttered environments using constrained search

    Artificial Intelligence

    (1990)
  • F. Bookstein

    Fitting conic sections to scattered data

    CVGIP-9

    (1979)
  • R.T. Chin et al.

    Model based object recognition in robot vision

    ACM Computing Surveys

    (1986)
  • D.A. Forsyth et al.

    Projectively invariants representation using implicit algebraic curves

  • Y. Lamdan et al.

    Object recognition by affine invariant matching

  • P.C. Wayner

    Efficiently using invariant theory for model based matching

  • F. Arman et al.

    Model based object recognition in dense range images

    ACM Computing Surveys

    (1993)
  • N. Ayache et al.

    HYPER: A new approach for the recognition and positioning of two dimensional objects

    IEEE PAMI

    (1986)
  • R.C. Bolles et al.

    Recognizing and locating partially visible objects

    Int. J. Robot. Res.

    (1982)
  • R.C. Bolles et al.

    3DPO: A three dimensional part orientation system

    Int. J. Robot. Res.

    (1986)
  • W.E.L. Grimson et al.

    Model based recognition and localization from sparse range or tactile data

    Int. J. Robot. Res.

    (1984)
  • W.E.L. Grimson et al.

    Localizing overlapping parts by searching the interpretation tree

    IEEE PAMI-9

    (1987)
  • J.L. Turney et al.

    Recognizing partially occluded parts

    IEEE PAMI-7

    (1985)
  • A. Kalvin et al.

    Two dimensional model based boundary matching using footprints

    Int. J. Robot. Res.

    (1986)
  • Cited by (6)

    Present address: Department of Computer Science and Engineering, HT Delhi, New Delhi 110016, India.

    View full text