A linear signal decomposition approach to affine invariant contour identification

  • Authors:
  • David Cyganski;Richard F. Vaz

  • Affiliations:
  • -;-

  • Venue:
  • Pattern Recognition
  • Year:
  • 1995

Quantified Score

Hi-index 0.02

Visualization

Abstract

Means for the identification of objects from contours despite affine transform induced distortions using a linear signal space decomposition are described. This technique also yields robust estimates of the 3-D rotations of a near planar object. The ability to determine object identity and orientation from a single model representation without iteration or combinatorial search proceeds from the use of affine invariant differential measures derived via Lie group theory. The technique is extremely robust owing to the error rejection properties of signal space projections. Results illustrating the resilience of the solutions in the presence of severe non-affine distortion and pixelization are given.