Quasi-Invariant Parameterisations and Matching of Curves in Images

  • Authors:
  • Jun Sato;Roberto Cipolla

  • Affiliations:
  • Department of Engineering, University of Cambridge, Cambridge CB2 1PZ, UK. E-mail: js2@eng.cam.ac.uk;Department of Engineering, University of Cambridge, Cambridge CB2 1PZ, UK. E-mail: cipolla@eng.cam.ac.uk

  • Venue:
  • International Journal of Computer Vision
  • Year:
  • 1998

Quantified Score

Hi-index 0.00

Visualization

Abstract

In this paper, we investigate quasi-invariance on a smoothmanifold, and show that there exist quasi-invariantparameterisations which are not exactly invariant butapproximately invariant under group transformationsand do not require high order derivatives.The affine quasi-invariant parameterisation isinvestigated in more detail and exploited for defining general affinesemi-local invariants from second order derivatives only.The new invariants are implemented and used for matching curve segmentsunder general affine motions and extracting symmetry axes ofobjects with 3D bilateral symmetry.