Share Email Print

Proceedings Paper

Scale space and affine invariant recognition of occluded shapes
Author(s): Thierry Cohignac; Jean-Michel Morel
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

The recently proved existence of affine invariant scale spaces for shapes opens new possibilities for shape recognition. While affine invariant shape recognition is easily performed when shapes are complete, partially occluded or incomplete shapes must be recognized by dividing them into intrinsic parts. The characteristic point method, for instance, focuses on configurations of points with maximal curvature of the shape (in a euclidian invariant framework). Using the affine invariant scale space, we define affine invariant characteristic points and affine invariant parts of a shape. We prove that compatibility scale relations make feasible the matching of scale spaces and show experiments with noisy affine distorted and occluded shapes.

Paper Details

Date Published: 1 September 1995
PDF: 9 pages
Proc. SPIE 2567, Investigative and Trial Image Processing, (1 September 1995); doi: 10.1117/12.218476
Show Author Affiliations
Thierry Cohignac, Univ. Paris-Dauphine (France)
Jean-Michel Morel, Univ. Paris-Dauphine (France)

Published in SPIE Proceedings Vol. 2567:
Investigative and Trial Image Processing
Leonid I. Rudin; Simon K. Bramble, Editor(s)

© SPIE. Terms of Use
Back to Top