Integral and local affine invariant parameter and application to shape recognition

T. COHIGNAC, C. LOPEZ, J.-M. MOREL

Research output: Book Chapters | Papers in Conference ProceedingsConference paper (refereed)Referred Conference Paperpeer-review

32 Citations (Scopus)

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 pads. The characteristic point method, for instance, focuses on configurations of points with maximal curvature of the shape (in an euclidian invariant framework). Using the affine znvarzant scale space, we define affine znvariant 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.

Original languageEnglish
Title of host publicationProceedings of 12th IAPR International Conference on Pattern Recognition
PublisherIEEE
Pages164-168
Number of pages5
VolumeI
ISBN (Print)9780818662652
DOIs
Publication statusPublished - 1994
Externally publishedYes
Event12th IAPR International Conference on Pattern Recognition: Conference A: Computer Vision & Image Processing - Jerusalem, Israel
Duration: 9 Oct 199413 Oct 1994

Publication series

NameProceedings - International Conference on Pattern Recognition
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISSN (Print)1051-4651

Conference

Conference12th IAPR International Conference on Pattern Recognition: Conference A: Computer Vision & Image Processing
Country/TerritoryIsrael
CityJerusalem
Period9/10/9413/10/94

Bibliographical note

Publisher Copyright:
© 1994 Institute of Electrical and Electronics Engineers Inc.. All rights reserved.

Fingerprint

Dive into the research topics of 'Integral and local affine invariant parameter and application to shape recognition'. Together they form a unique fingerprint.

Cite this