Shape recognition based on an a contrario methodology

Research output: Book Chapters | Papers in Conference ProceedingsBook ChapterResearchpeer-review

Abstract

The Achilles’ heel of most shape recognition systems is the decision stage, whose goal is to clearly answer the question of whether two shapes look alike or not. In this chapter we propose a method to address this issue, that consists in pairing two shapes as soon as their proximity is unlikely to be observed “by chance.” This is achieved by bounding the number of false matches between a query shape and shapes from the database. The same statistical principle is used to extract relevant shape elements from images, yielding a complete procedure to decide whether or not two images share some common shapes.
Original languageEnglish
Title of host publicationStatistics and Analysis of Shapes
EditorsHamid KRIM, Anthony YEZZI
Place of PublicationBoston
PublisherBirkhauser Boston
Pages107-136
Number of pages30
ISBN (Electronic)9780817644819
ISBN (Print)9780817643768
DOIs
Publication statusPublished - 2006
Externally publishedYes

Publication series

NameModeling and Simulation in Science, Engineering and Technology
PublisherBirkhauser
ISSN (Print)2164-3679
ISSN (Electronic)2164-3725

Funding

This work was supported by the Office of Naval Research under grant N00014-97-1-0839, by the Centre National d’Études Spatiales, and by the Réseau National de Recherche en Télécommunications (projet ISII). Algorithms were implemented using the MegaWave2 free software.

Keywords

  • a contrario decision
  • background model
  • level lines
  • number of false alarms
  • shape elements
  • Shape recognition

Fingerprint

Dive into the research topics of 'Shape recognition based on an a contrario methodology'. Together they form a unique fingerprint.

Cite this