Passer à la navigation principale Passer à la recherche Passer au contenu principal

Entropy-of-likelihood feature selection for image correspondence

  • McGill University

Résultats de recherche: Contribution à un journal › Article de conférence › Revue par des pairs

14 Citations (Scopus)

Résumé

Feature points for image correspondence are often selected according to subjective criteria (e.g. edge density, nostrils). In this paper, we present a general, non-subjective criterion for selecting informative feature points, based on the correspondence model itself. We describe the approach within the framework of the Bayesian Markov random field (MRF) model, where the degree of feature point information is encoded by the entropy of the likelihood term. We propose that feature selection according to minimum entropy-of-likelihood (EOL) is less likely to lead to correspondence ambiguity, thus improving the optimization process in terms of speed and quality of solution. Experimental results demonstrate the criterion's ability to select optimal features points in a wide variety of image contexts (e.g. objects, faces). Comparison with the automatic Kanade-Lucas- Tomasi feature selection criterion shows correspondence to be significantly faster with feature points selected according to minimum EOL in difficult correspondence problems.

Langue originaleAnglais
Pages (de - à)1041-1047
Nombre de pages7
RevueProceedings of the IEEE International Conference on Computer Vision
Volume2
Les DOIs
ÉtatPublié - 2003
Modification externeOui
EvénementNINTH IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION - Nice, France
Durée: 13 oct. 2003 → 16 oct. 2003

Classification disciplinaire ASJC Scopus

  • Logiciel
  • Vision par ordinateur et reconnaissance de formes

Empreinte digitale

Voici les principaux termes ou expressions associés à « Entropy-of-likelihood feature selection for image correspondence ». Ces libellés thématiques sont générés à partir du titre et du résumé de la publication. Ensemble, ils forment une empreinte digitale unique.

Citer cette ressource