GESTALT-INSPIRED FEATURES EXTRACTION FOR OBJECT CATEGORY RECOGNITION - Université de Bourgogne Accéder directement au contenu
Communication Dans Un Congrès Année : 2013

GESTALT-INSPIRED FEATURES EXTRACTION FOR OBJECT CATEGORY RECOGNITION

Résumé

We propose a methodology inspired by Gestalt laws to ex- tract and combine features and we test it on the object cat- egory recognition problem. Gestalt is a psycho-visual the- ory of Perceptual Organization that aims to explain how vi- sual information is organized by our brain. We interpreted its laws of homogeneity and continuation in link with shape and color to devise new features beyond the classical proxim- ity and similarity laws. The shape of the object is analyzed based on its skeleton (good continuation) and as a measure of homogeneity, we propose self-similarity enclosed within shape computed at super-pixel level. Furthermore, we pro- pose a framework to combine these features in different ways and we test it on Caltech 101 database. The results are good and show that such an approach improves objectively the ef- ficiency in the task of object category recognition.
Fichier principal
Vignette du fichier
klavdianos.pdf (696.52 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-00839640 , version 1 (28-06-2013)

Identifiants

  • HAL Id : hal-00839640 , version 1

Citer

Patrycia Klavdianos, Alamin Mansouri, Fabrice Meriaudeau. GESTALT-INSPIRED FEATURES EXTRACTION FOR OBJECT CATEGORY RECOGNITION. IEEE International Conference on Image Processing, Sep 2013, Melbourne, Australia. pp.1-5. ⟨hal-00839640⟩
253 Consultations
485 Téléchargements

Partager

Gmail Facebook X LinkedIn More