Contour Detection by Synchronization of Integrate-and-Fire Neurons

Etienne Hugues 1 Florent Guilleux 1 Olivier Rochel 1
1 CORTEX - Neuromimetic intelligence
INRIA Lorraine, LORIA - Laboratoire Lorrain de Recherche en Informatique et ses Applications
Abstract : We present a biologically inspired spiking neural network which is able to detect contours in grey level images by synchronization of neurons. This network is made of integrate-and-fire neurons, spaced on a triangular network, whose oriented receptive field is constructed by a wavelet which specifically detects edges. The neurons are excitatorily and locally connected between receptive fields that tend to detect the same contour. A contour, if its width is not too large, activates a chain of neurons, with some heterogeneity in the inputs. The capacity of a chain to synchronize with respect to such heterogeneity is studied. Synchronization on a contour is found to be possible for a sufficiently large width.
Type de document :
Communication dans un congrès
Bülthoff, H.H. and Lee, S.-W and Poggio, T.A. and Wallraven, C. 2nd internationale Workshop on Biologically Motivated Computer Vision - BMCV 2002, Nov 2002, Tübingen, Allemagne, Verlag, 2525, pp.60-69, 2002, Lecture Notes in Computer Science
Liste complète des métadonnées

https://hal.inria.fr/inria-00100986
Contributeur : Publications Loria <>
Soumis le : mardi 26 septembre 2006 - 14:53:20
Dernière modification le : jeudi 11 janvier 2018 - 06:19:48

Identifiants

  • HAL Id : inria-00100986, version 1

Collections

Citation

Etienne Hugues, Florent Guilleux, Olivier Rochel. Contour Detection by Synchronization of Integrate-and-Fire Neurons. Bülthoff, H.H. and Lee, S.-W and Poggio, T.A. and Wallraven, C. 2nd internationale Workshop on Biologically Motivated Computer Vision - BMCV 2002, Nov 2002, Tübingen, Allemagne, Verlag, 2525, pp.60-69, 2002, Lecture Notes in Computer Science. 〈inria-00100986〉

Partager

Métriques

Consultations de la notice

191