An approach to active vision based on information theory and statistical mechanics is presented. Density of entropy production measured along a spatio-chromatic diffusion of a colour image is used to build a conspicuity map of the image. The map is successively given as input to a dynamic neural network in order to drive a focus-of-attention scanpath.

An information-theoretic approach to active vision / G. Boccignone, M. Ferraro, T. Caelli - In: Image Analysis and Processing, 2001. Proceedings. 11th International Conference on / [a cura di] E. Ardizzone, V. DiGesu. - [s.l] : IEEE, 2001. - ISBN 076951183X. - pp. 340-345 (( Intervento presentato al 11. convegno International Conference on Image Analysis and Processing tenutosi a Palermo nel 2001 [10.1109/ICIAP.2001.957032].

An information-theoretic approach to active vision

G. Boccignone
Primo
;
2001

Abstract

An approach to active vision based on information theory and statistical mechanics is presented. Density of entropy production measured along a spatio-chromatic diffusion of a colour image is used to build a conspicuity map of the image. The map is successively given as input to a dynamic neural network in order to drive a focus-of-attention scanpath.
color; image; segmentation
Settore ING-INF/05 - Sistemi di Elaborazione delle Informazioni
2001
International Association for Pattern Recognition (IAPR)
Italian Council of Research (CNR)
University of Palermo
Book Part (author)
File in questo prodotto:
File Dimensione Formato  
00957032.pdf

accesso riservato

Tipologia: Publisher's version/PDF
Dimensione 630.28 kB
Formato Adobe PDF
630.28 kB Adobe PDF   Visualizza/Apri   Richiedi una copia
Pubblicazioni consigliate

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/2434/494305
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 9
  • ???jsp.display-item.citation.isi??? 2
social impact