Title :
An information-theoretic approach to active vision
Author :
Boccignone, Giuseppe ; Ferraro, Mario ; Caelli, Terry
Author_Institution :
Dipartimento di Ingegneria dell´´Inf., Salerno Univ., Italy
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
Keywords :
active vision; entropy; image colour analysis; neural nets; statistical mechanics; active vision; colour image; conspicuity map; dynamic neural network; entropy production; focus-of-attention scanpath; information theory; spatio-chromatic diffusion; statistical mechanics; Computer vision; Density measurement; Entropy; Focusing; Image analysis; Image edge detection; Layout; Machine vision; Neural networks; Production;
Conference_Titel :
Image Analysis and Processing, 2001. Proceedings. 11th International Conference on
Conference_Location :
Palermo
Print_ISBN :
0-7695-1183-X
DOI :
10.1109/ICIAP.2001.957032
