Title :
Irregular adaptative pyramid of agents for segmentation to interpretation of image
Author :
Duchesnay, Edouard ; Montois, Jean-Jacques ; Jacquelet, Yann ; Kinie, Abel
Author_Institution :
Lab. Traitement du Signal et de l´´Image, Rennes I Univ., France
Abstract :
The paper presents the main concepts of a machine vision architecture based on a hybrid and a fine granularity multiagent system, that encourages incremental design via modular and hierarchical structuring of knowledge and pattern recognition mechanisms. The objective is not optimality of the image segmentation/interpretation but rather reliability versus unforeseen observation. We then present a first implementation of the architecture that tends to validate the approach and also that shows up a physical distribution of computation
Keywords :
adaptive systems; computer vision; image recognition; image segmentation; multi-agent systems; fine granularity multiagent system; hierarchical knowledge structuring; image interpretation; image segmentation; image segmentation/interpretation; incremental design; irregular adaptative agent pyramid; irregular adaptive pyramid; machine vision architecture; pattern recognition mechanisms; reliability; unforeseen observation; Computer architecture; Computer vision; Computerized monitoring; Distributed control; Image segmentation; Machine vision; Merging; Multiagent systems; Pattern recognition; Physics computing;
Conference_Titel :
Systems, Man, and Cybernetics, 2000 IEEE International Conference on
Conference_Location :
Nashville, TN
Print_ISBN :
0-7803-6583-6
DOI :
10.1109/ICSMC.2000.886246
