A SOCIETY OF GOAL-ORIENTED AGENTS FOR THE ANALYSIS OF LIVING CELLS

This paper presents a new model for the segmentation and analysis of l iving cells. A multi-agent model has been developed for this applicati on. It is based on a generic agent model, which is composed of differe nt behaviors: perception, interaction and reproduction. The agent is f urther specialized to accomplish a specific goal. Different goals are defined from the different components of the cell images. The speciali zation specifies the parameters of the behaviors for the achievement o f the agent's goal. From these goal-oriented agents, a society is defi ned, and it evolves dynamically as the agents are created and deleted. An internal manager is integrated in the agent to control the behavio r's execution. It makes use of an event-driven scheme to manage the be havior priorities. The present design is mainly oriented toward image segmentation, however, it includes some features on tracking and motio n analysis. (C) 1998 Elsevier Science B.V. All rights reserved.