Adaptive image segmentation with distributed behavior-based agents

This paper presents an autonomous agent-based image segmentation approach. In this approach, a digital image is viewed as a two-dimensional cellular e nvironment in which the agents inhabit and attempt to label homogeneous seg ments. In so doing, the agents rely on some reactive behaviors such as bree ding and diffusion. The agents that are successful in finding the pixels of a specific homogeneous segment will breed offspring agents inside their ne ighboring regions. Hence, the offspring agents will become likely to find m ore homogeneous-segment pixels. In the mean time, the unsuccessful agents w ill be inactivated, without further search in the environment.