An Autonomy Oriented Computing approach to image-component labeling

This paper presents an autonomy oriented computing (AOC) approach to gray-level image-component labeling. The basic elements of such AOC systems are autonomous entities placed in an environment. The environment, in our case, is viewed as a two-layer 2D lattice containing a gray-level image in the first layer and a notice board at the second layer. The environment serves as the place where autonomous entities reside, roam and operate. The goal of each autonomous entity is to locate and label image pixels belonging to the homogeneous component according to the specified criteria of the region's homogeneity. During the image exploration and evaluation the entities rely on their reactive and rational behaviors, such as diffusion, breeding and communication. By communicating, the entities are able to determine distinct components by assigning them different labels. Experiments based on a simulation of the proposed AOC system were run over a set of images from ldquoblocks worldrdquo.