Image segmentation based on locally excitatory globally inhibitory oscillator network

An image segmentation scheme was presented on the basis of locally excitato ry, globally inhibitory oscillator network (LEGION). Based on the concept o f the lateral potential, a solution to remove noisy regions in an image was proposed for LEGION. The temporal evolution of every stimulated oscilltor and network properties were illustrated by computer simulation. The dynamic connection weight addressing the grouping principles of proximity, similar ity and connectedness was setup. Using HSI space, the dynamic connection we ight emphasizing the Hue information was established, and better experiment al results than that based on RGB space were obtained.