Abstract:

In the view of human visual feature, the Lateral Inhibition of human vision that has features of inhibiting center and enhancing surroundings is combined with Intersecting Cortical Model, for the sake of forming the Lateral InhibitionIntersecting Cortical Model which brings into correspondence with human visual. Meanwhile, through the gray levelaverage gray level histogram, 1D Chisquare divergence is extended to 2D Chisquare divergence, then the segmentation criterion based on the rule of 2D Chisquare divergence is structured. Further, a new realtime segmentation algorithm is proposed. At last, simulations validate that this algorithm is not only more simple than 2D crossentropy one in computing complexity, but also superior to the classical original ICM and Otsu in the performance of outcomes.

Key words: intersecting cortical model;gray levelaverage gray level histogram；2D chisquare divergence;lateral inhibition model;inhibition modulus