Biologically motivated trainable selective attention model using adaptive resonance theory network

Abstract

In this paper, we propose a trainable selective attention model that can inhibit an unwanted salient area and only focus on an interesting area in a static natural scene. The proposed model was implemented by the bottom-up saliency map model in conjunction with the adaptive resonance theory (ART) network. The bottom-up saliency map model generates a salient area based on intensity, edge, color and symmetry feature maps, and human supervisor decides whether the selected salient area is important. If the selected area is not interesting, the ART network trains and memorizes that area, and also generates an inhibit signal so that the bottom-up saliency map model does not have attention to an area with similar characteristic in subsequent visual search process. Computer simulation results show that the proposed model successfully generates the plausible sequence of salient region that does not give an attention to an unwanted area.