Extracting regions of interest based on visual attention model

This paper proposed a new approach of extracting regions of interest based on visual attention model, which segmented image regions with the region growing algorithm. According to the physiological characteristics of Human Visual System (HVS), image features were extracted by non-uniform sampling of image and computing "center-surround", which were used to simulate the human visual receptive field properties. Features became multi-scale conspicuity maps, which were combined into a saliency map. The focus of attention (FOA) as seeds of the region growing algorithm was obtained by the "winner-take-all" (WTA) competition. Then the regions of interest were extracted by using the region growing algorithm. The experiment results show that this approach can select suitable seeds automatically and the extraction of regions of interest can be consistent with human visual attention mechanism.