A region of interest extraction for color image based on bottom-up saliency map

Rapid increase of the amount of image data necessitates the development of efficient tools for representing visual input. In this paper, we present an approach for automatically extracting the ROI (region of interest) and that can find objects using visual attention technique. Multiple image features such as intensity, color and orientation in multiple scales are extracted to get some feature maps. Using visual attention model to locate salient points, in which the winner point, the most salient point, is selected as candidate area for extracted ROIS. ROIs are obtained by combining salient regions in bottom-up saliency map. The experimental results obtained with the proposed method have demonstrated that the proposed method is effective in auto-extracting ROIs and performs well for different objects.