Visual Attention Region Determination Using Low-Level Features *

In this study, a visual attention region determination approach using low-level lu-minance, color, and region features is proposed. First, the contrast map of an image is obtained by computing the contrast between each pixel and its “thresholding ” neighbor-ing pixels in eight directions, based on the just noticeable difference (JND) model. Then, the block-based edge map and standard deviation representation are used to generate the region mask of the image. The saliency map of the image is generated by using the con-trast map and the region mask of the image. Finally, based on the saliency map of the image, a visual attention region determination scheme is proposed to determine the visu-al attention regions in the image. Based on the experimental results obtained in this study, the performance of the proposed approach is better than that of three comparison approaches