Bottom-up saliency based on weighted sparse coding residual

Abstract

The guidance of attention helps the human vision system (HVS) to detect and recognize objects rapidly. In this paper, we propose a bottom-up saliency algorithm based on sparse coding theory. Sparse coding decomposes the inputs into two parts, codes and residual. From the viewpoint of biological vision and information theory, the coding length is closely related to the local complexity while the residual is closely related to the uncertainty. The proposed algorithm defines the weighted residual using sparse coding length as saliency. By multiplying the L0 norm of sparse codes and the residual, a saliency map is obtained. The performance of the proposed method is evaluated using ROC curves with two different scale datasets and is compared with state-of-the-art models. Our algorithm outperforms all other methods and the results indicate a robust and accurate saliency.