Contextual texture based bottom-up visual attention

Modeling visual attention provides an alternative methodology to image description in many applications such as adaptive content delivery and image retrieval. In this paper, we propose a robust approach to the modeling bottom-up visual attention. The main contributions are twofold: 1) A novel contextual texture feature is extracted to describe texture consistency of a region globally. And then the salient map can be robustly generated for a variety of nature images; 2) A practicable framework for modeling visual attention is presented based on global information. The proposed approach intrinsically provides an alternative methodology to model attention with low implementation complexity. Experiments show that the proposed algorithm is effective and can characterize the human perception well.