Identifying the type of stimuli that attracts human visual attention has been an appealing topic for scientists for many years. In particular, marking the salient regions in images is useful for both psychologists and many computer vision applications. In this paper, we propose a computational approach for producing saliency maps using statistics and machine learning methods. Based on four assumptions, three properties (Feature-Prior, Position-Prior, and Feature-Distribution) can be derived and combined by a simple intersection operation to obtain a saliency map. These properties are implemented by a similarity computation, support vector regression (SVR) technique, statistical analysis of training samples, and information theory using low-level features. This technique is able to learn the preferences of human visual behavior while simultaneously considering feature uniqueness. Experimental results show that our approach performs better in predicting human visual attention regions than 12 other models in two test databases.

No abstract

Computational visual attention (CVA) model is one of the methods which focus on finding region of interesting (ROI) in an image or in a scene. Similarity attention is one important task in CVA. If there are many objects in a scene, people will pick up the most abnormal one, which perhaps the similar one or dissimilar one, according to the composition objects of the scene. Capability of similarity attention enables human vision to promptly focus on similar or dissimilar regions in a scene. This paper implements this capability in the CVA model by attaching a high-level similarity comparison function to find ROI in the scene. The output of the model simulates the serial search mode and more approach to human visual behavior. Experimental results show that the function of similarity attention can be achieved successfully.