A Novel Biologically Inspired Visual Saliency Model

The paper focuses on the modeling of visual saliency. We present a novel model to simulate the two stages of visual processing that are involved in attention. Firstly, the proto-object features are extracted in the pre-attentive stage. On the one hand, the salient pixels and regions are extracted. On the other hand, the semantic proto-objects, which involve all possible states of the observer’s memories such as face, person, car, and text, are detected. Then, the support vector machines are utilized to simulate the learning process. As a consequence, the association between the proto-object features and the salient information is established. A visual attention model is built via the method of machine learning, and the saliency information of a new image can be obtained by the way of reasoning. To validate the model, the eye fixations prediction problem on the MIT dataset is studied. Experimental results indicate that the proposed model effectively improves the predictive accuracy rates compared with other approaches.