A Psychophysical Oriented Saliency Map Prediction Model

Visual attention is one of the most significant characteristics for selecting and understanding the outside redundancy world. The nature of complex scenes includes enormous redundancy. The human vision system can not process all information simultaneously because of visual information bottleneck. The human visual system mainly focuses on dominant parts of the scenes to reduce the input visual redundancy information. It is commonly known as visual attention prediction or visual saliency map. This paper proposes a new psychophysical saliency prediction architecture, WECSF, inspired by human low-level visual cortex function. The model consists of opponent color channels, wavelet transform, wavelet energy map, and contrast sensitivity function for extracting low-level image features and maximum approximation to the human visual system. The proposed model is evaluated several datasets, including MIT1003, MIT300, TORONTO, SID4VAM and UCF Sports dataset to explain its efficiency. We also quantitatively and qualitatively compared the performance of saliency prediction with other state-of-the-art models. Our model achieved very stable and good performance. Second, we also confirmed that Fourier and spectral-inspired saliency prediction models achieved outperformance compared to other start-of-the-art non-neural networks and even deep neural network models on psychophysical synthesis images. Finally, the proposed model also can be applied to spatial-temporal saliency prediction and got better performance.