Image Saliency Analysis Based on Retina Simulation

Shu Fang, Yang Yue, Liuyuan He, Kai Du, Yonghong Tian, Tiejun Huang

Abstract: In this paper, we provide an insight of visual saliency modeling from the perspective of simulating visual information manipulation process in human vision system. For humans, visual stimuli are converted into spike trains by retina, and the spike signals are then transferred to brain areas for further analysis. Therefore, we propose to estimate image saliency based on a retina neural network, which is built with realistic morphology and electrophysics data. Then, we analyze the correlation between the spike trains generated by retina and image saliency. The experimental results show the effectiveness of retinal spike trains in image saliency analysis.