AUTHOR=Wang Yan , Li Teng , Wu Jun , Ding Chris H. Q. TITLE=Bio-driven visual saliency detection with color factor JOURNAL=Frontiers in Bioengineering and Biotechnology VOLUME=Volume 10 - 2022 YEAR=2022 URL=https://www.frontiersin.org/journals/bioengineering-and-biotechnology/articles/10.3389/fbioe.2022.946084 DOI=10.3389/fbioe.2022.946084 ISSN=2296-4185 ABSTRACT=Most visual saliency computing methods build models based on the contents in image, without considering the colorized effects. Biologically human attention can be influenced by color significantly. This paper firstly investigates the sole contribution of colors in visual saliency, and then propose a bio-driven saliency detection method with color factor. To study the color saliency despite of the contents, an eye-tracking dataset containing color images and gray-scale images of the same content is proposed, collected from 18 subjects. The CIELab color space is selected to conduct extensive analysis to identify the contribution of colors in guiding visual attention. Based on the observations that some particular colors and combinations of color blocks can attract more attention than others, the influence of colors on visual saliency is represented computationally. Incorporating the color factor, a novel saliency detection model is proposed to model the human color perception prioritization, and a deep neural network model is proposed for eye fixation prediction. Experiments validate that the proposed bio-driven saliency detection models make substantial improvements in finding informative content, and they are benefit to the detection of salient object which is close to human visual attention in natural scene.