Abstract
The amount of visual information projected from the retina to the brain exceeds the information processing capacity of the latter. Attention, therefore, functions as a filter to highlight important information at multiple stages of the visual pathway that requires further and more detailed analysis. Among other functions, this determines where to fixate since only the fovea allows for high resolution imaging. Visual saliency modeling, i.e. understanding how the brain selects important information to analyze further and to determine where to fixate next, is an important research topic in computational neuroscience and computer vision. Most existing bottom-up saliency models use low-level features such as intensity and color, while some models employ high-level features, like faces. However, little consideration has been given to mid-level features, such as texture, for visual saliency models. In this paper, we extend a biologically plausible proto-object based saliency model by adding simple texture channels which employ nonlinear operations that mimic the processing performed by primate visual cortex. The extended model shows statistically significant improved performance in predicting human fixations compared to the previous model. Comparing the performance of our model with others on publicly available benchmarking datasets, we find that our biologically plausible model matches the performance of other models, even though those were designed entirely for maximal performance with little regard to biological realism.
Highlights
Human eyes capture and send large amounts of data from the environment to the brain, more than can be processed in detail
We propose simplified descriptions of texture that can be incorporated into cortical models of visual attention, our previous proto-object based visual saliency model (Russell et al, 2014)
The saliency maps of each model are blurred by Gaussian filters whose standard deviations are set as resulting the best similarity metric (SIM) metrics for each model as described in Effect of Blurring the Saliency Map
Summary
Human eyes capture and send large amounts of data from the environment to the brain, more than can be processed in detail. To deal with the overwhelming quantity of input, various stages of visual processing select a small subset of all available information for detailed processing and discard the remainder, for reviews see Desimone and Duncan (1995), Reynolds and Chelazzi (2004), Petersen and Posner (2012). Understanding quantitatively how the brain selects important information, and where humans fixate, is an important research topic in neuroscience and computer vision. In a seminal study, Koch and Ullman (1985) laid the basis for understanding the mechanisms of selective attention in terms of biologically plausible neuronal circuitry which led to the development of detailed computational models of this process (Niebur and Koch, 1996; Itti et al, 1998; Itti and Koch, 2001). A better understanding of visual attentive selection will improve the effectiveness of graphic arts, advertisements, traffic signs, camouflage and many other applications, as well as contributing to the basic science goal of understanding visual processing in the brain.
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
