A biologically motivated and computationally tractable model of low and mid-level vision tasks

This paper presents a biologically motivated model for low and mid-level vision tasks and its interpretation in computer vision terms. Initially we briefly present the biologically plausible model of image segmentation developed by Stephen Grossberg and his collaborators during the last two decades, that has served as the backbone of many researchers' work. Subsequently we describe a novel version of this model with a simpler architecture but superior performance to the original system using nonlinear recurrent neural dynamics. This model integrates multi-scale contour, surface and saliency information in an efficient way, and results in smooth surfaces and thin edge maps, without posterior edge thinning or some sophisticated thresholding process. When applied to both synthetic and true images it gives satisfactory results, favorably comparable to those of classical computer vision algorithms. Analogies between the functions performed by this system and commonly used techniques for low- and mid-level computer vision tasks are presented. Further, by interpreting the network as minimizing a cost functional, links with the variational approach to computer vision are established.