A neural model of contour integration in the primary visual cortex

Algorithms that encode images using a sparse set of basis functions have previously been shown to explain aspects of the physiology of a primary visual cortex (V1), and have been used for applications, such as image compression, restoration, and classification. Here, a sparse coding algorithm, that has previously been used to account for the response properties of orientation tuned cells in primary visual cortex, is applied to the task of perceptually salient boundary detection. Specifically, neurons are linked by lateral excitatory connections if they represent edge elements that have locations and orientations consistent with a smooth, co-circular, contour. Such connections are consistent with natural image statistic. . Lateral connections serve to enhance the representation of extended contours. The method of implementing lateral excitatory connections in the PC/BC model