Corner Detection in Color Images By Multiscale Combination of End-Stopped Cortical Cells

. We present a corner-detection algorithm based on a model for end-stopping cells in the visual cortex. Shortcomings of this model are overcome by a combination over several scales. The notion of an end-stopped cell and the resulting corner detector is generalized to color channels in a biologically plausible way. The resulting corner detection method yields good results in the presence of high frequency texture, noise, varying contrast, and rounded corners. This compares favorably with known corner detectors. 1 Introduction Corners are important image features because they are robust with respect to changes in perspective and small distortions, and they allow efficient matching for recognition purposes. It is known that removing the corners from images impedes human recognition performance, while removing much of the edge information does not [1]. Robustness and speed of corner matching can be improved by adding attributes to the corners [8]. This makes computationally expensive dete..