ICCVG 2002 - template

We propose a biologically motivated computational step, called surround inhibition, which improves the performance of contour detectors. The mechanism of surround inhibition is exhibited by the majority of the orientation selective neurons in the primary visual cortex of macaque monkeys and has been demonstrated to influence the visual perception of man as well. We illustrate the principle and the effect of surround inhibition by adding this step to the Canny edge detector. The resulting operator responds strongly to isolated lines, edges, and contours but exhibits a weaker or no response to edges that make part of texture. We use natural images with associated ground truth edge maps to evaluate the performance of the proposed operator in contour detection tasks. The new operator outperforms the traditional Canny edge detector, mostly due to a reduced number of false positives. keywords : Canny operator, contour detection, edge detection, texture, surround inhibition, nonclassical receptive field inhibition.