Frequency domain filtering of gradient image for contour detection

A novel computational step, frequency-domain filtering of gradient image, is proposed to improve detection of object contours and region boundaries in natural scenes for gradient-based edge detectors. The step is inspired by analyzing the spectrum distribution of object contours and texture edges in the frequency domain of gradient image. We illustrate the principle and effect of the proposed step by adding it to the Canny edge detector. The resulting operator can selectively retain object contours, and meanwhile can dramatically reduce non-meaningful elements resulting from a texture background. Experimental results demonstrate the effectiveness of the proposed additional step.