A real-time edge detection ASIC design

A method of generating edge maps thereby segmenting an image into regions based an the Kolomogorov-Smirnov test is presented. By applying this test to compare the cumulative distribution functions of the intensities in the neighborhood of a given pixel, the pixel call be accurately classified as either an edge pixel on the boundary between regions, or as a pixel of a particular type of region. Using the simple operations in a parallel pipeline fashion, an ASIC for this algorithm is designed and it is shown that this algorithm can satisfy easily the required speed for implementing edge detection for images with 512/spl times/512 refreshing at 25 frames per second.<>