Finding Boundaries in Images

In computational vision, finding the boundaries of the regions in a image which correspond to different surfaces in the scene is usually approached as a problem of detecting brightness edges.In this paper, we argue that this is a limited ••iew.Boundaries in images could be associated with differences on a number of visual attributes-brightness, color, texture, stereoscopic disparity and motion-all of which are utilized in human <•ision.Machine vision systems should do the same.We argue that conmlution of the image with a bank of Gaussian derivative filters is a suitable common first stage for this task.\Fe also present some new results on the problem of detecting and localizing brightness edges composed of step, peak and roof profiles.