Using directional variance to extract curves in images , thus improving object recognition in clutter

In this report we describe a method for extracting curves from an image using directional pixel variances instead of gradient measures as low-level boundary evidence. The advantage of the variance over the image gradient is that we can accurately compute the direction of a local edge even if a sudden contrast change occurs in the background. This allows curves belonging to object contours to be followed more easily. We compared our method to a similar method based on the image gradient and we found that it obtains better results when run on synthetic and natural images. Our method also improved the performance of a contour-based 3D object recognition system in cluttered images.