Inferring region salience from binary and gray-level images

We introduce a method that uses contour fragments to highlight regions of interest. Our method obtains as input either a binary image or the gradient map of a gray-level image. It produces a saliency map that re0ects for every point in the image our belief that it belongs to a salient region. Saliency is determined by criteria such as closure, convexity, and size. In addition, gaps in the boundaries of regions diminish their saliency. Explicit scale parameter determines the size of interest. The method is implemented by a convolution of the input edge image with a linear 6lter that speci6es the region of in0uence of a contour point over the image. Experiments demonstrate the utility of the method for saliency and segmentation. ? 2003 Pattern Recognition Society. Published by Elsevier Ltd. All rights reserved.