Salient Regions for Image Matching

A probabilistic definition of saliency is given in a form suitable for applications to image matching. In order to make this definition, the values of the pixels in pairs of matching regions are modeled using an elliptically symmetric distribution (ESD). The values of the pixels in background pairs of regions are also modeled using an ESD. If a region is given in one image, then the conditional probability density function for the matching region in a second image of the same scene can be calculated. The saliency of the given region is defined to be the Kullback-Leibler divergence between this conditional pdf and a background conditional pdf. Experiments carried out using images in the Middlebury stereo database show that if the salience of a given image region is high, then there are few background regions with a better match to the given region than the true matching region. Salient Regions for Image Matching S.J. Maybank 1st December 2011 Department of Computer Science and Information Systems, Birkbeck College, Malet Street, London, WC1E 7HX, UK. [email protected] Abstract. A probabilistic definition of saliency is given in a form suitable for applications to image matching. In order to make this definition, the values of the pixels in pairs of matching regions are modeled using an elliptically symmetric distribution (ESD). The values of the pixels in background pairs of regions are also modeled using an ESD. If a region is given in one image, then the conditional probability density function for the matching region in a second image of the same scene can be calculated. The saliency of the given region is defined to be the Kullback-Leibler divergence between this conditional pdf and a background conditional pdf. Experiments carried out using images in the Middlebury stereo database show that if the salience of a given image region is high, then there are few background regions with a better match to the given region than the true matching region.