The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Publications Copernicus
Articles | Volume XL-3
11 Aug 2014
 | 11 Aug 2014

Shape-Based Image Matching Using Heat Kernels and Diffusion Maps

Yu. V. Vizilter, V. S. Gorbatsevich, A. Yu. Rubis, and S. Yu. Zheltov

Keywords: Image Matching, Diffusion Maps, Mathematical Morphology

Abstract. 2D image matching problem is often stated as an image-to-shape or shape-to-shape matching problem. Such shape-based matching techniques should provide the matching of scene image fragments registered in various lighting, weather and season conditions or in different spectral bands. Most popular shape-to-shape matching technique is based on mutual information approach. Another wellknown approach is a morphological image-to-shape matching proposed by Pytiev. In this paper we propose the new image-to-shape matching technique based on heat kernels and diffusion maps. The corresponding Diffusion Morphology is proposed as a new generalization of Pytiev morphological scheme. The fast implementation of morphological diffusion filtering is described. Experimental comparison of new and aforementioned shape-based matching techniques is reported applying to the TV and IR image matching problem.