With the rotation, translation and scaling invariance, etc. it is difficult to measure the similarity between GIS planar elements. To describe the graphics precisely, according to the number of shortest paths where vertices occur, we define the “vertex betweenness;” this measures the importance of each vertex in a graph. The higher the vertex betweenness, the more important vertex becomes. We propose a contour fea ture points extraction method, where Fourier descriptors are used. We normalize the first n order factors of Fourier descriptors, on the basis of similarity between polygons, which is obtained by comparing the cosine values for every two vectors. The experiment is operated on two different data scales, 1:50 000 and 1:250 000. Combined with analysis of impact factors during similarity measurement, the experiment results show that the contour feature points extraction method can effectively measure the geometrical similarity between GIS planar elements.
Fusion of Multispectral and Panchromatic Images via Local Geometrical Similarity
