Similarity measure of spectral vectors based on set theory and its application in hyperspectral RS image retrieval  

作　　者：杜培军 方涛 唐宏 施鹏飞 

机构地区：[1]Institute of Image Processing and Pattern Recognition, Shanghai Jiaotong University, Shanghai 200030 Department of Spatial Informatics, China University of Mining and Technology, Xuzhou 221008 [2]Institute of Image Processing and Pattern Recognition, Shanghai Jiaotong University, Shanghai 200030

出　　处：《Chinese Optics Letters》2003年第11期637-640,共4页中国光学快报（英文版）

基　　金：This research was supported by the National 863 Program of China(No.2001AA135091);National Natural Science Foundation of China(No.60275021);China Postdoctoral Science Foundation(No.2002032152).

摘　　要：In this paper, two new similarity measure methods based on set theory were proposed. Firstly, similarity measure of two sets based on set theory and set operation was discussed. This principle was used to spectral vectors, and two approaches were proposed. The first method was to create a spectral polygon corresponding to spectral curve, and similarity of two spectral vectors can be replaced by that of two polygons. Area of spectral polygon was used as quantification function and some effective indexes for similarity and dissimilarity were computed. The second method was to transform the original spectral vector to encoding vector according to absorption or reflectance feature bands, and similarity measure was conducted to encoding vectors. It proved that the spectral polygon-based approach was effective 'and can be used to hyperspectral RS image retrieval.In this paper, two new similarity measure methods based on set theory were proposed. Firstly, similarity measure of two sets based on set theory and set operation was discussed. This principle was used to spectral vectors, and two approaches were proposed. The first method was to create a spectral polygon corresponding to spectral curve, and similarity of two spectral vectors can be replaced by that of two polygons. Area of spectral polygon was used as quantification function and some effective indexes for similarity and dissimilarity were computed. The second method was to transform the original spectral vector to encoding vector according to absorption or reflectance feature bands, and similarity measure was conducted to encoding vectors. It proved that the spectral polygon-based approach was effective 'and can be used to hyperspectral RS image retrieval.

关 键 词：Image processing Set theory 

分 类 号：O433[机械工程—光学工程]