Automatic multi-resolution image registration based on genetic algorithm and Hausdorff distance

作     者：叶发茂 苏林 李树楷 

作者机构：Institute of Remote Sensing Applications Chinese Academy of Sciences 

出 版 物：《Chinese Optics Letters》 (中国光学快报（英文版）)

年 卷 期：2006年第4卷第7期

页      面：386-388页

核心收录：

学科分类：0808[工学-电气工程] 0809[工学-电子科学与技术（可授工学、理学学位）] 08[工学] 080203[工学-机械设计及理论] 0805[工学-材料科学与工程（可授工学、理学学位）] 0802[工学-机械工程] 0702[理学-物理学] 

主　　题：Decomposition Genetic algorithms 

摘      要：Image registration is a crucial step in all image analysis tasks in which the final information is gained from the combination of various data sources, and it is difficult to automatically register due to the complexity of image. An approach based on genetic algorithm and Hausdorff distance to automatic image registration is presented. We use a multi-resolution edge tracker to find out the fine-quality edges and utilize the Hausdorff distance between the input image and the reference image as similarity measure. We use wavelet decomposition and genetic algorithm, which combine local search methods with global ones balancing exploration and exploitation, to speed up the search of the best transformation parameters. Experimental results show that the proposed approach is a promising method for registration of image.