基于Hausdorff距离和遗传算法的物体匹配方法  

Hausdorff Distance Based Object Matching with Genetic Algorithms

作　　者：刘健庄[1] 谢维信[1] 高新波[1] 马堃 

机构地区：[1]西安电子科技大学

出　　处：《电子学报》1996年第4期1-6,共6页Acta Electronica Sinica

基　　金：国家自然科学基金

摘　　要：在模式识别与机器视觉中，常常需要进行图像中的物体检测。本文将Ｈａｕｓｄｏｒｆｆ距离作为物体轮廓的相似性的测度，并用遗传算法进行最佳物体匹配的快速搜索方法，实验结果表明，本文的方法能有效地检测出具有平移。Detection of objects in images is often needed in pattern recognition and machine vision.In this paper,the Hausdorff distance is used to measure the degree of similarity between two objects,and a genetic algorithm is utilized to search interested objects.The experimental results show that the proposed method can efficiently detect the objects in images regardless of their changes in translation,rotation and scale.

关 键 词：豪斯道夫距离 匹配 遗传算法 模式识别 

分 类 号：O235[理学—运筹学与控制论] TP391.4[理学—数学]