一种改进的部分Hausdorff距离检测技术和遗传算法在图像匹配识别中的应用  

One technique of improved Hausdorff distance and genetic algorithm in image matching recognition

作　　者：沈庭芝[1] 臧铁飞[1] 朱少娟[1] 方力[1] 

机构地区：[1]北京理工大学电子工程系,北京100081

出　　处：《通信学报》2001年第12期112-116,共5页Journal on Communications

基　　金：国防预研基金资助项目

摘　　要：本文提出一种改进的部分Hausdorff距离作为模板和图像中物体轮廓相似性的测度,较大地减少计算量。同时把遗传算法引入图像匹配识别,由于GA的高并行性和鲁棒性,可以较快地完成全局搜索,而不会陷入局部最优,因此GA和改进的Hausdorff距离相结合能有效地检测出具有平移、旋转和尺度变化的物体,以达到模板和图像间的有效匹配。The paper provide that improved partial Hausdorff distance is to measure the degree of similarity between models and images outline,which can greatly reduce the computational complexity.GA is used to image march recognition, because GA has high parallel and robust performance,it will fast search global ,and it is not possible to get into partial optimum。The combination of GA and improved Hausdorff distance can be efficiently detected the objects that are changed in translation, rotation and scale, so that effectively matching between model and image

关 键 词：HAUSDORFF距离 图像匹配 遗传算法 图像识别 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]