改进的Hausdorff距离和遗传算法在图像匹配中的应用  

The Application of Improved Hausdorff Distance and Genetic Algorithm in Image Matching

作　　者：臧铁飞[1] 沈庭芝[1] 陈建军[1] 顾建军 

机构地区：[1]北京理工大学电子工程系,北京100081

出　　处：《北京理工大学学报》2000年第6期733-737,共5页Transactions of Beijing Institute of Technology

摘　　要：研究模板和图像间的有效匹配 .将部分 Hausdorff距离的计算进行改进 ,提出一种改进的部分 Hausdorff距离作为检测模板和图像中物体轮廓相似性的测度 ,可以较大地减少计算量 .同时把遗传算法引入图像匹配识别 .由于遗传算法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 ,因此该算法和改进的 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 .Effectively matching the model with the image is studied. The directed Hausdorff distance is improved to measure the degree of similarity between models and images, which can reduce the computational complexity. Genetic algorithm is used to search the interested objects. Because the genetic algorithm is a parallel and robust algorithm, the combination of genetic algorithm and improved Hausdorff distance can be used to find the global optimum results. The experimental results show that the proposed method can efficiently detect the objects that are changed in translation, rotation and scale. The method can be used in image identification and matching in practice.

关 键 词：HAUSDORFF距离 数字图像处理 图像匹配 遗传算法 

分 类 号：TN911.73[电子电信—通信与信息系统] TP18[电子电信—信息与通信工程]