用边缘金字塔结构实现Hausdorff距离匹配

Hausdorff Distance Matching Algorithm Using Edge Pyramidal Structure

为了快速准确地在海量图像中搜索模板的所有实例 ,提出运用边缘金字塔结构来实现Hausdorff距离匹配 根据模板的边缘自适应地确定边缘金字塔分解次数和抽取模式 ,然后通过金字塔结构的引导搜索策略实现快速匹配 对以水平和垂直边缘为主的集成电路显微图像 ,文中算法体现出优越的匹配性能 在集成电路显微图像和一般图像上分别测试的实验结果表明 :文中算法在获得良好的匹配效果的同时 。

In order to match and locate all instances of a model precisely in massive images, an effective Hausdorff distance matching algorithm using edge pyramidal structure is proposed. The decomposition level and decimation mode of pyramidal structure are determined adaptively by the model edges. This can decrease the number of losing objects, at the same time greatly increase the speed of searching the model's instances in massive images. For integrated circuit's micro images, which are mainly composed of vertical and horizontal edges, the algorithm shows superior performance. The algorithm is tested in other images, and the matching also gives good results.