基于改进Hausdorff距离在图像匹配中的算法  

Algorithm Based on Advanced Hausdorff Distance in Image Registration

作　　者：徐文科 王国刚 

机构地区：[1]沈阳化工大学信息工程学院,辽宁 沈阳

出　　处：《计算机科学与应用》2020年第10期1798-1803,共6页Computer Science and Application

摘　　要：研究了一种基于Hausdorff距离的图像快速匹配算法。该方法是在单向Hausdorff距离算法对图像进行匹配,对目标区域和模板图像进行相似度计算,确定相似度最高的区域,去除距离相对较大匹配点,同时求其平均值,然后通过距离图像进行模板匹配。实验结果表明,该方法对包含噪声的复杂场景仍然有较高匹配速度和鲁棒性。A fast image registration algorithm based on Hausdorff distance is studied. This method is to match the image in the one-way Hausdorff distance algorithm and calculate the similarity between the target area and the template image. It can also determine the area with the highest similarity and remove the relatively large matching points. At the same time, it can calculate the average value, and then perform template matching through the distance image. Experimental results show that this method still has a high matching speed and robustness to complex scenes containing noise.

关 键 词：HAUSDORFF距离 图像处理 鲁棒性 图像匹配 

分 类 号：TP3[自动化与计算机技术—计算机科学与技术]