一种改进的Hausdorff距离模板匹配算法  

A Modified Algorithm for Model-Based Matching Using Hausdorff Distance

作　　者：陈玲芝[1] 王保保[1] 董建国[1] 

机构地区：[1]西安电子科技大学计算机科学与技术系,陕西西安710071

出　　处：《计算机技术与发展》2009年第5期82-85,共4页Computer Technology and Development

摘　　要：检测和提取图像中的目标图像是图像处理和模式识别等领域里非常活跃的问题。因为Hausdorff距离对于目标遮挡、图像噪声和图像晃动等情况具有较好的鲁棒性,因此使用Hausdorff距离进行图像匹配是较常用的方法之一。为了降低此算法的计算复杂度,提高匹配效率,提出了一种能够从待匹配图像中高效匹配出模板图像的改进算法。将文中提出的改进算法分别应用到一幅图像和视频序列图像中,实验结果证明了该算法的高效性。In image processing and pattern recognition, it is a key technique to detect regions of interested in test image and extract them from test image. Because Hausdorff distance is robust to object occlusion, image noise, and clutter, etc, model - based matching using Hausdorff distance is one of the frost common approaches. In order to reduce the computational complexity of the approach above, improve efficiency, a modified algorithm that can efficiently detect model image in test image is proposed in this paper with the same accuracy as the one unmodified. Finally, the proposed algorithm is applied to image matching on a single image and a video sequence, with good visual and objective matching efficiency results.

关 键 词：感兴趣区域 HAUSDORFF距离 模板匹配 高效性 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]