一种基于距离变换的图象匹配方法

AN IMAGE MATCHING METHOD BASED ON DISTANCE TRANSFORMS

如何对于不同成像条件下的图象进行匹配是采用传统方法难以解决的一个难题。本文将距离变换引入图象匹配中，提出抗几何失真和边缘变化的边缘特征匹配准则，推导出它的快速匹配算法。大量实验表明，这种方法有效地克服了几何失真、边缘变化的影响，而且具有抗灰度反转的能力。

How to match two images obtained from different sensors or under different imaging conditions is a difficult problem for traditional matching methods. In this paper, distance transform is introduced into matching process. First, an edge matching criterion condidering geometric distortions and edge changes is proposed. Then its fast matching algorithm is induced. Experimental results prove that this method can effectively overcome the affection of geometric distortion and edge changes.