一种新的基于对应像素距离度量的图像相关匹配方法

传统的图像相关匹配方法中，由于实时图和参考图之间存在着灰度差异和一定程度的几何形变以及对目标的局部遮挡，使得利用求取对应像素灰度差累加和来进行相似性度量算法的性能很容易受到影响。文中从另一角度提出了一种新的图像相关匹配算法。该方法改变了原先匹配算法中求取模块图像和目标图像的像素灰度差的和的方法，而改为求取两幅图像之间相接近的点的个数，从而使匹配算法的稳定性大大提高，因为 局部出现的大片噪声点将不会影响匹配的结果，而这样的情况在传统的相关算法中将会显著影响匹配结果。实验结果表明了该方法的有效性。

A new image matching method based on a novel pixel distance measurement

Because of the difference of the grey value and the distortion between the object image and the reference image, traditional matching method will be degraded, and more useful characters are needed. In this paper, a new image matching method based on a novel distance measurement is proposed. Firstly it defines a novel similarity measurement from the thought of the Hausdorff distance measurement. It counts not only the distance of the grey level of the two images, but also the number of the similar points in the two images. Then the measurement method is applied in the image matching. The experimental results show that this image matching method could bear much image distortion and it is very promising.