中文说明:图像匹配主要可分为以灰度为基础的匹配和以特征为基础的匹配。灰度匹配的基本思想:以统计的观点将图像看成是二维信号,采用统计相关的方法寻找信号间的相关匹配。利用两个信号的相关函数,评价它们的相似性以确定同名点。灰度匹配通过利用某种相似性度量,如相关函数、协方差函数、差平方和、差绝对值和等测度极值,判定两幅图像中的对应关系。特征匹配是指通过分别提取两个或多个图像的特征(点、线、面等特征),对特征进行参数描述,然后运用所描述的参数来进行匹配的一种算法。本代码包含下面两种基于灰度图像匹配算法:① 基于灰度的模板匹配算法② 基于灰度的快速匹配算法。
English Description:
Image matching can be divided into gray based matching and feature-based matching. The basic idea of gray level matching is to regard the image as a two-dimensional signal from the point of view of statistics, and use the method of statistical correlation to find the correlation matching between signals. By using the correlation function of two signals, the similarity between them is evaluated to determine the point with the same name. Gray level matching uses some similarity measures, such as correlation function, covariance function, sum of squares of difference, sum of absolute values of difference, to determine the corresponding relationship between two images. Feature matching is an algorithm that extracts two or more image features (point, line, surface and so on), describes the features with parameters, and then uses the described parameters to match. This code contains the following two gray image matching algorithms: ① gray based template matching algorithm; ② fast gray based matching algorithm.