中文摘要：

针对传统的归一化互相关方法（NCC）在图像匹配时计算量大的缺陷,提出了一种新的基于NCC的快速模板匹配算法。该算法基于粗、精匹配的思想,将区域质心特征、颜色直方图信息与归一化互相关匹配方法结合起来实现图像的定位匹配。在图像匹配时以搜索图像的质心点作为参考点,而非通常情况下以左上角点作为参考点,减少模板的搜寻空间。通过大量的实验表明,该算法可以大大提高全搜索NCC匹配算法的运算速度,同时保持了匹配的精度,可以满足实时性的要求。

英文摘要：

A new algorithm of fast template matching based on normalized cross correlation（NCC） is proposed.In this paper,area centroid and histogram information are used to select the matching candidates,then by applying NCC to get the final result.Additionally,the searching starts from the image centroid,not usual upper left corner points.A large number of experimental results show the proposed algorithm is very efficient comparing with full-search NCC,and it can be used for real-time matching.