基于图象差距分割的快速目标匹配识别算法  

A FAST TEMPLATE MATCHING ALGORITHM BASED ON THE MEASURE OF DIFFERENCE BETWEEN IMAGES

作　　者：丘江[1] 刘波[1] 杨静[1] 

机构地区：[1]中国科学院西安光学精密机械研究所,710068

出　　处：《光子学报》2001年第11期1343-1347,共5页Acta Photonica Sinica

基　　金：中国科学院西安分院院长基金资助项目

摘　　要：本文在模板匹配的算法基础上 ,引入图象差距度量的思想 ,以最大图象距离差选取好的阈值 ,实现目标与背景的有效分离 ,以减少模板匹配的计算区域为手段 ,减少算法的计算量 ,并提高模板匹配算法的识别精度 .实验证明 。Template matching has high discrimination in identification when target has no rotation and scaling invariant.It is simple and efficient.In the situation which the background is complex,discrimination will be very low since background disturbing.To solve this problem,the images difference measure is introduced in template matching algorithm.A good threshold is selected based on the principle that the difference between garget and background is big.With this threshold,the target and background is segmented.Since the template matching operation region is reduced,the operation times are much more reduced and high discrimination is kept.Experimental results show that this algorithm can work effectively.

关 键 词：图象分割 阈值选取 模板匹配 图像识别 图像差距 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]