加权模板匹配的二值化阈值不敏感性研究  

Binarization Threshold Insensitivity Research of Weighted Template Matching

作　　者：王刚[1] 段会川[2] 

机构地区：[1]山东师范大学信息科学与工程学院,山东济南250014 [2]山东省分布式计算机软件新技术重点实验室,山东济南250014

出　　处：《计算机技术与发展》2012年第1期122-125,共4页Computer Technology and Development

基　　金：山东省信息产业发展专项资金项目(2008R00038)

摘　　要：数字图像二值化处理过程中,阈值的选取非常之关键,为了在实际应用中能够快速准确地匹配出二值化图像中的目标图像,文中采用模板匹配的方法,对标准模板匹配算法和加权模板匹配算法的二值化阈值敏感性进行了研究。根据实验图像在二值化处理过程中所取阈值的波动对图像匹配结果的影响情况,得到加权模板匹配算法与标准模板匹配算法的二值化阈值敏感性差异。实验结论同时表明加权模板匹配算法具有较强的二值化阈值不敏感性和匹配性能好的优点。In binary digital image processing, threshold selection is very critical. In order to match the target image of the binary image quickly and accurately in practice, use template matching method to research binary threshold sensitivity for the standard template matching algorithm and the weighted template matching algorithm. According to the threshold results of fluctuations on the match situation in the experimental binary image processing, obtain binarization threshold sensitivity difference between the weighted template matching algorithm and the standard template matching algorithm. Experimental results also show that the weighted template matching algorithm has strong binarization threshold does not match the performance of sensitivity and good benefits.

关 键 词：加权模板匹配 标准模板匹配 阈值不敏感性 二值化 权值矩阵 

分 类 号：TP39[自动化与计算机技术—计算机应用技术]