加权模板匹配的二值化阈值不敏感性研究-《计算机技术与发展》

文章信息/Info

Title:: Binarization Threshold Insensitivity Research of Weighted Template Matching

Author(s):: WANG Gang; DUAN Hui-chuan; [1]School of Information Science and Engineering, Shandong Normal University[2]Shandong Provincial Key Laboratory for Distributed Computer Software Novel Technology

Keywords:: weighted template matching; standard template matching; threshold insensitivity; binarization; weight matrix

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

Abstract:: 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