一种改进的模板匹配算法

近几年来，数字图像处理在印刷质量自动检测系统中的应用得到了飞速的发展，寻找一种快速简单，自适应强，检测精度高的算法已引起了许多研究者的关注，文中在印刷质量检测过程中所用到的传统模板匹配的基础上提出了一种改进的新算法，在新算法中较详细的介绍了如何将多幅模板图像的特征综合为一个标准模板，如何随实时图像的不断变化对标准模板进行调整的自学习方法等，并通过实验证明新算法具有自适应性强和检测精度高等特点。

AN IMPROVED TEMPLATE MATCHING ALGORITHM

In recent years, the application of digital image processing to the print quality inspection system developed greatly. Many researchers focus on searching for a simple and fast algorithm with self-adjusting capability and high inspection precision. In this paper, an improved new algorithm, based on the traditional pattern matching method applied in the process of print quality inspection, is presented. In the new algorithm, we deliberately introduce how to synthesize characteristics of many templates into a standard template and how to adjust the standard template according to the variation of real-time images. And the results of experiments indicate the new algorithm has the advantages of self-adjusting capability and high inspection precision.