基于模板匹配的电能表液晶屏检测新方法

为实现自动化检定中对智能电能表液晶屏质量的在线检测,并解决误判率高的难题,文中提出了一种基于快速模板匹配的电能表在线液晶屏检测新方法。该方法采用基于阈值自适应序贯相似性算法的自学习型模板快速匹配算法,将多幅模板图像的特征综合为一个标准模板,建立实时调整的自学习型模板库,并改进传统的序贯相似性算法,将其阈值自适应。实验结果表明文中提出的方法不仅具有较高的检测效率和匹配精度,还有效降低误判率,具有较高的工程应用价值。

LCD detecting method of smart electricity meter based on template matching

In order to realize the function of on-line detection on LCD screen of smart electricity meters in automation test system, and to solve the problem of high wrong judgment rate, a quality on-line detection method based on fast tem-plate matching is proposed in this paper. In the method, a new algorithm of self-learning fast template matching based on Sequential Similarity Detection Algorithm (SSDA) with threshold automatic is adopted. The paper describes in detail how to synthesize characteristics of many templates into a standard template and how to establish real-time and self-learning template library. And SSDA is improved with threshold self-adjusting. The results of experiments indicate that the new method not only has high detection efficiency and matching accuracy, and low wrong judgment rate, but also has great application value of engineering.