摘要
指针式仪表示值的自动判读技术在工农业生产中有着广泛的应用,这种自动判读技术主要是通过图像处理技术来实现的,其常见的自动判读方法有三种:步长法、圆周灰度检测法、哈夫变换法。本文在总结上述方法的基础上,提出了一种鲁棒性较好的基于灰度信息的多特征模板匹配法。
This paper puts forward the crux algorithm that identifies automatically the position and direction of the pointers of meter with techniques of the image processing. Considering the optics of the non-uniform shining on the meter and the shadow jam of pointers,the author employs the moldplate-matching method based on the several characteristic parameters of the pointers of the meter to recognize the indicating values of the pointer.The characteristic parameters include the area,the gray,the shape and the information of distribution of the pointer's gray. These series of processing methods offer high stability and good repetition.
出处
《电测与仪表》
北大核心
2004年第4期56-58,共3页
Electrical Measurement & Instrumentation
