基于图像处理的智能电表显示缺陷自动检测系统设计  

Automatic testing system design of smart meter based on computer vision

作　　者：王舒憬[1] 陈凯[1] 

机构地区：[1]上海大学机电工程与自动化学院,上海200072

出　　处：《电测与仪表》2016年第4期63-68,共6页Electrical Measurement & Instrumentation

摘　　要：文章设计了一种基于图像处理的自动检测系统,能够实现智能电表显示面板质量检测的自动化。该系统能够很好的检测出LCD显示面板中包括中文字符、数码管以及一些特殊字符和图形由于焊接加工问题导致的图形显示缺笔画或者不显示问题;此过程主要包括图像特征区域的定位、字符的分割、字符的缺陷识别判断;在特征区域定位中,首先采样获取LCD区域彩色图像直方图,然后利用反投影法获取大致特征区域,接着通过Canny边缘检测、概率直线检测确定特征区域的具体坐标;在字符分割的过程中,主要对预处理图像使用了水平、垂直投影等方法;最后利用模板匹配进行缺陷检测。此方法以DL/T 645-2007电表为检测对象,经过工厂实地图像取样,算法经代码实现,缺陷识别度高。A automatic testing system based on computer Vision is designed to realize the atttomation of smart meterquality test. It can effectively detect the defect of chinese characters mnixie tube ,alphabet and symbals on the LCDpanel,caused in automatic welding; Main algorithm ,of the System includes three parts：orientation ,of image fea- turearea, characters ;segmentation and itsdefect judgment,; Baok projection of color image histogram is used to lecate general LED area. Canny edge detection algorithm and line detectiem are applied to obtain theprecise coordinate -of featured area, and the horizontal projection and vertical projection are ：respectively nsed to split the symbols in the fea- tured area. At last, template matching is used to judge the existence of the defect.The system is implemented totest the meter DL/T645-2007, and good precision and high efficiency are ;acquired.

关 键 词：智能电表 缺陷检测 反投影 直线检测 图像分割 模板 

分 类 号：TM714[电气工程—电力系统及自动化]