基于图像处理的电能表数字识别方法  

Digital Recognition Method for Electricity Meter Based on Image Processing

作　　者：李明[1] 丁琦 江洋[1] 彭筱筱[1] 傅时胜 Li Ming;Ding Qi;Jiang Yang;Peng Xiao-xiao;Fu Shi-sheng(Zhejiang Province Institute of Metrology,Zhejiang Hangzhou 310018;China JiLiang University,Zhejiang Hangzhou 310000)

机构地区：[1]浙江省计量科学研究院,浙江杭州310018 [2]中国计量大学,浙江杭州310000

出　　处：《电子质量》2018年第3期41-45,共5页Electronics Quality

基　　金：浙江省质监局科研项目"电能表电磁兼容抗扰度试验自动检测系统研发(20160216)

摘　　要：针对电能表检测试验中,由于人工读数产生的效率低下和长期工作容易出错的问题,提出了一种基于数字图像识别的电能表数字识别方法。该方法首先对初始的电能表图像采用高斯滤波,二值化进行图像预处理,然后用连通域分割的方法进行数字字符分割,最后采用BP神经网络进行数字识别。试验结果表明,该方法识别准确率高,行之有效。The digital recognition algorithm of the electricity meter is proposed in order to solve the problem of low efficiency and easy to make mistakes in the electricity meter test.The image is preprocessed by Gaussian filtering and binarization,and the digital character segmentation is performed by the method of connection domain segmentation,and the BP-neural network is used for digital recognition.The experimental results show that this method is an efficient method which has high recognition rate.

关 键 词：电能表 数字识别 图像处理 BP神经网络 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]