基于改进Hough变换和BP网络的指针仪表识别  

Pointer instrument recognition based on BP network and improved Hough transform

作　　者：朱海霞 

机构地区：[1]大庆油田公司电力集团,黑龙江大庆163000

出　　处：《电测与仪表》2015年第5期11-14,共4页Electrical Measurement & Instrumentation

摘　　要：指针仪表示数的视觉识别,对于提高电气、机械、汽车等工业领域的生产效率具有重要意义。采用Hough变换方法完成指针直线特征的识别,进而在表盘圆形特征的识别过程中对Hough变换方法进行了改进,通过减少累加像素数目结合灰度中心法来提高原性特征定位的效率和精度。在字符识别阶段,构建了一个三层次的BP神经网络。实验结果表明,该方法对于Hough变换的改进措施达到了预期效果,BP神经网络也实现了字符特征的准确识别。Visual identification of pointer instrument number has important significance to improve the production effi -ciency of the electrical , mechanical and automotive industry .In this paper , Hough transformation method was used in recognition of linear feature of pointer , and then Hough transform was improved during the process of dial circular fea-ture identification .The efficiency and precision are improved by reducing the accumulated number of pixels and com-bining the gray center method .In the character recognition stage , BP neural network is built with a three level struc-ture.Experimental results show that , this method can achieve the expected effect for improving measures of Hough transform, and accurate recognition of characters can be obtained by using BP neural network .

关 键 词：指针仪表 字符识别 HOUGH变换 BP神经网络 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]