面向指针式仪表读数的图像检测与识别方法研究进展  

Survey of Image Detection and Recognition Methods for Pointer Meter

作　　者：毛银杰 于广平 郭清达[1] 刘坚 MAO Yinjie;YU Guangping;GUO Qingda;LIU Jian(Guangzhou Industrial Intelligence Research Institute,Guangzhou 511458,China;School of Chemical Process Automation,Shenyang University of Technology,Shenyang 110016,China;Shenyang Institute of Automation Chinese Academy of Sciences,Shenyang 110016,China)

机构地区：[1]广州工业智能研究院,广州511458 [2]沈阳工业大学化工过程自动化学院,沈阳110016 [3]中国科学院沈阳自动化研究所,沈阳110016

出　　处：《自动化与仪表》2025年第2期6-9,38,共5页Automation & Instrumentation

基　　金：国家自然科学基金项目(61890935);广东省国际科技合作项目(2023A0505050090)。

摘　　要：随着工业领域智能化和自动化的发展,指针式仪表检测与读数识别成为了一个备受关注的研究领域,该文综述了近些年指针式仪表检测与读数识别方面的研究进展。首先,介绍了指针式仪表读数的作用及计算机视觉应用于指针式仪表读数识别方向。随后,总结了指针式仪表读数识别方法,详细地阐述了国外和国内学者的主要研究。进一步介绍了图像处理与深度学习相结合的5个步骤,即图像预处理、仪表盘检测、仪表指针与刻度检测、仪表盘数字检测与识别和仪表数值识别的研究现状与方法对比。绍了指针式仪表的检测与识别框架内容及技术;然后对指针式仪表的检测与识别框架内容及技术进行阐述与比较;最后对基于机器视觉的指针式仪表检测与识别进行了总结与展望。With the development of intelligence and automation in the industrial field,detection and recognition methods for point meter have become a research field that has attracted much attention,and the paper reviews the research progress of detection and recognition methods for pointer meter in recent years.Firstly,the role and significance of pointer meter,and pointer meter recognition using computer are introduced.Then,summarizes the pointer meter reading recognition method,in detail elaborated the foreign and domestic scholars mainly study.Furthermore,the five steps of the combination of image processing and deep learning are introduced,which are image preprocessing,meter panel detection,meter pointer and scale detection,meter panel digital detection and recognition,and meter numerical recognition research status and method comparison.

关 键 词：机器视觉 指针式仪表 图像处理 深度学习 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]