基于机器视觉的机械水表读数识别系统设计与实现  

Mechanical Water Meter Reading Recognition System Based on Machine Vision

作　　者：秦平 张圆明 邬嘉敏 Qin Ping

机构地区：[1]广州能源检测研究院,广东广州511447

出　　处：《工业控制计算机》2024年第1期40-41,共2页Industrial Control Computer

基　　金：广州市市场监督管理局科技项目:基于激光传感器的DN(125-200)机械式水表智能检定装置研制(2022kj24);基于图像识别的DN(15-25)机械式水表智能检定装置研制(2023KJ21)。

摘　　要：目前,机械式水表检定装置仍然大多依靠人工操作进行检定,存在检定过程耗时长、人力成本高、效率低下的问题。为了提高机械式水表检定的效率,设计了一种基于机器视觉的机械水表读数识别系统。该系统通过读取实时视频流获取机械式水表的图片,采用卷积神经网络构建水表读数识别系统。该系统根据视频流获取的水表图片,识别出机械式水表上的读数。最后,实验验证了所提出系统的有效性。At present,mechanical water meter verification devices still rely on manual operation.There are many problems in the verification process,such as long time consuming,high labor cost and low efficiency.In order to improve the efficiency of mechanical water meter verification,a reading recognition system based on machine vision is designed in this paper.The proposed system obtains the picture of the mechanical water meter by reading the real-time video stream,and then adopts the convolutional neural network to build the reading recognition system of the water meter.The proposed system identifies the reading of the mechanical water meter according to the water meter picture obtained by the video stream.Finally,the effectiveness of the proposed system is verified by experiments.

关 键 词：机械式水表 卷积神经网络 机器视觉 

分 类 号：TU821.2[建筑科学] TP391.41[自动化与计算机技术—计算机应用技术]