玻璃体温计自动检定图像识别技术研究  

Research on image recognition technology for automatic verification of glass thermometer

作　　者：王志远 王语瑄 Wang Zhiyuan;Wang Yuxuan(Zhengzhou Product Quality Inspecting and Testing Center,Zhengzhou 450000,China;Macao University of Science and Technology,Macao 999078,China)

机构地区：[1]郑州市产品质量检验检测中心,郑州450000 [2]澳门科技大学,中国澳门999078

出　　处：《现代仪器与医疗》2025年第1期22-26,共5页Modern Instruments & Medical Treatment

基　　金：河南省市场监督管理局科技计划项目(HNSCJGK2024110)。

摘　　要：目的 法定计量技术机构需要依据计量检定规程《JJG111-2019玻璃体温计》进行玻璃体温计的强检工作,工作量巨大,因此,急需对玻璃体温计自动化检定进行相关研究。方法 根据近年来人工智能在图像识别中相关研究,基于系统设计、图像采集及算法、现有图像识别技术优缺点构建玻璃体温计自动识别系统。结果 实现玻璃体温计快速准确的自动读数,模型识别准确率高达0.9640。结论 采用图像识别自动化检定,解决了体温计传统人工检定方式存在诸多问题,极大提高检定效率与精度。Objective The legal metrological technical institutions need to carry out the inspection work of glass thermometer according to the metrological verification regulation‘JJG111-2019 Glass thermometer’,and the workload is huge,so,it is urgent to study the automatic verification of glass thermometer.Methods According to the related researches of artificial intelligence in image recognition in recent years,the automatic recognition system of vitreous thermometer was constructed based on system design,image acquisition and algorithm,advantages and disadvantages of existing image recognition technology.Results The fast and accurate automatic reading of the glass thermometer is realized,and the model recognition accuracy was as high as 0.9640.Conclusion The automatic verification with image recognition solved many problems in the traditional manual verification of thermometers,and greatly improved the verification efficiency and accuracy.

关 键 词：玻璃体温计 自动检定 图像识别 算法优化 系统设计 图像特征提取 

分 类 号：TH77[机械工程—仪器科学与技术]