Open AccessScale recognition of non-electronic thermometers based on image features
Author(s) -
Yao Si,
Miao Guo,
Jingmin Gao,
Yue Li
Publication year - 2021
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1971/1/012003
Subject(s) - thermometer , reading (process) , artificial intelligence , pixel , computer science , scale (ratio) , computer vision , international temperature scale of 1990 , statistics , mathematics , calibration , cartography , geography , physics , quantum mechanics , political science , law
At present, in terms of clinical temperature measurement in China, most hospitals use traditional mercury thermometers to obtain patient temperature data through human readings and records. In order to improve the work efficiency of medical staff and reduce the frequency of their contact with patients, machine vision is adopted. A scale recognition method of non-electronic thermometer based on image features is proposed. The reading data of clinical thermometers is calculated through pixels. The automatic reading record of the clinical thermometer is realized, and the relative error does not exceed 0.25% in the temperature range of 35.5 to 37.5°C, which has certain practical significance for the research in the field of intelligent medical treatment.