Mercury Thermometer Temperature Value Visual Estimation Dataset

The current medical industry faces challenges in accuracy and efficiency in temperature monitoring; traditional manual reading of mercury thermometers is prone to errors and slow processing speed. Existing automated solutions mostly focus on electronic thermometers, overlooking scenarios involving mercury thermometers. This dataset aims to achieve automated estimation of temperature values on mercury thermometers using visual technology, meeting the needs for fast and accurate temperature monitoring. The dataset includes images of mercury thermometers taken under various conditions, captured by smartphone cameras and professional cameras, ensuring image quality. To ensure data quality, we adopted multiple rounds of annotation and consistency checks, with all annotations reviewed by medical experts to ensure accuracy and reliability. Data is stored in JPG format and organized in a standard folder structure for easy processing and access.