Mobile-platform for automatic fever screening system based on infrared forehead temperature

In this paper, automatic fever screening system is proposed and experimentally implemented using an IR camera and a mobile phone. Our system locates position of patients automatically using face detection algorithm on RGB image and obtains temperature from IR image at detected location. Advantages are fast, portable, non-contacting and simultaneously temperature measurement. Furthermore, face detection algorithm allows the system to track patient's face position. Hence, robust and non-contacting temperature measurement can be properly done even patients are not stand still. Our system has been field-tested to measure temperature and screen ill patients at a children medical clinic. In this experiment, the system is calibrated to measure temperature of patients at 1 meter away and gives an alarm sound when the measured temperature is above the desired setting threshold. According to experimental results, the correlation coefficient between temperature obtained from our system and commercial infrared forehead skin thermometer [2] is more than 0.80. In addition, our system achieves a 100% sensitivity and 70% specificity. Although our approach loses specificity, all fever patients are identified correctly. Thus, they are significantly correlated. Therefore, this system can reliably estimate body temperature of patients and can be used for effectively pre-screening fever patients.