Face Tracking based on Temperature Distribution of Thermal Images for Real-Time Psychophysiological States Evaluation using Facial Skin Temperature

Abstract

Psychophysiological states have been evaluated using facial skin temperature, measured by infrared thermography. However, it is necessary to extract facial skin temperature manually, which is a technical problem in thermal image analysis. The objective of this study is to establish a technique for face tracking on thermal images. In this study, face tracking on thermal images was attempted using background subtraction and temporal analysis. As a result, the face region could be tracked with high precision, except during left-to-right horizontal movement.