Wang Pingjiang

Infrared Human Face Auto Locating Based on SVM and A Smart Thermal Biometrics System

The SARS epidemic resulted in the introduction of IR thermal camera for non-voluntary screening on human face for fever symptoms. However, two major problems emerged. One is the temperature measurement precision, which is not adequate enough. The other is the poor automatic ability. This paper analyses the importance and deals with the second automation problem. We discuss the inherent consistency of SVM with the pattern recognition in infrared image. A smart biometrics system that automatically detects human face in infrared video and performs temperature measurement is implemented. The potential for illumination invariant face recognition using thermal IR imagery is fully utilized. This potentiality is approved by the result of infrared human face detection experiment based on C-SVM