Blood Perfusion Models for Infrared Face Recognition

Infrared (IR) technology has traditionally been applied to military use and remote sensing. During the last two decades, the cost of IR cameras (especially uncooled imagers) has been significantly reduced with the development of CCD technology, and therefore civil applications have increased constantly due to its unique features. One of such applications is IR face recognition (Prokoski et al., 1992, Prokoski, 2000, Kong et al., 2005). The fundamentals behind it are, as indicated by Kong et al (Kong et al., 2005) that IR images are independent of external illumination. While visible images represent the reflectance information of the face surface, IR face images contain more fundamental information about faces themselves, such as anatomical information (Prokoski, et al., 1992, Prokoski, 2000); the thermal characteristics of faces with variations in facial expression and make-up remain nearly invariant (Socolinsky & Selinger, 2002) and the tasks of face detection, localization, and segmentation are relatively easier and more reliable than those in visible images (Kong et al., 2005). It has been pointed by Prokoski et al. (Prokoski et al., 1992) that humans are homoiotherm and hence capable of maintaining constant temperature under different surroundings. The thermal images collected over 20 years have demonstrated that the thermal measurements of individuals are highly repeatable under the same conditions. Furthermore, as discussed by Prokoski (Prokoski, 2000), a facial thermal pattern is determined by the vascular structure of each face, which is irreproducible and unique. Based on the assumption that facial thermal patterns are determined by blood vessels transporting warm blood, Prokoski tried to extract the blood vessel minutiae (Prokoski, 2001) or vascular network (Buddharaju et al., 2004, Buddharaju et al., 2005) as the facial features for recognition. The basic idea is to extract such features using image segmentation. It has been indicated by Guyton & Hall (Guyton & Hall, 1996) that the average diameter of blood vessels is around 10~15μm, which is too small to be detected by current IR cameras (limited by the spatial resolution); the skin directly above a blood vessel is on average 0.1°C warmer than the adjacent skin, which is beyond the thermal accuracy of current IR cameras. The methods using image segmentation in (Prokoski, 2001, Buddharaju et al., 2004, Buddharaju et al., 2005) are heuristic, and it still remains a big challenge to capture the pattern of blood vessels on each face. On the other hand, the phenomenon of “homoiotherm” due to human temperature regulation has led to the direct use of thermograms for recognition (Wilder et al., 1996, O pe n A cc es s D at ab as e w w w .in te ch w eb .o rg