Physiological face recognition is coming of age

Pradeep Buddharaju, Ioannis T. Pavlidis

Abstract: The previous work of the authors has shown that physiological information on the face can be extracted from thermal infrared imagery and can be used as a biometric. Although, that work has proved the feasibility of physiological face recognition, the experimental results revealed high false acceptance rates due to methodological weaknesses in the feature extraction and matching algorithms. This paper, presents a new methodology that corrects these problems and yields high recognition rates. Specifically, a post-processing algorithm removes fake vascular contours, which degraded performance. Also, a new vascular network matching algorithm copes with deformations caused by varying facial pose and expressions. First, it estimates the facial pose in the test image and then calculates the deformation of the vascular network in the database image. Next, it registers test and database vascular networks using the dual bootstrap iterative closest point (ICP) matching algorithm. Finally, it computes a matching score between the vascular networks, which is a function of overlapping vessel pixels. Extensive experiments have been undertaken to test the new method. The results highlight its superiority.