On the use of dynamic features in face biometrics: recent advances and challenges

The way a person is moving his/her head and facial parts (such as the movements of the mouth when a person is talking) defines so called facial dynamics and characterizes personal behaviors. An emerging direction in automatic face analysis consists of also using such dynamic cues, in addition to facial structure, in order to enhance the performance of static image based methods. This is inspired by psychophysical and neural studies indicating that behavioral characteristics do also provide valuable information to face analysis in the human visual system. This survey article presents the motivations, reviews the recent developments and discusses several other important issues related to the use of facial dynamics in computer vision. As a case study of using facial dynamics, two LBP based baseline methods are considered and experimental results in different face-related problems, including face recognition, gender recognition, age estimation and ethnicity classification are reported and discussed. Furthermore, remaining challenges are highlighted and some promising directions are pointed out.