Geometric Analysis of 3D Facial Image Data: A Survey

Background: 3D facial image data has become an important data source in many biometric computing applications due to the increasing availability of 3D surface image collection technologies. Objective: In this survey paper, we aim to review recent advances in 3D geometry-based techniques for facial image analysis and their roles in several critical applications. Methods: We first study the 3D facial landmark detection techniques which are often required for many facial data analysis applications. We then review the literature related to several critical 3D facial image based applications, including face recognition, medical diagnosis, and 3D face reconstruction. Conclusion: Our review shows that while 3D facial image data has been widely used as an important biometric data source, critical solutions still need to be developed in applications that require substantial understanding of the underlying anatomic and geometric structures of human faces.