Rotation invariant face recognition survey

Abstract

Face recognition is one of the most active research topics in pattern recognition and computer vision due to its potential applications in access control, authentication systems, law enforcement, human-machine interfaces, etc. Most of the developed face recognition techniques are only capable of recognizing frontal views of faces, assuming that the person was looking straight into the camera. The frontal face recognition method is suitable for certain applications where the client poses consistently the same way from session to session. However, a user might not pose to a camera for the purpose of being recognized, perhaps not even knowing that a face image is being captured. In these cases it is important for the system to handle faces with in plane and in depth rotations. Rotation invariant face recognition is an important area of research because of its many real-world applications, especially in creating a more robust recognition system for commercial and government technologies. In this survey paper, an overview of the available rotation invariant face recognition algorithms is provided, including both feature-based and holistic approaches, and the potential for future work is discussed.