On the Pose Invariance Capability for Face Recognition in Human Beings

Automatic face recognition is becoming increasingly important in the contexts of surveillance, credit card fraud detection, assistive devices for visual impaired, etc. A number of face recognition algorithms have been proposed in the literature. Though most of the algorithms achieve good recognition rates with the frontal views of faces, they fail when the pose of the face in the database and that in the query are different. We believe that an important question to be answered in this context is whether human visual system could achieve pose invariance. In this paper, we describe an experimental method that was used to answer the above question. We also show that in the experiment conducted humans were not hugely successful in doing pose invariant recognition.