Manifold analysis of facial gestures for face recognition

Abstract

The particulars of facial gestures are frequently used to qualitatively define and characterize faces. It is not merely the skin motion induced by such gestures, but the appearance of the skin changes that provides this information. For gestures and their appearance to be utilized as a biometric, it is critical that a robust model be established. For this purpose we are exploring gesture manifolds.This paper describes work underway toward evaluation of the manifold representation of facial gestures both as a biometric, and as a means to extract biometric information. Details of the current acquisition system are discussed with the motivating principles behind the device. Preliminary observations are presented to motivate manifold analysis followed by an exposition of the experiments underway that will be used to validate the model.