Face Analysis : Identity vs

Due to several parameters, facial images present important visual variations, Here, we will focus on identity and expression. We will study the hypothesis of (image-based) automatic separability of identity from expressions. Indeed, sign language speakers using video need a tool able to offer anonymity to their sign productions, and such a tool has to modify the part of the facial image carrying identity features, without degrading the part which is expressive and needed for comprehension. We present here models of the face space, and how they can be used to anonymize facial images.