Face recognition under varying pose: The role of texture and shape

Although remarkably robust, face recognition is not perfectly invariant to pose and viewpoint changes. It has been known since long, that the profile as well as the full-face view result in a recognition performance that is worse than a view from within that range. However, only few data exists that investigate this phenomenon in detail. This work intends to provide such data using a high angular resolution and a large range of poses. Since there are inconsistencies in the literature concerning these issues, we emphasize on the different role of the learning view and the testing view in the recognition experiment and on the role of information contained in the texture and in the shape of a face. Our stimuli were generated from laser-scanned head models and contained either the natural texture or only Lambertian shading and no texture. The results of our same/different face recognition experiments are: 1. Only the learning view but not the testing view effects the recognition performance. 2. For the textured faces the optimal learning view is closer to the full-face view than for the shaded faces. 3. For the shaded faces, we find a significantly better recognition performance for the symmetric view. The results can be interpreted in terms of different strategies to recover invariants from texture and from shading