Rotation-invariant 3D reconstruction

Lighting variations and geometrical transformations in the image formation process can severely degrade the performance of many face recognition techniques. In previous work, Atick et al. (see Advance Imaging, vol.10, no.5, p.58-62) proposed a KL expansion-based technique for 3D facial surface reconstruction. Since a facial surface is intrinsic to the face and independent to lighting conditions, this leads to face recognition algorithms insensitive to lighting variations. Atick et al.´s technique, however, is sensitive to 3D affine transformations. In this paper, we describe a novel technique that makes face surface reconstruction rotation-invariant. Specifically, rotation transformations are described by parameters that are estimated during the reconstruction process, along with the KL expansion coefficients. Experimental results indicate this technique can significantly improve recognition performance. Finally, our approach extends naturally to all other affine transformations, including translation and scaling