Marian Bartlett, Terrence J. Sejnowski
We have explored two approaches to recogmzmg faces across changes in pose. First, we developed a representation of face images based on independent component analysis (ICA) and compared it to a principal component analysis (PCA) representation for face recognition. The ICA basis vectors for this data set were more spatially local than the PCA basis vectors and the ICA representa(cid:173) tion had greater invariance to changes in pose. Second, we present a model for the development of viewpoint invariant responses to faces from visual experience in a biological system. The temporal continuity of natural visual experience was incorporated into an attractor network model by Hebbian learning following a lowpass temporal filter on unit activities. When combined with the tem(cid:173) poral filter, a basic Hebbian update rule became a generalization of Griniasty et al. (1993), which associates temporally proximal input patterns into basins of attraction. The system acquired rep(cid:173) resentations of faces that were largely independent of pose.
Independent component representations of faces
Important advances in face recognition have employed forms of principal compo(cid:173) nent analysis, which considers only second-order moments of the input (Cottrell & Metcalfe, 1991; Turk & Pentland 1991). Independent component analysis (ICA) is a generalization of principal component analysis (PCA), which decorrelates the higher-order moments of the input (Comon, 1994). In a task such as face recogni(cid:173) tion, much of the important information is contained in the high-order statistics of the images. A representational basis in which the high-order statistics are decorre(cid:173) lated may be more powerful for face recognition than one in which only the second order statistics are decorrelated, as in PCA representations. We compared an ICA(cid:173) based representation to a PCA-based representation for recognizing faces across changes in pose.
M. S. Bartlett and T. J. Sejnowski