Face distinctiveness in recognition across viewpoint: an analysis of the statistical structure of face spaces

We present an analysis of the effects of face distinctiveness on the performance of a computational model of recognition over viewpoint change. In the first stage of the model, the face stimulus is normalized by being mapped to an arbitrary standard view. In the second stage, the normalized stimulus is mapped into a "face space" spanned by a number of reference faces, and is classified as familiar or unfamiliar We carried out experiments employing a parametrically generated family of face stimuli that vary in distinctiveness. The experiments show that while the "view-mapping" process operates more accurately for typical versus distinctive faces, the base level distinctiveness of the faces is preserved in the face space coding. These data provide insight into how the psychophysically well-established inverse relationship between the typically and recognizability of faces might operate for recognition across changes in viewpoint.

[1]  Shimon Edelman,et al.  Learning to Recognize Faces from Examples , 1992, ECCV.

[2]  S. Edelman.  Representation of Similarity in 3D Object Discrimination , 1995 .

[3]  I. Borg.  Multidimensional similarity structure analysis , 1987 .

[4]  M. Turk,et al.  Eigenfaces for Recognition , 1991, Journal of Cognitive Neuroscience.

[5]  Shimon Edelman,et al.  Receptive field spaces and class-based generalization from a single view in face recognition , 1995 .

[6]  D J Field,et al.  Relations between the statistics of natural images and the response properties of cortical cells. , 1987, Journal of the Optical Society of America. A, Optics and image science.

[7]  D. Ruderman.  The statistics of natural images , 1994 .

[8]  Alex Pentland,et al.  Human Face Recognition and the Face Image Set's Topology , 1994 .

[9]  V. Bruce,et al.  The Effects of Distinctiveness in Recognising and Classifying Faces , 1986, Perception.

[10]  A. O'Toole,et al.  Structural aspects of face recognition and the other-race effect , 1994, Memory & cognition.

[11]  EdelmanFlorin CutzuSharon Duvdevani-BarDept.  Similarity to reference shapes as a basis for shaperepresentationShimon , 1996 .

[12]  Shimon Edelman,et al.  Representation of Similarity in Three-Dimensional Object Discrimination , 1995, Neural Computation.

[13]  Joseph J Atick,et al.  The vocabulary of shape: principal shapes for probing perception and neural response. , 1996, Network.

[14]  Shimon Edelman,et al.  Representation of similarity as a goal of early visual processing , 1995 .

[15]  A. O'Toole,et al.  Sex Classification is Better with Three-Dimensional Head Structure Than with Image Intensity Information , 1997, Perception.

[16]  S Hollander,et al.  Recognition memory for typical and unusual faces. , 1979, Journal of experimental psychology. Human learning and memory.

[17]  T Poggio,et al.  Regularization Algorithms for Learning That Are Equivalent to Multilayer Networks , 1990, Science.