A similarity-based method for the generalization of face recognition over pose and expression

Human observers are capable of recognizing a face seen only once before when confronted with it subsequently under different viewing conditions. We constructed a working computational model of such generalization from a single view, and tested it on a homogeneous database of face images obtained under tightly controlled viewing conditions. The model effectively constructs a view space for novel faces by interpolating view spaces of familiar ones. Its performance /spl sim/30% error rate in one out of 18 recognition, and 8% in one out of three discrimination-is encouraging, given that it reflects generalization from a single view/expression to a range of /spl plusmn/34/spl deg/ rotation in depth and to two additional expressions. For comparison, human subjects in the one out of three task involving only viewpoint changes exhibit a 3% error rate.

[1]  P. Alfeld.  Scattered data interpolation in three or more variables , 1989 .

[2]  Shimon Edelman,et al.  Similarity-based viewspace interpolation and the categorization of 3D objects , 1997 .

[3]  D. Shepard.  A two-dimensional interpolation function for irregularly-spaced data , 1968, ACM National Conference.

[4]  W. J. Gordon,et al.  Shepard’s method of “metric interpolation” to bivariate and multivariate interpolation , 1978 .

[5]  T. Poggio,et al.  Recognition and Structure from one 2D Model View: Observations on Prototypes, Object Classes and Symmetries , 1992 .

[6]  Ronen Basri,et al.  Recognition by Linear Combinations of Models , 1991, IEEE Trans. Pattern Anal. Mach. Intell..

[7]  S. Ullman,et al.  Generalization to Novel Images in Upright and Inverted Faces , 1993, Perception.

[8]  Alice J. O'Toole,et al.  Face Recognition Across Viewpoint , 1995 .

[9]  Shimon Edelman,et al.  Similarity, Connectionism, and the Problem of Representation in Vision , 1997, Neural Computation.

[10]  T. Poggio,et al.  A network that learns to recognize three-dimensional objects , 1990, Nature.

[11]  Tomaso Poggio,et al.  Image Representations for Visual Learning , 1996, Science.

[12]  Tomaso A. Poggio,et al.  Image Synthesis from a Single Example Image , 1996, ECCV.

[13]  Ronen Basri,et al.  Recognition by prototypes , 1993, Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

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