Example-Based Learning for View-Based Human Face Detection

We present an example-based learning approach for locating vertical frontal views of human faces in complex scenes. The technique models the distribution of human face patterns by means of a few view-based "face" and "nonface" model clusters. At each image location, a difference feature vector is computed between the local image pattern and the distribution-based model. A trained classifier determines, based on the difference feature vector measurements, whether or not a human face exists at the current image location. We show empirically that the distance metric we adopt for computing difference feature vectors, and the "nonface" clusters we include in our distribution-based model, are both critical for the success of our system.

[1]  Richard O. Duda,et al.  Pattern classification and scene analysis , 1974, A Wiley-Interscience publication.

[2]  Peter E. Hart,et al.  Pattern classification and scene analysis , 1974, A Wiley-Interscience publication.

[3]  David Casasent,et al.  Principal-Component Imagery For Statistical Pattern Recognition Correlators , 1982 .

[4]  W. Grimson,et al.  Model-Based Recognition and Localization from Sparse Range or Tactile Data , 1984 .

[5]  Tomas Lozano-Perez,et al.  Model-Based Recognition and Localization from Sparse Range Data , 1986 .

[6]  Azriel Rosenfeld,et al.  Techniques for 3-D machine perception , 1986 .

[7]  L Sirovich,et al.  Low-dimensional Procedure for the Characterization of Human Faces , 1986 .

[8]  Alan L. Yuille,et al.  Feature extraction from faces using deformable templates , 1989, Proceedings CVPR '89: IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[9]  A. Dale Magoun,et al.  Decision, estimation and classification , 1989 .

[10]  Lawrence Sirovich,et al.  Application of the Karhunen-Loeve Procedure for the Characterization of Human Faces , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[11]  M. Bichsel.  Strategies of robust object recognition for the automatic identification of human faces , 1991 .

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

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

[14]  Roberto Brunelli,et al.  Face Recognition: Features Versus Templates , 1993, IEEE Trans. Pattern Anal. Mach. Intell..

[15]  Tomaso Poggio,et al.  Example Based Image Analysis and Synthesis , 1993 .

[16]  Geoffrey E. Hinton,et al.  Recognizing Handwritten Digits Using Mixtures of Linear Models , 1994, NIPS.

[17]  David Beymer,et al.  Face recognition under varying pose , 1994, 1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[18]  Arthur V. Forman,et al.  Multi-class SAR ATR using shift-invariant correlation filters , 1994, Pattern Recognition.

[19]  Alex Pentland,et al.  View-based and modular eigenspaces for face recognition , 1994, 1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[20]  P. Perona,et al.  A Trainable Tool for Finding Small volcanoes in SAR Imagery of Venus , 1994 .

[21]  Kah Kay Sung,et al.  Learning and example selection for object and pattern detection , 1995 .

[22]  Tomaso A. Poggio,et al.  Pedestrian detection using wavelet templates , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.