Categorization by Learning and Combining Object Parts

We describe an algorithm for automatically learning discriminative components of objects with SVM classifiers. It is based on growing image parts by minimizing theoretical bounds on the error probability of an SVM. Component-based face classifiers are then combined in a second stage to yield a hierarchical SVM classifier. Experimental results in face classification show considerable robustness against rotations in depth and suggest performance at significantly better level than other face detection systems. Novel aspects of our approach are: a) an algorithm to learn component-based classification experts and their combination, b) the use of 3-D morphable models for training, and c) a maximum operation on the output of each component classifier which may be relevant for biological models of visual recognition.

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

[2]  R. Vaillant,et al.  An original approach for the localization of objects in images , 1993 .

[3]  R. Vaillant,et al.  Original approach for the localisation of objects in images , 1994 .

[4]  Michael C. Burl,et al.  Finding faces in cluttered scenes using random labeled graph matching , 1995, Proceedings of IEEE International Conference on Computer Vision.

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

[6]  Vladimir Vapnik,et al.  Statistical learning theory , 1998 .

[7]  Takeo Kanade,et al.  Rotation Invariant Neural Network-Based Face Detection , 1998, Proceedings. 1998 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No.98CB36231).

[8]  Takeo Kanade,et al.  Probabilistic modeling of local appearance and spatial relationships for object recognition , 1998, Proceedings. 1998 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No.98CB36231).

[9]  Paul A. Viola,et al.  A cluster-based statistical model for object detection , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[10]  T. Poggio,et al.  Hierarchical models of object recognition in cortex , 1999, Nature Neuroscience.

[11]  Joachim M. Buhmann,et al.  Feature selection for support vector machines , 2000, Proceedings 15th International Conference on Pattern Recognition. ICPR-2000.

[12]  Takeo Kanade,et al.  A statistical method for 3D object detection applied to faces and cars , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).

[13]  Pietro Perona,et al.  Towards automatic discovery of object categories , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).

[14]  Massimiliano Pontil,et al.  Face Detection in Still Gray Images , 2000 .

[15]  Shimon Ullman,et al.  Object Classification Using a Fragment-Based Representation , 2000, Biologically Motivated Computer Vision.

[16]  Sayan Mukherjee,et al.  Feature reduction and hierarchy of classifiers for fast object detection in video images , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[17]  Tomaso A. Poggio,et al.  Example-Based Object Detection in Images by Components , 2001, IEEE Trans. Pattern Anal. Mach. Intell..

[18]  Tomaso A. Poggio,et al.  Face recognition with support vector machines: global versus component-based approach , 2001, Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001.

[19]  Terence Sim,et al.  The CMU Pose, Illumination, and Expression (PIE) database , 2002, Proceedings of Fifth IEEE International Conference on Automatic Face Gesture Recognition.