Face Identification and Verification via ECOC

We propose a novel approach to face identification and verification based on the Error Correcting Output Coding (ECOC) classifier design concept. In the training phase the client set is repeatedly divided into two ECOC specified sub-sets (super-classes) to train a set of binary classifiers. The output of the classifiers defines the ECOC feature space, in which it is easier to separate transformed patterns representing clients and impostors. As a matching score in this space we propose the average first order Minkowski distance between the probe and gallery images. The proposed method exhibits superior verification performance on the well known XM2VTS data set as compared with previously reported results.

[1]  Josef Kittler,et al.  Pattern recognition : a statistical approach , 1982 .

[2]  Morton Nadler,et al.  Pattern recognition engineering , 1993 .

[3]  Thomas G. Dietterich,et al.  Solving Multiclass Learning Problems via Error-Correcting Output Codes , 1994, J. Artif. Intell. Res..

[4]  E B Kong,et al.  PROBILITY ESTIMATION VIA ERROR CORRECTING OUTPUT CODING , 1997 .

[5]  Reza Ghaderi,et al.  Circular ECOC. A theoretical and experimental analysis , 2000, Proceedings 15th International Conference on Pattern Recognition. ICPR-2000.

[6]  Jiri Matas,et al.  Fast face localisation and verification , 1999, Image Vis. Comput..

[7]  Juergen Luettin,et al.  Evaluation Protocol for the extended M2VTS Database (XM2VTSDB) , 1998 .

[8]  Gareth M. James,et al.  Majority vote classifiers: theory and applications , 1998 .

[9]  Andy Harter,et al.  Parameterisation of a stochastic model for human face identification , 1994, Proceedings of 1994 IEEE Workshop on Applications of Computer Vision.

[10]  David B. Skalak,et al.  Prototype Selection for Composite Nearest Neighbor Classifiers , 1995 .

[11]  Jiri Matas,et al.  XM2VTSDB: The Extended M2VTS Database , 1999 .

[12]  Reza Ghaderi,et al.  Binary codes for multiclass decision combining , 2000, SPIE Defense + Commercial Sensing.

[13]  Terrence J. Sejnowski,et al.  Parallel Networks that Learn to Pronounce English Text , 1987, Complex Syst..

[14]  CodingEun Bae Kong.  Probability Estimation via Error-Correcting Output , 1997 .

[15]  David J. Kriegman,et al.  Eigenfaces vs. Fisherfaces: Recognition Using Class Specific Linear Projection , 1996, ECCV.

[16]  Yingnan Philip Li.  Linear Discriminant Analysis and its Application to Face Identification. , 2000 .

[17]  W. W. Peterson,et al.  Error-Correcting Codes. , 1962 .

[18]  L Sirovich,et al.  Low-dimensional procedure for the characterization of human faces. , 1987, Journal of the Optical Society of America. A, Optics and image science.

[19]  Thomas G. Dietterich,et al.  Error-Correcting Output Codes: A General Method for Improving Multiclass Inductive Learning Programs , 1991, AAAI.

[20]  Jiri Matas,et al.  On Matching Scores for LDA-based Face Verification , 2000, BMVC.

[21]  Jiri Matas,et al.  Audio-visual person verification , 1999, Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149).

[22]  Hong Yan,et al.  Comparison of face verification results on the XM2VTFS database , 2000, Proceedings 15th International Conference on Pattern Recognition. ICPR-2000.