ECOC-based training of neural networks for face recognition

Error correcting output codes, ECOC, is an output representation method capable of discovering some of the errors produced in classification tasks. This paper describes the application of ECOC to the training of feed forward neural networks, FFNN, for improving the overall accuracy of classification systems. Indeed, to improve the generalization of FFNN classifiers, this paper proposes an ECOC-Based training method for neural networks that use ECOC as the output representation, and adopts the traditional back-propagation algorithm, BP, to adjust weights of the network. Experimental results for face recognition problem on Yale database demonstrate the effectiveness of our method. With a rejection scheme defined by a simple robustness rate, high reliability is achieved in this application.

[1]  Jordi Vitrià,et al.  Discriminant ECOC: a heuristic method for application dependent design of error correcting output codes , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

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

[3]  Ching Y. Suen,et al.  Data-driven decomposition for multi-class classification , 2008, Pattern Recognit..

[4]  Giorgio Valentini,et al.  An Experimental Analysis of the Dependence Among Codeword Bit Errors in Ecoc Learning Machines , 2002, Neurocomputing.

[5]  Geoffrey E. Hinton,et al.  Adaptive Mixtures of Local Experts , 1991, Neural Computation.

[6]  Reza Ghaderi,et al.  Coding and decoding strategies for multi-class learning problems , 2003, Inf. Fusion.

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

[8]  Alex Pentland,et al.  Face recognition using eigenfaces , 1991, Proceedings. 1991 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[9]  David G. Stork,et al.  Pattern Classification , 1973 .

[10]  Avinash C. Kak,et al.  PCA versus LDA , 2001, IEEE Trans. Pattern Anal. Mach. Intell..

[11]  Marian Stewart Bartlett,et al.  Face recognition by independent component analysis , 2002, IEEE Trans. Neural Networks.

[12]  Ethem Alpaydin,et al.  Combining Linear Dichomotizers to Construct Nonlinear Polychotomizers , 1998 .

[13]  Carlos E. Thomaz,et al.  Design of radial basis function network as classifier in face recognition using eigenfaces , 1998, Proceedings 5th Brazilian Symposium on Neural Networks (Cat. No.98EX209).

[14]  Yoram Singer,et al.  Reducing Multiclass to Binary: A Unifying Approach for Margin Classifiers , 2000, J. Mach. Learn. Res..