A Continuous Learning for Solving a Face Recognition Problem

We propose a Hybrid System for dynamic environments, where a "Multiple Neural Networks" system works with Bayes Rule to solve the face recognition problem. One or more neural nets may no longer be able to properly operate, due to partial changes in some of the characteristics of the individuals. For this purpose, we assume that each expert network has a reliability factor that can be dynamically re-evaluated on the ground of the global recognition operated by the overall group. Since the net’s degree of reliability is defined as the probability that the net is giving the desired output, in case of conflicts between the outputs of the various nets the re-evaluation of their degrees of reliability can be simply performed on the basis of the Bayes Rule. The new vector of reliability will be used to establish who is the conflict winner, making the final choice (the name of subject), by applying two algorithms, the “Inclusion based weighted” and the “Weighted” one over all the maximally consistent subsets of the global outcome. Moreover the network disagreed with the group and specialized to recognize the changed characteristic of the subject will be retrained and then forced to correctly recognize the subject. Then the system is subjected to continuous learning.

[1]  Zhi-Hua Zhou,et al.  Recognizing partially occluded, expression variant faces from single training image per person with SOM and soft k-NN ensemble , 2005, IEEE Transactions on Neural Networks.

[2]  Farooq Azam,et al.  Biologically Inspired Modular Neural Networks , 2000 .

[3]  David Zhang,et al.  Modular Neural Networks and Their Applications in Biometrics , 2007, Trends in Neural Computation.

[4]  Aldo Franco Dragoni,et al.  Belief revision: from theory to practice , 1997, The Knowledge Engineering Review.

[5]  Eduardo L. Fermé,et al.  Belief Revision , 2007, Inteligencia Artif..

[6]  Harry Wechsler,et al.  The FERET database and evaluation procedure for face-recognition algorithms , 1998, Image Vis. Comput..

[7]  Yong Deng,et al.  Evaluating Sensor Reliability in Classification Problems Based on Evidence Theory , 2006, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[8]  Gerhard Brewka,et al.  Preferred Subtheories: An Extended Logical Framework for Default Reasoning , 1989, IJCAI.

[9]  Zhi-Hua Zhou,et al.  Face recognition from a single image per person: A survey , 2006, Pattern Recognit..

[10]  M. W. Shields,et al.  A theoretical framework for multiple neural network systems , 2008, Neurocomputing.

[11]  Amanda J. C. Sharkey,et al.  Modularity, Combining and Artificial Neural Nets , 1997, Connect. Sci..

[12]  Azriel Rosenfeld,et al.  Face recognition: A literature survey , 2003, CSUR.

[13]  Teuvo Kohonen,et al.  Learning vector quantization , 1998 .

[14]  A. A. El-Harby,et al.  Face Recognition: A Literature Review , 2008 .

[15]  T. Kohonen,et al.  Appendix 2.4 Stopping Rule 2.3 Fine Tuning Using the Basic Lvq1 or Lvq2.1 Lvq Pak: a Program Package for the Correct Application of Learning Vector Quantization Algorithms , 1992 .

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

[17]  M. V. Velzen,et al.  Self-organizing maps , 2007 .