An RCE-based Associative Memory with Application to Human Face Recognition

Many models of neural network-based associative memory have been proposed and studied. However, most of these models do not have a rejection mechanism and hence are not practical for many real-world associative memory problems. For example, in human face recognition, we are given a database of face images and the identity of each image. Given an input image, the task is to associate when appropriate the image with the corresponding name of the person in the database. However, the input image may be that of a stranger. In this case, the system should reject the input. In this paper, we propose a practical associative memory model that has a rejection mechanism. The structure of the model is based on the restricted Coulomb energy (RCE) network. The capacity of the proposed memory is desibed by two measures: the ability of the system to correctly identify known individuals, and the ability of the system to reject individuals who are not in the database. Experimental results are given which show how the performance of the system varies as the size of the database increases up to 1000 individuals.

[1]  Tony R. Martinez,et al.  Improved Heterogeneous Distance Functions , 1996, J. Artif. Intell. Res..

[2]  Kenji Shibata,et al.  An adaptive neural network: Application to character recognition on x-ray films , 1996, Neural Networks.

[3]  M.H. Hassoun,et al.  Fundamentals of Artificial Neural Networks , 1996, Proceedings of the IEEE.

[4]  Mohamad H. Hassoun,et al.  Construction and Analysis of a Database of Face Images which Requires Minimal Preprocessing , 2000 .

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

[6]  Mohamad H. Hassoun,et al.  Generalizations of the Hamming Associative Memory , 2004, Neural Processing Letters.

[7]  Norbert Krüger,et al.  Face Recognition by Elastic Bunch Graph Matching , 1997, CAIP.

[8]  Mohamad H. Hassoun,et al.  A two-level Hamming network for high performance associative memory , 2001, Neural Networks.

[9]  Laurenz Wiskott,et al.  The role of topographical constraints in face recognition , 1999, Pattern Recognition Letters.

[10]  Hyeonjoon Moon,et al.  The FERET Evaluation Methodology for Face-Recognition Algorithms , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[11]  Mohamad H. Hassoun,et al.  Associative neural memories : theory and implementation , 1993 .

[12]  Stefan Fischer,et al.  Face authentication with Gabor information on deformable graphs , 1999, IEEE Trans. Image Process..

[13]  David G. Stork,et al.  Pattern classification, 2nd Edition , 2000 .

[14]  Mohamad H. Hassoun,et al.  Application of a post-processing algorithm for improved human face recognition , 1999, IJCNN'99. International Joint Conference on Neural Networks. Proceedings (Cat. No.99CH36339).

[15]  D. L. Reilly,et al.  A neural model for category learning , 1982, Biological Cybernetics.

[16]  Rama Chellappa,et al.  Human and machine recognition of faces: a survey , 1995, Proc. IEEE.

[17]  Volodymyr Mosorov.  A main stem concept for image matching , 2005, Pattern Recognit. Lett..

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

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