Gray-scale morphological associative memories

Neural models of associative memories are usually concerned with the storage and the retrieval of binary or bipolar patterns. Thus far, the emphasis in research on morphological associative memory systems has been on binary models, although a number of notable features of autoassociative morphological memories (AMMs) such as optimal absolute storage capacity and one-step convergence have been shown to hold in the general, gray-scale setting. In this paper, we make extensive use of minimax algebra to analyze gray-scale autoassociative morphological memories. Specifically, we provide a complete characterization of the fixed points and basins of attractions which allows us to describe the storage and recall mechanisms of gray-scale AMMs. Computer simulations using gray-scale images illustrate our rigorous mathematical results on the storage capacity and the noise tolerance of gray-scale morphological associative memories (MAMs). Finally, we introduce a modified gray-scale AMM model that yields a fixed point which is closest to the input pattern with respect to the Chebyshev distance and show how gray-scale AMMs can be used as classifiers

[1]  Paul D. Gader,et al.  Automatic target detection using entropy optimized shared-weight neural networks , 2000, IEEE Trans. Neural Networks Learn. Syst..

[2]  Willi Hock,et al.  Lecture Notes in Economics and Mathematical Systems , 1981 .

[3]  Jennifer L. Davidson.  Foundation and Applications of Lattice Transforms in Image Processing , 1992 .

[4]  Paul D. Gader,et al.  Morphological regularization neural networks , 2000, Pattern Recognit..

[5]  Correlation Matrix Memory , 2005 .

[6]  B. Carré.  An Algebra for Network Routing Problems , 1971 .

[7]  Manuel Graña,et al.  On the Application of Associative Morphological Memories to Hyperspectral Image Analysis , 2003, IWANN.

[8]  Giovanni Costantini,et al.  Multiplierless digital learning algorithm for cellular neural networks , 2001 .

[9]  H Rieger,et al.  Storing an extensive number of grey-toned patterns in a neural network using multistate neurons , 1990 .

[10]  Kaoru Nakano,et al.  Associatron-A Model of Associative Memory , 1972, IEEE Trans. Syst. Man Cybern..

[11]  Geoffrey W. Brooks,et al.  Analog VLSI implementation of a morphological associative memory , 1998, Optics & Photonics.

[12]  William W. Armstrong,et al.  Adaptive Logic Networks , 2005 .

[13]  Jacek M. Zurada,et al.  Generalized Hopfield networks for associative memories with multi-valued stable states , 1996, Neurocomputing.

[14]  Catherine Blake,et al.  UCI Repository of machine learning databases , 1998 .

[15]  R. Cuninghame-Green.  Minimax algebra and applications , 1991 .

[16]  Teuvo Kohonen,et al.  Correlation Matrix Memories , 1972, IEEE Transactions on Computers.

[17]  H. Heijmans.  Morphological image operators , 1994 .

[18]  Frank H. Eeckman,et al.  A normal form projection algorithm for associative memory , 1993 .

[19]  Jacek M. Zurada,et al.  Complex-valued multistate neural associative memory , 1996, IEEE Trans. Neural Networks.

[20]  Peter Sussner,et al.  Generalizing Operations of Binary Autoassociative Morphological Memories Using Fuzzy Set Theory , 2003, Journal of Mathematical Imaging and Vision.

[21]  Peter Sussner,et al.  Morphological associative memories , 1998, IEEE Trans. Neural Networks.

[22]  Giovanni Costantini,et al.  Neural associative memory storing gray-coded gray-scale images , 2003, IEEE Trans. Neural Networks.

[23]  Shuzhi Sam Ge,et al.  Face recognition by applying wavelet subband representation and kernel associative memory , 2004, IEEE Transactions on Neural Networks.

[24]  Weimin Huang,et al.  A kernel autoassociator approach to pattern classification , 2005, IEEE Trans. Syst. Man Cybern. Part B.

[25]  Jacek M. Zurada,et al.  A new design method for the complex-valued multistate Hopfield associative memory , 2003, IEEE Trans. Neural Networks.

[26]  Peter Sussner.  Fixed points of autoassociative morphological memories , 2000, Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks. IJCNN 2000. Neural Computing: New Challenges and Perspectives for the New Millennium.

[27]  P. Sussner,et al.  New results on binary auto- and heteroassociative morphological memories , 2005, Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005..

[28]  R. Cuninghame-Green.  Minimax Algebra and Applications , 1994 .

[29]  James A. Anderson,et al.  A simple neural network generating an interactive memory , 1972 .

[30]  Bogdan Raducanu,et al.  Morphological Scale Spaces and Associative Morphological Memories: Results on Robustness and Practical Applications , 2004, Journal of Mathematical Imaging and Vision.

[31]  Teuvo Kohonen,et al.  Self-Organization and Associative Memory , 1988 .

[32]  Peter Sussner,et al.  Associative morphological memories based on variations of the kernel and dual kernel methods , 2003, Neural Networks.

[33]  John A. Hertz,et al.  Exploiting Neurons with Localized Receptive Fields to Learn Chaos , 1990, Complex Syst..