Image compression using an outer product neural network

The application of the outer product neural network (OPNN) to the problem of image compression is described. Basic characteristics of the OPNN are discussed and related to image compression. A method of image compression using a hierarchy of two or more OPNNs is also described. Examples of results obtained with both a single OPNN and a hierarchy of two OPNNs are given and contrasted.<<ETX>>

[1]  L. E. Russo.  An outer product neural network for extracting principal components from a time series , 1991, Neural Networks for Signal Processing Proceedings of the 1991 IEEE Workshop.

[2]  Erkki Oja,et al.  Neural Networks, Principal Components, and Subspaces , 1989, Int. J. Neural Syst..

[3]  Terence D. Sanger,et al.  Optimal unsupervised learning in a single-layer linear feedforward neural network , 1989, Neural Networks.

[4]  E. Oja.  Simplified neuron model as a principal component analyzer , 1982, Journal of mathematical biology.

[5]  T. Kohonen,et al.  The subspace learning algorithm as a formalism for pattern recognition and neural networks , 1988, IEEE 1988 International Conference on Neural Networks.

[6]  Paul W. Munro,et al.  Principal Components Analysis Of Images Via Back Propagation , 1988, Other Conferences.