Uwecbue O., Pandya A. Human Face Recognition Using Third-Order Synthetic Neural Networks

New York: Springer, 1997. - 131 p.
Literature is replete with applications of fITst-order neural networks (i.e. traditional multilayer perceptrons) in pattern recognition. They can also be applied to the related task of transformation-invariant pattern recognition typically by paying the high cost of very large training sets and very long training times. The objective of this book is to explore the viability of the application of high-order synthetic neural network technology to transformation-invariant recognition of complex visual patterns. High-order networks require little training data (hence, short training times) and have been used to perform transformation-invariant recognition of relativelysimple visual patterns, achieving very high recognition rates. The successful results of these methods provided inspiration to address more practical problems which have grayscale as opposed to binary patterns (e.g. alphanumeric characters, aircraft silhouettes) and are also more complex in nature as opposed to purely edge-extracted images - human face recognition is such a problem.