1 April 1998 Application of the neural networks based on multivalued neurons in image processing and recognition
Author Affiliations +
Abstract
Multi-valued neurons are the neural processing elements with complex-valued weights, huge functionality (it is possible to implement arbitrary mapping described by partial-defined multiple-valued function on the single neuron), fast converged learning algorithms. Such features of the multi- valued neurons may be used for solution of the different kinds of problems. Special kind of neural network with multi-valued neurons for image recognition will be considered in the paper. Such a network analyzes the spectral coefficients corresponding to low frequencies. A quickly converged learning algorithm and example of face recognition are also presented. The next application of multi-valued neurons proposed in this paper is their using as basic elements of a cellular neural network. Such an approach makes it possible to implement high effective non- linear multi-valued filters. These filters are very effective for reduction of Gaussian, uniform and speckle noise. They are also highly effective for solution of the frequency correction problem. A correction of the high and medium spatial frequencies using multi-valued filters leads to highly effective extraction of details and local contrast enhancement. Two methods for solution of the super- resolution problem using prediction of high frequency coefficients on multi-valued neuron, and correction of the high frequency part of spectrum by multi-valued filtering are proposed also.
© (1998) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Igor N. Aizenberg, Igor N. Aizenberg, Naum N. Aizenberg, Naum N. Aizenberg, } "Application of the neural networks based on multivalued neurons in image processing and recognition", Proc. SPIE 3307, Applications of Artificial Neural Networks in Image Processing III, (1 April 1998); doi: 10.1117/12.304648; https://doi.org/10.1117/12.304648
PROCEEDINGS
10 PAGES


SHARE
RELATED CONTENT

Recursive FatBear filter
Proceedings of SPIE (April 30 1994)
Nonlinear filtering using weightless adaptive neural nets
Proceedings of SPIE (March 27 1995)
1p-norm optimum filters for image recognition
Proceedings of SPIE (September 30 1999)
Adaptive region-based filtering of multiplicative noise
Proceedings of SPIE (April 03 1997)
Edge and corner preserving smoothing for artistic imaging
Proceedings of SPIE (February 26 2007)
A novel method of image Gaussian noise filtering based on...
Proceedings of SPIE (January 27 2009)

Back to Top