Share Email Print
cover

Proceedings Paper

Classification of the images of gene expression patterns using neural networks based on multi-valued neurons with the minimal number of inputs
Author(s): Igor N. Aizenberg; Constantine Butakoff; Ekaterina Myasnikova; Maria Samsonova; John Reinitz
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

Multi-valued neurons (MVN) are the neural processing elements with complex-valued weights and high functionality. It is possible to implement an arbitrary mapping described by partial-defined multiple-valued function on the single MVN. The MVN-based neural networks are applied to temporal classification of images of gene expression patterns, obtained by confocal scanning microscopy. The classification results confirmed the efficiency of this method for image recognition. It was shown that frequency domain of the representation of gene expression images is highly effective for their description.

Paper Details

Date Published: 5 April 2002
PDF: 10 pages
Proc. SPIE 4668, Applications of Artificial Neural Networks in Image Processing VII, (5 April 2002); doi: 10.1117/12.461675
Show Author Affiliations
Igor N. Aizenberg, Neural Networks Technologies Ltd. (Israel)
Constantine Butakoff, Neural Networks Technologies Ltd. (Israel)
Ekaterina Myasnikova, Institute of High Performance Computing and Databases (Russia)
Maria Samsonova, Institute of High Performance Computing and Databases (Russia)
John Reinitz, SUNY/Stony Brook (United States)


Published in SPIE Proceedings Vol. 4668:
Applications of Artificial Neural Networks in Image Processing VII
Nasser M. Nasrabadi; Aggelos K. Katsaggelos, Editor(s)

© SPIE. Terms of Use
Back to Top