1 April 1998 Neural network for invariant recognition of a few image classes
Author Affiliations +
Abstract
A neural network (NN) for recognition of a few image classes is considered. The method of recognition in the initial and transformed space of the features, where the training set is based on dispersion analysis, is investigated. Simulation results of the recognition process by type (alpha) NN are presented for the images of objects in the initial and transformed space of the features.
© (1998) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Alexandr N. Oparin, Alexandr N. Oparin, Irina V. Plekhanova, Irina V. Plekhanova, Nickolay G. Soloviov, Nickolay G. Soloviov, } "Neural network for invariant recognition of a few image classes", Proc. SPIE 3402, Optical Information Science and Technology (OIST97): Optical Memory and Neural Networks, (1 April 1998); doi: 10.1117/12.304961; https://doi.org/10.1117/12.304961
PROCEEDINGS
5 PAGES


SHARE
RELATED CONTENT

Hybrid neural networks for gray image recognition
Proceedings of SPIE (August 19 1998)
Neural network transformation of arbitrary Boolean functions
Proceedings of SPIE (December 16 1992)
Neural network for invariant recognition
Proceedings of SPIE (December 27 1996)
Image segmentation by a multilayer neural network
Proceedings of SPIE (December 31 1996)

Back to Top