1 April 1998 Image processing algorithms based on neural network technology
Author Affiliations +
Abstract
This paper is devoted to implementation of the some original image processing algorithms using cellular neural networks on multi-valued and universal binary neurons. High-effective multi-valued filters, their implementation and application to the noise removing and frequencies correction are considered. Algorithms of the edge detection and impulse noise filtering, and their implementation are also considered. Application of the networks from multi-valued neurons to image recognition and to extrapolation of the image orthogonal spectrum to the highest frequencies domain is also presented.
© (1998) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Igor N. Aizenberg, "Image processing algorithms based on neural network technology", Proc. SPIE 3402, Optical Information Science and Technology (OIST97): Optical Memory and Neural Networks, (1 April 1998); doi: 10.1117/12.304971; https://doi.org/10.1117/12.304971
PROCEEDINGS
10 PAGES


SHARE
Back to Top