21 May 1993 Designing morphological composite operators based on fuzzy systems
Author Affiliations +
Abstract
In this paper, we introduce a method to design gray scale composite morphological operators as fuzzy neural networks. In this structure, synaptic weights are represented by a gray scale structuring element. The proposed method is a two-step procedure. First, a suitable neural topology is found through the basis functions of the composite operators. Second, a learning rule based on the average least mean square is applied where each synaptic weight is found through a back propagation algorithm. One dimensional examples are shown. This scheme can be easily extended to two dimensions.
© (1993) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Aldo W. Morales, Sung-Jea Ko, "Designing morphological composite operators based on fuzzy systems", Proc. SPIE 1902, Nonlinear Image Processing IV, (21 May 1993); doi: 10.1117/12.144762; https://doi.org/10.1117/12.144762
PROCEEDINGS
11 PAGES


SHARE
KEYWORDS
Fuzzy logic

Neural networks

Composites

Nonlinear image processing

Chemical elements

Fuzzy systems

Mathematical morphology

RELATED CONTENT


Back to Top