Paper
1 June 1992 Template generation for pattern classification
Paul D. Gader
Author Affiliations +
Abstract
A method for combining fuzzy morphological operations with fuzzy logic operations in a heterogeneous network structure is described. The first layer of the network would consist of template operations. The other layers would perform decision making. Such a network could be used to perform classification, image processing functions, and computer vision tasks. Generalized template operations are defmed using image algebra. It is shown that fuzzy morphological operations and linear operations can be obtained from the generalized operations by suitable choices of parameters. Training rules are described that can be used to "learn" the parameters of the generalized operations in a fashion similar to standard backpropagation. Thus, the network could learn linear or morphological operations, or a combination of the two.
© (1992) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Paul D. Gader "Template generation for pattern classification", Proc. SPIE 1769, Image Algebra and Morphological Image Processing III, (1 June 1992); https://doi.org/10.1117/12.60633
Lens.org Logo
CITATIONS
Cited by 7 scholarly publications.
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Image processing

Fuzzy logic

Image classification

Image filtering

Neural networks

Convolution

Computer vision technology

RELATED CONTENT

An improved multi-scale autoconvolution transform
Proceedings of SPIE (November 24 2014)
DC UNet research on image segmentation based on deep...
Proceedings of SPIE (November 30 2022)
VEST - The Visual. Expert Syptep Testbed
Proceedings of SPIE (March 26 1986)
Robust parallel clustering algorithm for image segmentation
Proceedings of SPIE (February 27 1996)
Can Scale Space Filtering Enhance Fractal Analysis?
Proceedings of SPIE (March 27 1989)

Back to Top