A Brief Review and Comparison of Feedforward Morphological Neural Networks with Applications to Classification

Authors:
Alexandre Monteiro Da Silva;Peter Sussner
Affiliations:
Institute of Math., Stat. and Sci. Comp, University of Campinas, Campinas, 13081-970;Institute of Math., Stat. and Sci. Comp, University of Campinas, Campinas, 13081-970
Venue:
ICANN '08 Proceedings of the 18th international conference on Artificial Neural Networks, Part II
Year:
2008

Citing 10
Cited 2

Why mathematical morphology needs complete lattices

Signal Processing
Decomposition of mappings between complete lattices by mathematical morphology, part I.: General lattices

Signal Processing
Fuzzy lattice neurocomputing (FLN) models

Neural Networks
Guest Editorial: Special Issue on Morphological Neural Networks

Journal of Mathematical Imaging and Vision
Morphological Scale Spaces and Associative Morphological Memories: Results on Robustness and Practical Applications

Journal of Mathematical Imaging and Vision
Optimizing Digital Hardware Perceptrons for Multi-Spectral Image Classification

Journal of Mathematical Imaging and Vision
Image Analysis and Mathematical Morphology

Image Analysis and Mathematical Morphology
A general framework for fuzzy morphological associative memories

Fuzzy Sets and Systems
Pattern Recognition and Neural Networks

Pattern Recognition and Neural Networks
Gray-scale morphological associative memories

IEEE Transactions on Neural Networks

Piecewise-linear approximation of non-linear models based on probabilistically/possibilistically interpreted intervals' numbers (INs)

Information Sciences: an International Journal
FL-GrCCA: A granular computing classification algorithm based on fuzzy lattices

Computers & Mathematics with Applications

Quantified Score

Hi-index	0.00

Visualization

Abstract

The mathematical background of MNNs can be found in mathematical morphology (MM). Since MM can be conducted very generally in the complete lattice setting, MNNs are closely related to other lattice-based neurocomputing models.This paper reviews some important types of feedforward morphological neural networks including their mathematical background. In addition, we analyze and compare the performance of feedforward morphological models and conventional multi-layer perceptrons in some classification problems.