Learning grayscale mathematical morphology with smooth morphological layers

DOI10.1007/s10851-022-01091-1OpenAlexW4280624426MaRDI QIDQ2678921

Romain Hermary, Élodie Puybareau, Jesús Angulo, Guillaume Tochon, Alexandre Kirszenberg

Publication date: 25 January 2023

Published in: Journal of Mathematical Imaging and Vision (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/s10851-022-01091-1

zbMATH Keywords

counter-harmonic meanmorphological neural networkgrayscale mathematical morphologymorphological layerP-convolution

Mathematics Subject Classification ID

Computer science (68-XX) Information and communication theory, circuits (94-XX)

Related Items

MorphoActivation: generalizing ReLU activation function by mathematical morphology

Uses Software

• MNIST

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Morphological perceptrons with competitive learning: lattice-theoretical framework and constructive learning algorithm
• An overview of morphological filtering
• Image restoration by learning morphological opening-closing network
• On some associations between mathematical morphology and artificial intelligence
• Going beyond p-convolutions to learn grayscale morphological operators
• Extreme learning machine for a new hybrid morphological/linear perceptron
• Max-plus operators applied to filter selection and model pruning in neural networks
• A Learning Framework for Morphological Operators Using Counter–Harmonic Mean
• Morphological Perceptrons: Geometry and Training Algorithms