Going beyond p-convolutions to learn grayscale morphological operators

DOI10.1007/978-3-030-76657-3_34zbMath1484.68300arXiv2102.10038OpenAlexW3164506637MaRDI QIDQ2061840

Alexandre Kirszenberg, Jesús Angulo, Élodie Puybareau, Guillaume Tochon

Publication date: 21 December 2021

Full work available at URL: https://arxiv.org/abs/2102.10038

zbMATH Keywords

counter-harmonic meangrayscale mathematical morphologymorphological layerp-convolution

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Computing methodologies for image processing (68U10)

Related Items (4)

Learning grayscale mathematical morphology with smooth morphological layers ⋮ Logarithmic morphological neural nets robust to lighting variations ⋮ On some associations between mathematical morphology and artificial intelligence ⋮ Learnable Empirical Mode Decomposition based on Mathematical Morphology

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Image restoration by learning morphological opening-closing network
• 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

This page was built for publication: Going beyond p-convolutions to learn grayscale morphological operators