Optimizing morphological representations: robustness to initialization and gradient sparsity

DOI10.1007/S10851-026-01331-8MaRDI QIDQ7346711zbMATH OpenFDO

Authors Mihaela Dimitrova, Samy Blusseau, Santiago Velasco-Forero

Publication date 11 September 2026

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

Full work available at URL https://doi.org/10.1007/S10851-026-01331-8

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Computing methodologies for image processing (68U10)

Cites work

• A learning framework for morphological operators using counter-harmonic mean
• A representation theory for morphological image and signal processing
• Cell counting with trainable h-maxima and connected component layers
• Decomposition of mappings between complete lattices by mathematical morphology. I: General lattices
• Going beyond p-convolutions to learn grayscale morphological operators
• scientific article; zbMATH DE number 6378127 (Why is no real title available?)
• scientific article; zbMATH DE number 3502485 (Why is no real title available?)
• scientific article; zbMATH DE number 1318029 (Why is no real title available?)
• Image restoration by learning morphological opening-closing network
• Learnable Empirical Mode Decomposition based on Mathematical Morphology
• Learning grayscale mathematical morphology with smooth morphological layers
• Minimal Representations for Translation-Invariant Set Mappings by Mathematical Morphology

This page was built for publication: Optimizing morphological representations: robustness to initialization and gradient sparsity

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q7346711)