Approximating morphological operators with part-based representations learned by asymmetric auto-encoders

DOI10.1515/MATHM-2020-0102MaRDI QIDQ1980892zbMATHOpenAlexFDO

Authors Samy Blusseau, Bastien Ponchon, Santiago Velasco-Forero, Jesús Angulo, I. Bloch

Publication date 9 September 2021

Published in Mathematical Morphology. Theory and Applications (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1515/mathm-2020-0102

zbMATH Keywords

mathematical morphologyrepresentation learningauto-encodersmorphological invariancenon-negative sparse codingXAI

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Computational aspects of data analysis and big data (68T09) Computer graphics; computational geometry (digital and algorithmic aspects) (68U05) Computing methodologies for image processing (68U10)

Recommendations

• Part-based approximations for morphological operators using asymmetric auto-encoders
• Generative model of autoencoders self-learning on images represented by count samples
• Sparse mathematical morphology using non-negative matrix factorization
• A learning framework for morphological operators using counter-harmonic mean
• Nonredundant sparse feature extraction using autoencoders with receptive fields clustering

Cites work

• scientific article; zbMATH DE number 1903408 (Why is no real title available?)
• Max-plus operators applied to filter selection and model pruning in neural networks
• Morphological Perceptrons: Geometry and Training Algorithms
• Non-negative matrix factorization with sparseness constraints
• Nonredundant sparse feature extraction using autoencoders with receptive fields clustering
• Part-based approximations for morphological operators using asymmetric auto-encoders
• Sparse mathematical morphology using non-negative matrix factorization
• Sparse modeling for image and vision processing

Cited in

(3)

• Nonredundant sparse feature extraction using autoencoders with receptive fields clustering
• Part-based approximations for morphological operators using asymmetric auto-encoders
• Morpho-MNIST: quantitative assessment and diagnostics for representation learning

Describes a project that uses

Uses Software

• MNIST
• Fashion-MNIST
• InfoGAN

This page was built for publication: Approximating morphological operators with part-based representations learned by asymmetric auto-encoders

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1980892)