Logarithmic morphological neural nets robust to lighting variations

DOI10.1007/978-3-031-19897-7_36MaRDI QIDQ6103072zbMATH OpenOpenAlexFDO

Authors Guillaume Noyel, Emile Barbier-Renard, Michel Jourlin, T. Fournel

Publication date 2 June 2023

Published in Lecture Notes in Computer Science (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/2204.09319

zbMATH Keywords

functional Asplund metriclogarithmic image processinglogarithmic mathematical morphologymorphological neural netsrobustness to lighting variations

Mathematics Subject Classification ID

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

Abstract: Morphological neural networks allow to learn the weights of a structuring function knowing the desired output image. However, those networks are not intrinsically robust to lighting variations in images with an optical cause, such as a change of light intensity. In this paper, we introduce a morphological neural network which possesses such a robustness to lighting variations. It is based on the recent framework of Logarithmic Mathematical Morphology (LMM), i.e. Mathematical Morphology defined with the Logarithmic Image Processing (LIP) model. This model has a LIP additive law which simulates in images a variation of the light intensity. We especially learn the structuring function of a LMM operator robust to those variations, namely : the map of LIP-additive Asplund distances. Results in images show that our neural network verifies the required property.

Recommendations

• scientific article; zbMATH DE number 647316
• Morphological networks for image de-raining
• Mathematical morphology based on logarithmic image processing theory
• Morphology neural networks: An introduction with applications
• scientific article; zbMATH DE number 1759586

Cites work

• A learning framework for morphological operators using counter-harmonic mean
• Deep learning
• Double-sided probing by map of Asplund's distances using logarithmic image processing in the framework of mathematical morphology
• Functional Asplund metrics for pattern matching, robust to variable lighting conditions
• Going beyond p-convolutions to learn grayscale morphological operators
• scientific article; zbMATH DE number 3902440 (Why is no real title available?)
• Image dynamic range enhancement and stabilization in the context of the logarithmic image processing model
• Image restoration by learning morphological opening-closing network
• Learnable Empirical Mode Decomposition based on Mathematical Morphology
• Max-plus operators applied to filter selection and model pruning in neural networks
• Morphological Perceptrons: Geometry and Training Algorithms
• Morphology neural networks: An introduction with applications
• The algebraic basis of mathematical morphology I. Dilations and erosions

Cited in

(6)

• Image restoration by learning morphological opening-closing network
• scientific article; zbMATH DE number 1759586 (Why is no real title available?)
• Functional Asplund metrics for pattern matching, robust to variable lighting conditions
• Morphological networks for image de-raining
• Discrete morphological Neural networks
• Morphological neural networks: a review

This page was built for publication: Logarithmic morphological neural nets robust to lighting variations

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6103072)