A learning framework for morphological operators using counter-harmonic mean

DOI10.1007/978-3-642-38294-9_28MaRDI QIDQ4925124zbMATH OpenOpenAlexFDO

Authors Jonathan Masci, Jesús Angulo, Jürgen Schmidhuber

Publication date 11 June 2013

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

Full work available at URL https://arxiv.org/abs/1212.2546

zbMATH Keywords

convolutional networksmachine learningmathematical morphologyonline learning

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Computer graphics; computational geometry (digital and algorithmic aspects) (68U05) Computing methodologies for image processing (68U10)

Abstract: We present a novel framework for learning morphological operators using counter-harmonic mean. It combines concepts from morphology and convolutional neural networks. A thorough experimental validation analyzes basic morphological operators dilation and erosion, opening and closing, as well as the much more complex top-hat transform, for which we report a real-world application from the steel industry. Using online learning and stochastic gradient descent, our system learns both the structuring element and the composition of operators. It scales well to large datasets and online settings.

Recommendations

• Going beyond p-convolutions to learn grayscale morphological operators
• Image restoration by learning morphological opening-closing network
• Morphological Operator Design from Training Data
• scientific article; zbMATH DE number 1262716
• Stochastic morphological filtering and Bellman-Maslov chains

Cited in

(16)

• Approximating morphological operators with part-based representations learned by asymmetric auto-encoders
• Image restoration by learning morphological opening-closing network
• Some open questions on morphological operators and representations in the deep learning era. A personal vision
• On some associations between mathematical morphology and artificial intelligence
• Going beyond p-convolutions to learn grayscale morphological operators
• From mathematical morphology to machine learning of image operators
• Part-based approximations for morphological operators using asymmetric auto-encoders
• Learning grayscale mathematical morphology with smooth morphological layers
• Morphological Operator Design from Training Data
• Learnable Empirical Mode Decomposition based on Mathematical Morphology
• Morphological networks for image de-raining
• Generalised morphological image diffusion
• Logarithmic morphological neural nets robust to lighting variations
• Optimizing morphological representations: robustness to initialization and gradient sparsity
• Morphological neural networks: a review
• Morphological representations for learning image operators: a review

This page was built for publication: A learning framework for morphological operators using counter-harmonic mean

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4925124)