Part-based approximations for morphological operators using asymmetric auto-encoders

DOI10.1007/978-3-030-20867-7_25zbMATH Open1445.68312arXiv1904.00763OpenAlexW2930937638MaRDI QIDQ2189384FDOQ2189384

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

Publication date: 15 June 2020

Abstract: This paper addresses the issue of building a part-based representation of a dataset of images. More precisely, we look for a non-negative, sparse decomposition of the images on a reduced set of atoms, in order to unveil a morphological and interpretable structure of the data. Additionally, we want this decomposition to be computed online for any new sample that is not part of the initial dataset. Therefore, our solution relies on a sparse, non-negative auto-encoder where the encoder is deep (for accuracy) and the decoder shallow (for interpretability). This method compares favorably to the state-of-the-art online methods on two datasets (MNIST and Fashion MNIST), according to classical metrics and to a new one we introduce, based on the invariance of the representation to morphological dilation.

Full work available at URL: https://arxiv.org/abs/1904.00763

Recommendations

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

zbMATH Keywords

mathematical morphologyrepresentation learningauto-encodersmorphological invariancenon-negative sparse coding

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Image processing (compression, reconstruction, etc.) in information and communication theory (94A08) Computing methodologies for image processing (68U10)

Cited In (2)

• Approximating morphological operators with part-based representations learned by asymmetric auto-encoders
• Editorial -- special issue: ISMM 2019

This page was built for publication: Part-based approximations for morphological operators using asymmetric auto-encoders

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2189384)