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

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.
Complete list of metadatas

https://hal.archives-ouvertes.fr/hal-02071470
Contributor : Samy Blusseau <>
Submitted on : Monday, April 1, 2019 - 10:24:52 AM
Last modification on : Friday, October 18, 2019 - 1:32:35 AM
Long-term archiving on : Tuesday, July 2, 2019 - 1:20:38 PM

Files

ponchon-et-al.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-02071470, version 2
  • ARXIV : 1904.00763

Citation

Bastien Ponchon, Santiago Velasco-Forero, Samy Blusseau, Jesus Angulo, Isabelle Bloch. Part-based approximations for morphological operators using asymmetric auto-encoders. International Symposium on Mathematical Morphology, Jul 2019, Saarbrücken, Germany. ⟨hal-02071470v2⟩

Share

Metrics

Record views

144

Files downloads

143