HAL will be down for maintenance from Friday, June 10 at 4pm through Monday, June 13 at 9am. More information
Skip to Main content Skip to Navigation
Conference papers

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 metadata

Contributor : Samy Blusseau Connect in order to contact the contributor
Submitted on : Monday, April 1, 2019 - 10:24:52 AM
Last modification on : Wednesday, November 17, 2021 - 12:27:16 PM
Long-term archiving on: : Tuesday, July 2, 2019 - 1:20:38 PM


Files produced by the author(s)


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


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⟩



Record views


Files downloads