EUVIMEDEUVIMED entdecken
Crossref

Group Equivariant Morphological Networks

Valentin Penaud–Polge, Santiago Velasco-Forero, Jesus G. Angulo

SIAM Journal on Imaging Sciences · 31.12.2025 · 18 (4) · 2236-2276

DOI: 10.1137/24m1685766 ↗

Kurz gefasst

Fachartikel in der Zeitschrift SIAM Journal on Imaging Sciences, online erschienen am 13.10.2025. Verfasst von Valentin Penaud–Polge und 2 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 47 Literaturangaben. Gefördert von: Grand Équipement National De Calcul Intensif.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Classical mathematical morphology on images relies on two translation equivariant operators which are often considered as the nonlinear counterparts of convolution. Observing the development of convolutional neural networks, mathematical morphology is transitioning to a deep learning framework. This paper is an attempt (extending the paper of Penaud–Polge, Velasco-Forero, and Angulo [ Proceedings of the International Conference on Discrete Geometry and Mathematical Morphology, 2024]) to build theoretical foundations to adapt mathematical morphology to group equivariant deep learning. The proposed theory generalizes existing framework of translation equivariant morphological operators by considering a special case of group morphology, introduced by Roerdink in the early 2000s, and deriving it in the context of nonabelian group actions. A theoretical aperture is given by (i) a generalized expression of [Formula: see text]-operators, proposed by Heijmans in the early 90s, for group equivariance and (ii) a group equivariant version of a recent smooth approximation of morphological operators by Hermary et al. [ J. Math. Imaging Vision, 64 (2022), pp. 736–753]. The theoretical results lead to the proposition of several group equivariant morphological layers. Finally, the proposed layers are assessed using the Fashion-MNIST dataset in the case of translations and [Formula: see text] rotations. The experiments show that the proposed morphological networks, trained only with upright samples, classify rotated images without a loss of performance.

Förderung

  • Grand Équipement National De Calcul Intensif

Zitieren

APA

Penaud–Polge, V., Velasco-Forero, S., & Angulo, J. G. (2025). Group Equivariant Morphological Networks. SIAM Journal on Imaging Sciences, 18(4), 2236-2276. https://doi.org/10.1137/24m1685766

Vancouver

Penaud–Polge V, Velasco-Forero S, Angulo JG. Group Equivariant Morphological Networks. SIAM Journal on Imaging Sciences. 2025;18(4):2236-2276. doi:10.1137/24m1685766

BibTeX
@article{PenaudPolge2025,
  author = {Penaud–Polge, Valentin and Velasco-Forero, Santiago and Angulo, Jesus G.},
  title = {Group Equivariant Morphological Networks},
  journal = {SIAM Journal on Imaging Sciences},
  year = {2025},
  volume = {18},
  number = {4},
  pages = {2236--2276},
  doi = {10.1137/24m1685766}
}
Kostenlos starten →