Scale-free Texture Segmentation: Expert Feature-based versus Deep Learning strategies - ENS de Lyon - École normale supérieure de Lyon Accéder directement au contenu
Communication Dans Un Congrès Année : 2021

Scale-free Texture Segmentation: Expert Feature-based versus Deep Learning strategies

Résumé

Texture segmentation constitutes a central task in image processing, classically based on two-step procedures consisting first in computing hand-crafted features devised from a priori expert knowledge and second in combining them into clustering algorithms. Deep learning approaches can be seen as merging these two steps into a single one with both discovering features and performing segmentation. Using fractal textures, often seen as relevant models in real-world applications, the present work compares a recently devised texture segmentation algorithm incorporating expert-driven scale-free features estimation into a Joint TV optimization framework against convolutional neural network architectures. From realistic synthetic textures, comparisons are drawn not only for segmentation performance, but also with respect to computational costs, architecture complexities and robustness against departures between training and testing datasets.
Fichier principal
Vignette du fichier
Eusipco20_v2.pdf (633.5 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03058780 , version 1 (11-12-2020)

Identifiants

Citer

Barbara Pascal, Vincent Mauduit, Nelly Pustelnik, Patrice Abry. Scale-free Texture Segmentation: Expert Feature-based versus Deep Learning strategies. 28th European Signal Processing Conference, Jan 2021, Amsterdam, Netherlands. ⟨10.23919/Eusipco47968.2020.9287829⟩. ⟨hal-03058780⟩
62 Consultations
221 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More