Light U-Net with a New Morphological Attention Gate Model Application to Analyse Wood Sections - Silva Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

Light U-Net with a New Morphological Attention Gate Model Application to Analyse Wood Sections

Résumé

This article focuses on heartwood segmentation from cross-section RGB images (see Fig.1). In this context, we propose a novel attention gate (AG) model for both improving performance and making light convolutional neural networks (CNNs). Our proposed AG is based on mathematical morphology operators. Our light CNN is based on the U-Net architecture and called Light U-net (LU-Net). Experimental results show that AGs consistently improve the prediction performance of LU-Net across different wood cross-section datasets. Our proposed morphological AG achieves better performance than original U-Net with 10 times less parameters.

Domaines

Informatique
Fichier principal
Vignette du fichier
main.pdf (9.51 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03887107 , version 1 (03-03-2023)

Identifiants

Citer

Rémi Decelle, Phuc Ngo, Isabelle Debled-Rennesson, Frédéric Mothe, Fleur Longuetaud. Light U-Net with a New Morphological Attention Gate Model Application to Analyse Wood Sections. ICPRAM 2023 - 12th International Conference on Pattern Recognition Applications and Methods, Feb 2023, Lisbon, Portugal. pp.759-766, ⟨10.5220/0011626800003411⟩. ⟨hal-03887107⟩
116 Consultations
43 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More