MSFA-Net: A convolutional neural network ...
Type de document :
Compte-rendu et recension critique d'ouvrage
Titre :
MSFA-Net: A convolutional neural network based on multispectral filter arrays for texture feature extraction
Auteur(s) :
Amziane, Anis [Auteur]
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
Losson, Olivier [Auteur]
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
Mathon, Benjamin [Auteur]
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
Macaire, Ludovic [Auteur]
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
Losson, Olivier [Auteur]
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
Mathon, Benjamin [Auteur]
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
Macaire, Ludovic [Auteur]
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
Titre de la revue :
Pattern Recognition Letters
Pagination :
93-99
Éditeur :
Elsevier
Date de publication :
2023-03-07
ISSN :
0167-8655
Mot(s)-clé(s) en anglais :
Multispectral Imaging
deep learning
deep learning
Discipline(s) HAL :
Informatique [cs]/Traitement du signal et de l'image [eess.SP]
Résumé en anglais : [en]
Multispectral snapshot cameras fitted with a multispectral filter array (MSFA) acquire several spectral bands in one shot and provide a raw mosaic image in which a single channel value is available at each pixel. Texture ...
Lire la suite >Multispectral snapshot cameras fitted with a multispectral filter array (MSFA) acquire several spectral bands in one shot and provide a raw mosaic image in which a single channel value is available at each pixel. Texture features are classically extracted from fully-defined images that are estimated by demosaicing. Such an estimation may however cause spatio-spectral artifacts. Moreover, texture feature extraction becomes computationally inefficient and yields to high-dimensional features as the number of bands increases. In this paper, we propose an original approach based on a convolutional neural network called MSFA-Net to capture spatio-spectral interactions in raw images at reduced computation costs. Experiments of multispectral image classification and outdoor image segmentation show that the proposed approach outperforms several hand-crafted and deep learning-based feature extractors.Lire moins >
Lire la suite >Multispectral snapshot cameras fitted with a multispectral filter array (MSFA) acquire several spectral bands in one shot and provide a raw mosaic image in which a single channel value is available at each pixel. Texture features are classically extracted from fully-defined images that are estimated by demosaicing. Such an estimation may however cause spatio-spectral artifacts. Moreover, texture feature extraction becomes computationally inefficient and yields to high-dimensional features as the number of bands increases. In this paper, we propose an original approach based on a convolutional neural network called MSFA-Net to capture spatio-spectral interactions in raw images at reduced computation costs. Experiments of multispectral image classification and outdoor image segmentation show that the proposed approach outperforms several hand-crafted and deep learning-based feature extractors.Lire moins >
Langue :
Anglais
Vulgarisation :
Non
Collections :
Source :
Fichiers
- document
- Accès libre
- Accéder au document
- Texture%20%281%29.pdf
- Accès libre
- Accéder au document