Amphora Detection Based on a Gradient Weighted Error in a Convolution Neuronal Network - Aix-Marseille Université Accéder directement au contenu
Communication Dans Un Congrès Année : 2017

Amphora Detection Based on a Gradient Weighted Error in a Convolution Neuronal Network

Résumé

In this paper, we propose a method based on pixel prediction to detect objects into a large image. We propose to integrate the Weighted Error Layer (WEL) in a Convolution Neuronal Network (CNN) architecture in order to weight the error during the backpropagation and to reduce the impact of the borders. We estimate the orientation of the objects when the detection step is achieved. Our proposed layer is evaluated on real data in order to detect amphorae on the Mazatos underwater archaeological site.
Fichier principal
Vignette du fichier
Amphora Detection.pdf (3.19 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03605616 , version 1 (11-03-2022)

Identifiants

  • HAL Id : hal-03605616 , version 1

Citer

Jérôme Pasquet, Stella Demesticha, Dimitrios Skarlatos, Djamal Merad, Pierre Drap. Amphora Detection Based on a Gradient Weighted Error in a Convolution Neuronal Network. IMEKO International Conference on Metrology for Archaeology and Cultural Heritage, MetroArchaeo 2017, Oct 2017, Lecce, Italy. ⟨hal-03605616⟩
12 Consultations
40 Téléchargements

Partager

Gmail Facebook X LinkedIn More