Robustness Study of Edge Segmentation and Completion by CNN Based Method for Tessellation Images - Mines Saint-Étienne Access content directly
Conference Papers Year : 2021

Robustness Study of Edge Segmentation and Completion by CNN Based Method for Tessellation Images

Abstract

In this paper, the robustness of tessellation images segmentation using Convolutional Neural Network (CNN) is presented. Particularly, this paper aims to study the effect of the quality and number of the images used for training on the robustness of the edge segmentation and completion. Three kinds of image deterioration are considered: the absence of a part of the tessellation, the discontinuity of the edges constituting the tessellation and the presence of a background noise. Five CNNs are trained with several kinds of deteriorated images and the trained models are then compared according to the results obtained with four classes of images.
Fichier principal
Vignette du fichier
VPP_YG ISIVC 2020.pdf (506.52 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

emse-03284617 , version 1 (03-02-2022)

Identifiers

Cite

Valentin Penaud-Polge, Yann Gavet. Robustness Study of Edge Segmentation and Completion by CNN Based Method for Tessellation Images. ISIVC'2020: The 10th International Symposium on Signal, Image, Video and Communications, Mines Saint-Etienne, Apr 2021, Saint-Etienne, France. pp.9487553, ⟨10.1109/ISIVC49222.2021.9487553⟩. ⟨emse-03284617⟩
63 View
65 Download

Altmetric

Share

Gmail Facebook X LinkedIn More