Improvement of Damage Segmentation Based on Pixel-Level Data Balance Using VGG-Unet

Improvement of Damage Segmentation Based on Pixel-Level Data Balance Using VGG-Unet

In this research, 200 corrosion images of steel and 500 crack images of rubber bearing are collected and manually labeled to build the data set. Then the two data sets are respectively adopted to train VGG-Unet models in two methods, aiming to conduct Damage Segmentation by inputting different size...

Full description

Bibliographic Details
Main Authors: Jiyuan Shi, Ji Dang, Mida Cui, Rongzhi Zuo, Kazuhiro Shimizu, Akira Tsunoda, Yasuhiro Suzuki
Format: Article
Language:English
Published: MDPI AG 2021-01-01
Series:Applied Sciences
Subjects:
fully convolutional network
damage segmentation
VGG-Unet
pixel-level data balance
Online Access:https://www.mdpi.com/2076-3417/11/2/518

Internet

https://www.mdpi.com/2076-3417/11/2/518

Similar Items