Surface Defect Detection of Steel Strips Based on Anchor-free Network with Channel Attention and Bidirectional Feature Fusion

2021 ◽  
pp. 1-1
Author(s):  
Jianbo Yu ◽  
Xun Cheng ◽  
Qingfeng Li
Keyword(s):  
Defect Detection ◽  
Surface Defect ◽  
Feature Fusion ◽  
Steel Strips ◽  
Surface Defect Detection ◽  
Free Network

A surface defect detection method based on multi-feature fusion

2017 ◽  
Author(s):  
Xiaojun Wu ◽  
Huijiang Xiong ◽  
Zhiyang Yu ◽  
Peizhi Wen
Keyword(s):  
Defect Detection ◽  
Surface Defect ◽  
Detection Method ◽  
Feature Fusion ◽  
Surface Defect Detection

scholarly journals PGA-Net: Pyramid Feature Fusion and Global Context Attention Network for Automated Surface Defect Detection

2020 ◽  
Vol 16 (12) ◽  
pp. 7448-7458 ◽  
Author(s):  
Hongwen Dong ◽  
Kechen Song ◽  
Yu He ◽  
Jing Xu ◽  
Yunhui Yan ◽  
...  
Keyword(s):  
Defect Detection ◽  
Surface Defect ◽  
Feature Fusion ◽  
Attention Network ◽  
Global Context ◽  
Surface Defect Detection

A surface defect detection method via fusing multi-level features

2022 ◽  
pp. 1-17
Author(s):  
Meijian Ren ◽  
Rulin Shen ◽  
Yanling Gong
Keyword(s):  
High Resolution ◽  
Defect Detection ◽  
Surface Defect ◽  
Detection Method ◽  
Feature Fusion ◽  
Size Difference ◽  
Feature Maps ◽  
Low Contrast ◽  
Surface Defect Detection ◽  
Multi Level

Abstract Surface defect detection is very important to ensure product quality, but most of the surface defects of industrial products are characterized by low contrast, big size difference and category similarity, which brings challenges to the automatic detection of defects. To solve these problems, we propose a defect detection method based on convolutional neural network. In this method, a backbone network with semantic supervision is applied to extract the features of different levels. While a multi-level feature fusion module is proposed to fuse adjacent feature maps into high-resolution feature maps successively, which significantly improves the prediction accuracy of the network. Finally, an Encoding module is used to obtain the global context information of the high-resolution feature map, which further improves the pixel classification accuracy. Experiments show that the proposed method is superior to other methods in NEU_SEG (mIoU of 85.27) and MT (mIoU of 77.82) datasets, and has the potential of real-time detection.

Sign in / Sign up

Export Citation Format

Share Document