Multi-defect detection for magnetic tile based on SE-U-Net

  • Xincheng Cao
  • , Bin Yao
  • , Binqiang Chen
  • , Yu Wang

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

7 Scopus citations

Abstract

Vision-based on-line full detection of surface defects is of great significance to the production efficiency and quality of magnetic tiles. In this work, we introduce a pixel-wise surface defect detection model called SE-U-Net, which simultaneously realizes detection and classification. The image augmentation based on instance transfer effectively reduces the imbalance between the background and the defect. The squeeze-and-excitation module empowers U-Net to adaptively learn the shallow information matched with deep features in the skip path, enhancing the ability to identify small defects with a few of additional network parameters. Experiments show that the recognition accuracy of this model exceeds the existing methods, and the mean pixel-accuracy reaches 0.97.

Original languageEnglish
Title of host publicationISPCE-CN 2020 - IEEE International Symposium on Product Compliance Engineering-Asia 2020
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781665414616
DOIs
StatePublished - 6 Nov 2020
Event2020 IEEE International Symposium on Product Compliance Engineering-Asia, ISPCE-CN 2020 - Chongqing, China
Duration: 6 Nov 20208 Nov 2020

Publication series

NameISPCE-CN 2020 - IEEE International Symposium on Product Compliance Engineering-Asia 2020

Conference

Conference2020 IEEE International Symposium on Product Compliance Engineering-Asia, ISPCE-CN 2020
Country/TerritoryChina
CityChongqing
Period6/11/208/11/20

Keywords

  • Convolutional networks
  • Deep learning
  • Magnetic tile
  • Multi-defect detection
  • Semantic Segmentation

Fingerprint

Dive into the research topics of 'Multi-defect detection for magnetic tile based on SE-U-Net'. Together they form a unique fingerprint.

Cite this