Fabric defect detection system using stacked convolutional denoising auto-encoders trained with synthetic defect data

Young Joo Han, Ha Jin Yu

Research output: Contribution to journalArticlepeer-review

26 Scopus citations

Abstract

As defect detection using machine vision is diversifying and expanding, approaches using deep learning are increasing. Recently, there have been much research for detecting and classifying defects using image segmentation, image detection, and image classification. These methods are effective but require a large number of actual defect data. However, it is very difficult to get a large amount of actual defect data in industrial areas. To overcome this problem, we propose a method for defect detection using stacked convolutional autoencoders. The autoencoders we proposed are trained by using only non-defect data and synthetic defect data generated by using the characteristics of defect based on the knowledge of the experts. A key advantage of our approach is that actual defect data is not required, and we verified that the performance is comparable to the systems trained using real defect data.

Original languageEnglish
Article number2511
JournalApplied Sciences (Switzerland)
Volume10
Issue number7
DOIs
StatePublished - 1 Apr 2020

Keywords

  • Autoencoders
  • CNN
  • Fabric defect detection
  • Synthetic defect generation

Fingerprint

Dive into the research topics of 'Fabric defect detection system using stacked convolutional denoising auto-encoders trained with synthetic defect data'. Together they form a unique fingerprint.

Cite this