Please use this identifier to cite or link to this item:
Title: Defect-GAN : high-fidelity defect synthesis for automated defect inspection
Authors: Zhang, Gongjie
Cui, Kaiwen
Hung, Tzu-Yi
Lu, Shijian
Keywords: Engineering::Computer science and engineering
Issue Date: 2021
Source: Zhang, G., Cui, K., Hung, T.- Y., & Lu, S. (2021). Defect-GAN : high-fidelity defect synthesis for automated defect inspection. Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2524-2534.
metadata.dc.contributor.conference: 2021 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)
Abstract: Automated defect inspection is critical for effective and efficient maintenance, repair, and operations in advanced manufacturing. On the other hand, automated defect inspection is often constrained by the lack of defect samples, especially when we adopt deep neural networks for this task. This paper presents Defect-GAN, an automated defect synthesis network that generates realistic and diverse defect samples for training accurate and robust defect inspection networks. Defect-GAN learns through defacement and restoration processes, where the defacement generates defects on normal surface images while the restoration removes defects to generate normal images. It employs a novel compositional layer-based architecture for generating realistic defects within various image backgrounds with different textures and appearances. It can also mimic the stochastic variations of defects and offer flexible control over the locations and categories of the generated defects within the image background. Extensive experiments show that Defect-GAN is capable of synthesizing various defects with superior diversity and fidelity. In addition, the synthesized defect samples demonstrate their effectiveness in training better defect inspection networks.
Schools: School of Electrical and Electronic Engineering 
Organisations: Delta Research Center, Singapore
Research Centres: Delta-NTU Corporate Laboratory 
Rights: © 2021 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Fulltext Permission: open
Fulltext Availability: With Fulltext
Appears in Collections:EEE Conference Papers

Files in This Item:
File Description SizeFormat 
WACV_2021_Defect_GAN__Camera_Ready_.pdf2.14 MBAdobe PDFThumbnail

Page view(s)

Updated on Oct 3, 2023

Download(s) 20

Updated on Oct 3, 2023

Google ScholarTM


Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.