An Unsupervised Generative Adversarial Network-Based Method for Defect Inspection of Texture Surfaces
Open Access
- 30 December 2020
- journal article
- research article
- Published by MDPI AG in Applied Sciences
- Vol. 11 (1), 283
- https://doi.org/10.3390/app11010283
Abstract
Recently, deep learning-based defect inspection methods have begun to receive more attention—from both researchers and the industrial community—due to their powerful representation and learning capabilities. These methods, however, require a large number of samples and manual annotation to achieve an acceptable detection rate. In this paper, we propose an unsupervised method of detecting and locating defects on patterned texture surface images which, in the training phase, needs only a moderate number of defect-free samples. An extended deep convolutional generative adversarial network (DCGAN) is utilized to reconstruct input image patches; the resulting residual map can be used to realize the initial segmentation defects. To further improve the accuracy of defect segmentation, a submodule termed “local difference analysis” (LDA) is embedded into the overall module to eliminate false positives. We conduct comparative experiments on a series of datasets and the final results verify the effectiveness of the proposed method.Funding Information
- National Natural Science Foundation of China (51875515)
This publication has 27 references indexed in Scilit:
- An improved Otsu method using the weighted object variance for defect detectionApplied Surface Science, 2015
- Multiscale image quality measures for defect detection in thin filmsThe International Journal of Advanced Manufacturing Technology, 2015
- Patterned Fabric Inspection and Visualization by the Method of Image DecompositionIEEE Transactions on Automation Science and Engineering, 2014
- Detection of surface crack defects on ferrite magnetic tileNDT & E International, 2014
- Automated fabric defect detection—A reviewImage and Vision Computing, 2011
- An automated inspection system for textile fabrics based on Gabor filtersRobotics and Computer-Integrated Manufacturing, 2008
- Discriminative fabric defect detection using adaptive waveletsOptical Engineering, 2002
- Neural networks for the optical recognition of defects in clothOptical Engineering, 1996
- Automated inspection of textile fabrics using textural modelsIEEE Transactions on Pattern Analysis and Machine Intelligence, 1991
- Applying Fourier and Associated Transforms to Pattern Characterization in TextilesTextile Research Journal, 1990