Semi-supervised fabric defect detection based on image reconstruction and density estimation
Source abstract
Abstract
Defective products are a major contributor toward a decline in profits in textile industries. Hence, there are compelling needs for an automated inspection system to identify and locate defects on the fabric surface. Although much effort has been made by researchers worldwide, there are still challenges with computation and accuracy in the location of defects. In this paper, we propose a hybrid semi-supervised method for fabric defect detection based on variational autoencoder (VAE) and Gaussian mixture model (GMM). The VAE model is trained for feature extraction and image reconstruction while the GMM is used to perform density estimation. By synthesizing the detection results from both image content and latent space, the method can construct defect region boundaries more accurately, which are useful in fabric quality evaluation. The proposed method is validated on AITEX and DAGM 2007 public database. Results demonstrate that the method is qualified for automated detection and outperforms other selected methods in terms of overall performance.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Industrial Vision Systems and Defect Detection · Image Processing Techniques and Applications · Image and Object Detection Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
College of Mechanical Engineering, Donghua University, China
Beijing National Innovation Institute of Lightweight Ltd., China
References (38)
Show source-provided references
1. 10.1016/j.mseb.2006.02.03310.1016/j.mseb.2006.02.033 ↗
2. Eyvaz M · Current status and perspectives in water and wastewater treatment. Textil Adv Appl Tech · 2017 · 11 · 293
3. Paul R. High Performance Technical Textiles. John Wiley & Sons, 2019.10.1002/9781119325062 ↗
4. Stefanov I, Bassegoda A and Tzanov T. Enzyme biotechnology for medical textiles. In: Advances in Textile Biotechnology . Elsevier: 2019, pp.133–158.10.1016/B978-0-08-102632-8.00007-4 ↗
5. 10.1080/00405000.2014.91606310.1080/00405000.2014.916063 ↗
6. Yıldız K · Pamukkale Univ Muh Bilim Derg · 2017 · 23 · 841
7. 10.5505/pajes.2016.8003710.5505/pajes.2016.80037 ↗
8. 10.1109/TIE.1930.89647610.1109/TIE.1930.896476 ↗
9. 10.1109/ACCESS.2019.291362010.1109/ACCESS.2019.2913620 ↗
10. Liu Z, Liu S, Li C, et al. Fabric defects detection based on SSD. In: Proceedings of the 2nd International Conference on Graphics and Signal Processing 2018, pp.74–78.10.1145/3282286.3282300 ↗
11. Jing J, Wang Z, Rätsch M, et al. Mobile-Unet: An efficient convolutional neural network for fabric defect detection. Textil Res J 2020: 0040517520928604.
12. Tolba AS. Manifolds for training set selection through outlier detection. In: The 10th IEEE International Symposium on Signal Processing and Information Technology. IEEE: 2010, pp.467–472.10.1109/ISSPIT.2010.5711754 ↗
13. 10.1080/01431161.2017.139947210.1080/01431161.2017.1399472 ↗
14. 10.1117/1.JEI.25.6.06141010.1117/1.JEI.25.6.061410 ↗
15. 10.3390/s1801020910.3390/s18010209 ↗
16. Goodfellow I, Pouget-Abadie J, Mirza M, et al. Generative adversarial nets. In: Advances in neural information processing systems. MIT Press: 2014, pp.2672–2680.
17. Haselmann M, Gruber DP and Tabatabai P. Anomaly detection using deep learning based image completion. In: 2018 17th IEEE International Conference on Machine Learning and Applications (ICMLA) . IEEE: 2018, pp.1237–1242.10.1109/ICMLA.2018.00201 ↗
18. Zhao Z, Li B, Dong R, et al. A surface defect detection method based on positive samples. In: Pacific Rim International Conference on Artificial Intelligence. Springer: 2018, pp.473–481.10.1007/978-3-319-97310-4_54 ↗
19. Schlegl T, Seeböck P, Waldstein SM, et al. Unsupervised anomaly detection with generative adversarial networks to guide marker discovery. In: International conference on information processing in medical imaging. Springer: 2017, pp.146–157.10.1007/978-3-319-59050-9_12 ↗
20. Zenati H, Foo CS, Lecouat B, et al. Efficient GAN-based anomaly detection. arXiv preprint arXiv:180206222 2018.
21. Akcay S, Atapour-Abarghouei A and Breckon TP. Ganomaly: Semi-supervised anomaly detection via adversarial training. In: Asian Conference on Computer Vision. Springer: 2018, pp.622–637.10.1007/978-3-030-20893-6_39 ↗
22. Kingma DP and Welling M. Auto-encoding variational bayes. arXiv preprint arXiv:13126114 2013.
23. Reynolds DA. Gaussian Mixture Models. In: Encyclopedia of biometrics. Springer: 2009; p.741.10.1007/978-0-387-73003-5_196 ↗
24. Van Looveren A, Vacanti G, Klaise J, et al. Variational auto-encoding gaussian mixture model, https://docs.seldon.io/projects/alibi-detect/en/stable/methods/vaegmm.html (accessed 22 Jul 2020).
25. Hu G, Huang J, Wang Q, et al. Unsupervised fabric defect detection based on a deep convolutional generative adversarial network. Textil Res J 2019: 0040517519862880.
26. 10.1109/TIP.2003.81986110.1109/TIP.2003.819861 ↗
27. 10.1007/s00170-014-6758-710.1007/s00170-014-6758-7 ↗
28. 10.32614/RJ-2016-02110.32614/RJ-2016-021 ↗
29. 10.1007/s11760-016-0939-910.1007/s11760-016-0939-9 ↗
30. 10.1038/323533a010.1038/323533a0 ↗
31. Akaike H. Factor analysis and AIC. In: Selected papers of Hirotugu Akaike . Springer: 1987, pp.371–386.10.1007/978-1-4612-1694-0_29 ↗
32. 10.1080/01621459.1995.1047657210.1080/01621459.1995.10476572 ↗
33. Papandreou G, Zhu T, Kanazawa N, et al. Towards accurate multi-person pose estimation in the wild. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. IEEE: 2017, pp.4903–4911.10.1109/CVPR.2017.395 ↗
34. Abadi M, Agarwal A, Barham P, et al. Tensorflow: Large-scale machine learning on heterogeneous distributed systems. arXiv preprint arXiv:160304467 2016.
35. 10.2478/aut-2019-003510.2478/aut-2019-0035 ↗
36. Wieler M and Hahn T. HCI: Weakly supervised learning for industrial optical inspection, https://hci.iwr.uni-heidelberg.de/node/3616 (accessed 1 May 2020).
37. Jeni LA, Cohn JF and De La Torre F. Facing imbalanced data–recommendations for the use of performance metrics. In: 2013 Humaine association conference on affective computing and intelligent interaction. IEEE: 2013, pp.245–251.10.1109/ACII.2013.47 ↗
38. 10.1177/152808371455577710.1177/1528083714555777 ↗