整合WGAN-GP及YOLOv5於不平衡鋼帶金屬表面資料集之瑕疵檢測

Integration of WGAN-GP and YOLOv5 for Defect Detection of Steel Strip Metal Surface with Unbalanced Dataset

10.6459/JCM.202309_20(2).0002

林嘉詳(J. X. Lin)；呂明山(M. S. Lu)

瑕疵檢測 ； 鋼帶瑕疵 ； 生成對抗網路 ； WGAN-GP ； YOLOv5 ； Defect Detection ； Steel Belt Defect ； Generative Adversarial Network ； WGAN-GP ； YOLOv5

危機管理學刊

20卷2期（2023 / 09 / 01）

11 - 22

繁體中文;英文

在鋼帶生產環境中，機台設備以及環境因素的影響，導致鋼帶產生表面缺陷，並且對於鋼鐵業來說，表面缺陷是對產品質量的最大威脅，使用有效且即時的瑕疵檢測技術為生產高質量產品的關鍵。然而，在工業領域實際生產中收集到的瑕疵樣本數量有限，各瑕疵類別數量也經常處在一個不平衡的狀態下，致使訓練物件檢測模型效果不佳。因此本研究使用鋼帶表面瑕疵資料集為例，利用基於梯度懲罰的Wasserstein生成對抗網路用於生成瑕疵樣本數量，已達資料平衡之目的，並透過訓練YOLOv5模型進行瑕疵檢測，最終評估驗證是否能有效的使用在實際生產環境瑕疵樣本在數量不平衡狀態下的瑕疵檢測。

In the steel belt production environment, the influence of equipment and environmental factors leads to surface defects in steel belts, and for the steel industry, surface defects are the biggest threat to product quality, and the use of effective and real-time defect detection technology is the key to producing high-quality products. However, the number of defect samples collected in the actual production of the industrial field is limited, and the number of defect categories is often in an unbalanced state, resulting in the poor effect of the training object detection model. Therefore, this study uses the steel belt surface defect dataset as an example, and uses the Wasserstein generative adversarial network based on gradient penalty to generate the number of defect samples, which has achieved the purpose of data balancing, and trains the YOLOv5 model for defect detection, and finally evaluates and verifies whether the defect detection in the actual production environment can be effectively used in the unbalanced number of defect samples.

1. Buda, M.,Maki, A.,Mazurowski, M. A.(2018).A systematic study of the class imbalance problem in convolutional neural networks.Neural Networks,106,249-259.
2. Chen, L.,Wang, Y.,Li, H.(2022).Enhancement of DNN-based multilabel classification by grouping labels based on data imbalance and label correlation.Pattern Recognition,132,108964.
3. Fernández, A.,López, V.,Galar, M.,del Jesus, M. J.,Herrera, F.(2013).Analysing the classification of imbalanced data-sets with multiple classes: Binarization techniques and ad-hoc approaches.Knowledge-Based Systems,42,97-110.
4. Goodfellow, I.,Pouget-Abadie, J.,Mirza, M.,Xu, B.,Warde-Farley, D.,Ozair, S.,Courville, A.,Bengio, Y.(2014).Generative adversarial nets.Advances in neural information processing systems
5. Gulrajani, I.,Ahmed, F.,Arjovsky, M.,Dumoulin, V.,Courville, A. C.(2017).Improved training of wasserstein gans.Advances in neural information processing systems
6. Hassan, A. U.,Memon, I.,Choi, J.(2023).Real-time high quality font generation with Conditional Font GAN.Expert Systems with Applications,213,118907.
7. Heusel, M.,Ramsauer, H.,Unterthiner, T.,Nessler, B.,Hochreiter, S.(2017).Gans trained by a two time-scale update rule converge to a local nash equilibrium.Advances in neural information processing systems
8. Kim, C.,Park, S.,Hwang, H. J.(2022).Local Stability of Wasserstein GANs With Abstract Gradient Penalty.IEEE Transactions on Neural Networks and Learning Systems,33(9),4527-4537.
9. Kim, D.,Byun, J.(2022).Selection of Augmented Data for Overcoming the Imbalance Problem in Facies Classification.IEEE Geoscience and Remote Sensing Letters,19,1-5.
10. Li, J.,Chen, Z.,Cheng, L.,Liu, X.(2022).Energy data generation with Wasserstein Deep Convolutional Generative Adversarial Networks.Energy,257,124694.
11. Li, L.,Jiang, Z.,Li, Y.(2021).Surface Defect Detection Algorithm of Aluminum Based on Improved Faster RCNN.2021 IEEE 9th International Conference on Information, Communication and Networks (ICICN)
12. Li, M.,Wang, H.,Wan, Z.(2022).Surface defect detection of steel strips based on improved YOLOv4.Computers and Electrical Engineering,102,108208.
13. Li, T.,Xing, L.,Fan, H.,Zhu, H.(2022).Surface Defect Detection of Aluminum Material based on Deep Learning.2022 IEEE International Conference on Advances in Electrical Engineering and Computer Applications (AEECA)
14. Liu, Q.,Ma, G.,Cheng, C.(2020).Data Fusion Generative Adversarial Network for Multi-Class Imbalanced Fault Diagnosis of Rotating Machinery.IEEE Access,8,70111-70124.
15. Lu, Y. W.,Liu, K. L.,Hsu, C. Y.(2019).Conditional Generative Adversarial Network for Defect Classification with Class Imbalance.2019 IEEE International Conference on Smart Manufacturing, Industrial & Logistics Engineering (SMILE)
16. Lv, X.,Duan, F.,Jiang, J.-j.,Fu, X.,Gan, L.(2020).Deep Metallic Surface Defect Detection: The New Benchmark and Detection Network.Sensors,20(6),1562.
17. Mordia, R.,Kumar Verma, A.(2022).Visual techniques for defects detection in steel products: A comparative study.Engineering Failure Analysis,134,106047.
18. Park, S. H.,Ha, Y. G.(2014).Large Imbalance Data Classification Based on MapReduce for Traffic Accident Prediction.2014 Eighth International Conference on Innovative Mobile and Internet Services in Ubiquitous Computing
19. Redmon, J.,Divvala, S.,Girshick, R.,Farhadi, A.(2016).You only look once: Unified, real-time object detection.Proceedings of the IEEE conference on computer vision and pattern recognition
20. Shorten, C.,Khoshgoftaar, T. M.(2019).A survey on Image Data Augmentation for Deep Learning.Journal of Big Data,6(1),60.
21. Su, Z.,Han, K.,Song, W.,Ning, K.(2022).Railway fastener defect detection based on improved YOLOv5 algorithm.2022 IEEE 6th Advanced Information Technology, Electronic and Automation Control Conference (IAEAC)
22. Ultralytics. (2020). “YOLOv5,” from: May 31 2020,https://reurl.cc/MRjyLp
23. Wang, H.,Li, M.,Wan, Z.(2022).Rail surface defect detection based on improved Mask R-CNN.Computers and Electrical Engineering,102,108269.
24. Wu, Z.,Zhang, D.,Shao, Y.,Zhang, X.,Zhang, X.,Feng, Y.,Cui, P.(2021).Using YOLOv5 for Garbage Classification.2021 4th International Conference on Pattern Recognition and Artificial Intelligence (PRAI)
25. Xing, Z.,Zhang, Z.,Yao, X.,Qin, Y.,Jia, L.(2022).Rail wheel tread defect detection using improved YOLOv3.Measurement,203,111959.
26. Yang, Q.,Yan, P.,Zhang, Y.,Yu, H.,Shi, Y.,Mou, X.,Kalra, M. K.,Zhang, Y.,Sun, L.,Wang, G.(2018).Low-Dose CT Image Denoising Using a Generative Adversarial Network With Wasserstein Distance and Perceptual Loss.IEEE Transactions on Medical Imaging,37(6),1348-1357.
27. Yeung, C. C.,Lam, K. M.(2022).Efficient Fused-Attention Model for Steel Surface Defect Detection.IEEE Transactions on Instrumentation and Measurement,71,1-11.
28. Zhu, R.,Guo, Y.,Xue, J.-H.(2020).Adjusting the imbalance ratio by the dimensionality of imbalanced data.Pattern Recognition Letters,133,217-223.
29. 劉佳佩 (2021). “受惠全球經濟復甦，鋼鐵出口可望結束連續 2年負成長,” 2021年 10月 5 日, 取自 https://reurl.cc/ZXVWWA