An Improved VGG19 Transfer Learning Strip Steel Surface Defect Recognition Deep Neural Network Based on Few Samples and Imbalanced Datasets
Source abstract
Abstract
The surface defects’ region of strip steel is small, and has various defect types and, complex gray structures. There tend to be a large number of false defects and edge light interference, which lead traditional machine vision algorithms to be unable to detect defects for various types of strip steel. Image detection techniques based on deep learning require a large number of images to train a network. However, for a dataset with few samples with category imbalanced defects, common deep learning neural network training tasks cannot be carried out. Based on rapid image preprocessing algorithms (improved gray projection algorithm, ROI image augmentation algorithm) and transfer learning theory, this paper proposes a set of processes for complete strip steel defect detection. These methods achieved surface rapid screening, defect feature extraction, sample dataset’s category balance, data augmentation, defect detection, and classification. Through verification of the mixed dataset, composed of the NEU surface dataset and dataset in this paper, the recognition accuracy of the improved VGG19 network in this paper reached 97.8%. The improved VGG19 network performs slightly better than the baseline VGG19 in six types of defects, but the improved VGG19 performs significantly better in the surface seams defects. The convergence speed and accuracy of the improved VGG19 network were taken into account, and the detection rate was greatly improved with few samples and imbalanced datasets. This paper also has practical value in terms of extending its method of strip steel defect detection to other products.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Industrial Vision Systems and Defect Detection · Infrastructure Maintenance and Monitoring · Surface Roughness and Optical Measurements
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Shanghai Key Laboratory of Intelligent Manufacturing and Robotics, Shanghai University, Shanghai 200444, China
Funding
The construction of professional CPS test and verification bed for the application of steel rolling process
References (48)
Show source-provided references
1. Nondestructive testing technique for strip surface defects and its applications
2. Tian, S., and Xu, K. (2017). An Algorithm for Surface Defect Identification of Steel Plates Based on Genetic Algorithm and Extreme Learning Machine. Metals, 7.10.3390/met7080311 ↗
3. FDAS: A Knowledge-based Framework for Analysis of Defects in Woven Textile Structures10.1080/00405009208631217 ↗
4. Yin, X., Yu, X., Sohn, K., Liu, X., and Chandraker, M. (2019, January 15–20). Feature Transfer Learning for Face Recognition with Under-Represented Data. Proceedings of the 2019 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA.10.1109/CVPR.2019.00585 ↗
5. Cui, Y., Jia, M., Lin, T.Y., Song, Y., and Belongie, S. (2019, January 15–20). Class-Balanced Loss Based on Effective Number of Samples. Proceedings of the 2019 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA.10.1109/CVPR.2019.00949 ↗
6. Fang, X., Luo, Q., Zhou, B., Li, C., and Tian, L. (2020). Research Progress of Automated Visual Surface Defect Detection for Industrial Metal Planar Materials. Sensors, 20.10.3390/s20185136 ↗
7. Improved sobel algorithm for defect detection of rail surfaces with enhanced efficiency and accuracy10.1007/s11771-016-3350-3 ↗
8. A surface defects inspection method based on multidirectional gray-level fluctuation10.1177/1729881417703114 ↗
9. A comparative study of texture measures with classification based on feature distributions10.1016/0031-3203(95)00067-4 ↗
10. Jeon, Y., Yun, J., Choi, D., and Kim, S.W. (2009, January 18–21). Defect detection algorithm for corner cracks in steel billet using discrete wavelet transform. Proceedings of the ICROS-SICE International Joint Conference, Fukuoka, Japan.
11. Surface Defect Classification in Large-scale Strip Steel Image Collection via Hybrid Chromosome Genetic Algorithm10.1016/j.neucom.2015.05.134 ↗
12. Yazdchi, M., Yazdi, M., and Mahyari, A.G. (2009, January 7–9). Steel surface defect detection using texture segmentation based on multifractal dimension. Proceedings of the International Conference on Digital Image Processing (ICDIP), Bangkok, Thailand.10.1109/ICDIP.2009.68 ↗
13. Filter-based feature selection for rail defect detection10.1007/s00138-004-0148-3 ↗
14. Steel Surface Defect Recognition Based on Support Vector Machine and Image Processing
15. Chu, M., Zhao, J., Gong, R., and Liu, L. (2017, January 28–30). Steel surface defects recognition based on multi-label classifier with hyper-sphere support vector machine. Proceedings of the Control and Decision Conference (CCDC), Chongqing, China.10.1109/CCDC.2017.7979072 ↗
16. Fast defect detection for various types of surfaces using random forest with VOV features10.1007/s12541-015-0125-y ↗
17. Masci, J., Meier, U., Ciresan, D., Schmidhuber, J., and Fricout, G. (2012, January 10–15). Steel defect classification with Max-Pooling Convolutional Neural Networks. Proceedings of the 2012 International Joint Conference on Neural Networks (IJCNN), Brisbane, QLD, Australia.10.1109/IJCNN.2012.6252468 ↗
18. A semi-supervised convolutional neural network-based method for steel surface defect recognition10.1016/j.rcim.2019.101825 ↗
19. Real-time Detection of Steel Strip Surface Defects Based on Improved YOLO Detection Network
20. Geirhos, R., Rubisch, P., Michaelis, C., Bethge, M., Wichmann, F.A., and Brendel, W. (2019, January 6–9). ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness. Proceedings of the International Conference on Learning Representations (ICLR 2019), New Orleans, LA, USA.
21. Kim, S., Kim, W., Noh, Y.K., and Park, F.C. (2017, January 14–19). Transfer learning for automated optical inspection. Proceedings of the International Joint Conference on Neural Networks, Anchorage, AK, USA.10.1109/IJCNN.2017.7966162 ↗
22. An End-to-End Steel Surface Defect Detection Approach via Fusing Multiple Hierarchical Features10.1109/TIM.2019.2915404 ↗
23. Autonomous concrete crack detection using deep fully convolutional neural network10.1016/j.autcon.2018.11.028 ↗
24. Deep transfer network with joint distribution adaptation: A new intelligent fault diagnosis framework for industry application10.1016/j.isatra.2019.08.012 ↗
25. DNN Transfer learning based non-linear feature extraction for acoustic event classification10.1587/transinf.2017EDL8048 ↗
26. Wind power prediction using deep neural network based meta regression and transfer learning10.1016/j.asoc.2017.05.031 ↗
27. Simonyan, K., and Zisserman, A. (2015, January 7–9). Very deep convolutional networks for large-scale image recognition. Proceedings of the 3rd International Conference on Learning Representations (ICLR 2015), San Diego, CA, USA.
28. Zhang, J., and Mani, I. (2003, January 21). KNN Approach to Unbalanced Data Distributions: A Case Study Involving Information Extraction. Proceedings of the ICML’2003 Workshop on Learning from Imbalanced Datasets, Washington, DC, USA.
29. He, H., Bai, Y., Garcia, E.A., and Li, S. (2008, January 1–8). ADASYN: Adaptive Synthetic Sampling Approach for Imbalanced Learning. Proceedings of the 2008 IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence), Hong Kong, China.
30. A study of the behavior of several methods for balancing machine learning training data10.1145/1007730.1007735 ↗
31. Elkan, C. (2001, January 4–10). The foundations of cost-sensitive learning. Proceedings of the Seventeenth International Conference on Artificial Intelligence, Seattle, USA.
32. Liu, X.Y., and Zhou, Z.H. (2006, January 18–22). The Influence of Class Imbalance on Cost-Sensitive Learning: An Empirical Study. Proceedings of the 6th IEEE International Conference on Data Mining (ICDM 2006), Hong Kong, China.10.1109/ICDM.2006.158 ↗
33. Wang, S., and Yao, X. (April, January 30). Diversity Analysis on Imbalanced Data Sets by Using Ensemble Models. Proceedings of the IEEE Symposium on Computational Intelligence and Data Mining, CIDM 2009, part of the IEEE Symposium Series on Computational Intelligence 2009, Nashville, TN, USA.10.1109/CIDM.2009.4938667 ↗
34. Exploratory Undersampling for Class-Imbalance Learning10.1109/TSMCB.2008.2007853 ↗
35. Shrivastava, A., Gupta, A., and Girshick, R. (2016, January 27–30). Training Region-Based Object Detectors with Online Hard Example Mining. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.10.1109/CVPR.2016.89 ↗
36. Li, M., Zhang, Z., Yu, H., Chen, X., and Li, D. (2017, January 11–14). S-OHEM: Stratified Online Hard Example Mining for Object Detection. Proceedings of the Chinese Conference on Computer Vision, Tianjin, China.10.1007/978-981-10-7305-2_15 ↗
37. Wang, X., Shrivastava, A., and Gupta, A. (2017, January 21–26). A-Fast-RCNN: Hard Positive Generation via Adversary for Object Detection. Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.10.1109/CVPR.2017.324 ↗
38. Lin, T.Y., Goyal, P., Girshick, R., He, K., and Dollár, P. (2017, January 22–29). Focal Loss for Dense Object Detection. Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy.10.1109/ICCV.2017.324 ↗
39. Li, B., Liu, Y., and Wang, X. (February, January 27). Gradient Harmonized Single-stage Detector. Proceedings of the Thirty-Third AAAI Conference on Artificial Intelligence (AAAI2019), Hilton Hawaiian Village, Honolulu, HI, USA.10.1609/aaai.v33i01.33018577 ↗
40. (2021, January 08). NEU Surface Defect Database. Available online: http://faculty.neu.edu.cn/yunhyan/NEU_surface_defect_database.html.
41. Springer Nature Editorial (2016). More accountability for big-data algorithms. Nature, 537, 449.10.1038/537449a ↗
42. Ghiasi, G., Lin, T.Y., and Le, Q.V. (2018, January 2–8). DropBlock: A regularization method for convolutional networks. Proceedings of the 32nd Conference on Neural Information Processing Systems (NIPS), Montreal, QC, Canada.
43. Singh, K.K., and Lee, Y.J. (2017, January 22–29). Hide-and-Seek: Forcing a Network to be Meticulous for Weakly-supervised Object and Action Localization. Proceedings of the 16th IEEE International Conference on Computer Vision (ICCV), Venice, Italy.10.1109/ICCV.2017.381 ↗
44. Zhao, Z., Li, B., and Dong, R. (2018, January 28–31). A Surface Defect Detection Method Based on Positive Samples. Proceedings of the 5th Pacific Rim International Conference on Artificial Intelligence (PRICAI), Nanjing, China.10.1007/978-3-319-97310-4_54 ↗
45. Sun, C., Shrivastava, A., Singh, S., and Gupta, A. (2017, January 22–29). Revisiting Unreasonable Effectiveness of Data in Deep Learning Era. Proceedings of the 16th IEEE International Conference on Computer Vision (ICCV), Venice, Italy.10.1109/ICCV.2017.97 ↗
46. Liu, L., Jiang, H., He, P., Chen, W., Liu, X., Gao, J., and Han, J. (2020, January 26–30). On the Variance of the Adaptive Learning Rate and Beyond. Proceedings of the International Conference on Learning Representations (ICLR 2020), Addis Ababa, Ethiopia.
47. Surface defect classification of steels with a new semi-supervised learning method10.1016/j.optlaseng.2019.01.011 ↗
48. Real-time system for automatic cold strip surface defect detection10.5937/fmet1904765K ↗