Journal of the Korea Institute of Information and Communication Engineering (한국정보통신학회논문지)

The Korea Institute of Information and Commucation Engineering (한국정보통신학회)
권호 표지
DOI QR코드

DOI QR Code

Comparative analysis of Machine-Learning Based Models for Metal Surface Defect Detection

머신러닝 기반 금속외관 결함 검출 비교 분석

  • Lee, Se-Hun (Department of Artificial Intelligence, Kyungpook National University) ;
  • Kang, Seong-Hwan (Department of Artificial Intelligence, Kyungpook National University) ;
  • Shin, Yo-Seob (Department of Artificial Intelligence, Kyungpook National University) ;
  • Choi, Oh-Kyu (Artificial Intelligence Research Center, Industry Applications Research Division, Korea Electrotechnology Research Institute (KERI)) ;
  • Kim, Sijong (Artificial Intelligence Research Center, Industry Applications Research Division, Korea Electrotechnology Research Institute (KERI)) ;
  • Kang, Jae-Mo (Department of Artificial Intelligence, Kyungpook National University)
  • Received : 2022.03.19
  • Accepted : 2022.05.22
  • Published : 2022.06.30
Download PDF
⟨ Previous Next ⟩

Abstract

Recently, applying artificial intelligence technologies in various fields of production has drawn an upsurge of research interest due to the increase for smart factory and artificial intelligence technologies. A great deal of effort is being made to introduce artificial intelligence algorithms into the defect detection task. Particularly, detection of defects on the surface of metal has a higher level of research interest compared to other materials (wood, plastics, fibers, etc.). In this paper, we compare and analyze the speed and performance of defect classification by combining machine learning techniques (Support Vector Machine, Softmax Regression, Decision Tree) with dimensionality reduction algorithms (Principal Component Analysis, AutoEncoders) and two convolutional neural networks (proposed method, ResNet). To validate and compare the performance and speed of the algorithms, we have adopted two datasets ((i) public dataset, (ii) actual dataset), and on the basis of the results, the most efficient algorithm is determined.

최근 스마트팩토리와 인공지능 기술의 수요 증가로 인해 다양한 분야에서 인공지능 기술을 적용하는 연구가 진행되고 있다. 결함 검사 분야에서도 인공지능 알고리즘을 도입하기 위한 노력을 기울이고 있다. 특히, 금속 외관의 결함을 검출하는 연구는 다른 소재(목재, 플라스틱, 섬유 등)의 결함을 검출하는 연구에 비해 많은 연구가 이루어지고 있다. 본 논문에서는 머신러닝 기법(서포터 벡터 머신(SVM: Support Vector Machine), 소프트맥스 회귀(Softmax Regression), 결정 트리(Decesion Tree))과 차원 축소 알고리즘(주성분 분석(PCA: Principal Component Analysis), 오토인코더(AutoEncoder))의 9가지 조합과 2가지 합성곱신경망(CNN: Convolutional Neural Network) 기법(자체 알고리즘, ResNet)의 금속 외관의 결함 분류 성능 및 속도를 비교하고 분석하는 연구를 수행하고자 한다. 두 종류의 학습 데이터셋((i) 공용 데이터셋(Public Dataset), (ii) 실측 데이터셋(Actual Dataset))에 대한 실험을 통해 각 데이터셋에 대한 성능 및 속도를 비교 분석하고, 가장 효율적인 알고리즘을 찾아낸다.

Keywords

Acknowledgement

This research was supported by Korea Electrotechnology Research Institute (KERI) Primary research program through the National Research Council of Science & Technology (NST) funded by the Ministry of Science and ICT (MSIT) (No. 22A01019)

References

  1. F. C. Campbell, Inspection of metals: understanding the basics, ASM International, OH: USA, 2013.
  2. X. Li, Y. Zhu, Y. Yi, Y. Ding, and K. Zhu, "Application of vision technology in metal surface defect detection," in 2021 IEEE 2nd International Conference on Information Technology, Big Data and Artificial Intelligence (ICIBA), Chongqing, China, vol. 2, pp. 50-54, 2021.
  3. F. Jia, Y. Lei, N. Lu, and S. Xing, "Deep normalized convolutional neural network for imbalanced fault classification of machinery and its understanding via visualization," Mechanical Systems and Signal Processing, vol. 110, pp. 349-367, Sep. 2018. https://doi.org/10.1016/j.ymssp.2018.03.025
  4. H. Lin and F. S. Wibowo, "Image data assessment approach for deep learning-based metal surface defect-detection systems," IEEE Access, vol. 9, pp. 47621-47638, Mar. 2021. https://doi.org/10.1109/ACCESS.2021.3068256
  5. J. Zhang, S. Li, Y. Yan, Z. Ni, and H. Ni, "Surface Defect Classification of Steel Strip with Few Samples Based on Dual-Stream Neural Network," steel research international, vol. 93, no. 5, 2100554, May. 2021.
  6. W. Zhang, J. Du, X. Li, and W. Wang, "Application of Weighted Object Variance Algorithm in Metal Surface Defect Detection," in IOP Conference Series: Materials Science and Engineering, Yunnan, China, vol. 612. no. 3, Oct. 2019.
  7. M. A. Hearst, S. T. Dumais, E. Osuna, J. Platt, and B. Scholkopf, "Support vector machines," IEEE Intelligent Systems and their Applications, vol. 13, no. 4, pp. 18-28, Jul-Aug. 1998. https://doi.org/10.1109/5254.708428
  8. P. Caleb and M. Steuer, "Classification of surface defects on hot rolled steel using adaptive learning methods," in KES'2000. Fourth International Conference on Knowledge-Based Intelligent Engineering Systems and Allied Technologies. Proceedings(Cat. No. 00TH8516), Brighton, UK, vol. 1, pp. 103-108, 2000.
  9. Md. F. Islam and Md. M. Rahman, "Metal surface defect inspection through deep neural network," in 2018 International Conference on Mechanical, Industrial and Energy Engineering, Khulna, Bangladesh, p. 258, 2018.
  10. Y. Lecun, L. Bottou, Y. Bengio, and P. Haffner, "Gradient-based learning applied todocumentrecognition," in Proceedings of the IEEE, vol. 86, no. 11, pp. 2278-2324, 1998. https://doi.org/10.1109/5.726791
  11. J. S. Bridle, "Training stochastic model recognition algorithms as networks can lead to maximum mutual information estimation of parameters," Advances in neural information processing systems 2, pp. 211-217, Jun. 1990.
  12. J. R. Quinlan, "Induction of decision trees," Machine learning 1.1, vol. 1, pp. 81-106, Mar. 1986. https://doi.org/10.1007/BF00116251
  13. K. He, X. Zhang, S. Ren, and J. Sun, "Deep residual learning for image recognition," in Proceedings of the IEEE conference on computer vision and pattern recognition, Las Vegas: NV, USA, pp. 770-778, 2016.
  14. K. Simonyan and A. Zisserman, "Very deep convolutional networks for large-scale image recognition," arXiv preprint arXiv:1409.1556, Sep. 2014.
  15. Northeastern University Kechen Song's Personal Hompage NEU Surface Defect Database [Internet]. Avaliable: http://faculty.neu.edu.cn/songkc/en/zhym/263264/list/index.htm.