Strip Defect Classification Based on Improved Generative Adversarial Networks and MobileNetV3

Jiang Chang; Shengqi Guan; Hongyu Shi; Luping Hu; Yiqi Ni

doi:10.3788/LOP202158.0410016

[1] Ghorai S, Mukherjee A, Gangadaran M et al. Automatic defect detection on hot-rolled flat steel products[J]. IEEE Transactions on Instrumentation and Measurement, 62, 612-621(2013).

[2] Neogi N, Mohanta D K, Dutta P K. Review of vision-based steel surface inspection systems[J]. EURASIP Journal on Image and Video Processing, 2014, 1-19(2014).

[3] Saito K, Ushiku Y, Harada T et al. Strong-weak distribution alignment for adaptive object detection[C]∥2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 15-20, 2019, Long Beach, CA, USA., 6949-6958(2019).

[4] Yang F, Fan H, Chu P et al. Clustered object detection in aerial images[C]∥2019 IEEE/CVF International Conference on Computer Vision (ICCV), October 27-November 2, 2019, Seoul, Korea (South)., 8310-8319(2019).

[5] Yan Z Y, Yuan Y C, Zuo W M et al. Perspective-guided convolution networks for crowd counting[C]∥2019 IEEE/CVF International Conference on Computer Vision (ICCV), October 27-November 2, 2019, Seoul, Korea (South)., 952-961(2019).

[6] Shen X H, Li Z H, Li M et al. Aluminum surface-defect detection based on multi-task deep learning[J]. Laser & Optoelectronics Progress, 57, 101501(2020).

[7] Zhang G S, Ge G Y, Zhu R H et al. Gear defect detection based on the improved YOLOv3 network[J]. Laser & Optoelectronics Progress, 57, 121009(2020).

[8] Liu F, Wu Z W, Yang A Z et al. Multi-scale feature fusion based adaptive object detection for UAV[J]. Acta Optica Sinica, 40, 1015002(2020).

[9] Bengio Y, Delalleau O. On the expressive power of deep architectures[M]. ∥Elomaa T, Hollmén J, Mannila H, et al. Discovery Science. DS 2011. Lecture Notes in Computer Science. Berlin, Heidelberg: Springer, 6926, 1(2011).

[10] Vannocci M, Ritacco A, Castellano A et al. Flatness defect detection and classification in hot rolled steel strips using convolutional neural networks. [C]∥15th International Work Conference on Artificial Neural Networks(IWANN),June 12-14,2019,Gran Canaria, Spain. Cham: Springer, 220-234(2019).

[11] Wang L Z, Guan S Q. Strip steel surface defect recognition based on deep learning[J]. Journal of Xi'an Polytechnic University, 31, 669-674(2017).

[12] Mi Z S, Song Y H, Yan Y. A defect classification network based on deformation dense connection in wire rod surface image[C]∥2019 2nd China Symposium on Cognitive Computing and Hybrid Intelligence (CCHI), September 21-22, 2019, 155-160(2019).

[13] Liu S Y, Guo H Y, Hu J G et al. A novel data augmentation scheme for pedestrian detection with attribute preserving GAN[J]. Neurocomputing, 401, 123-132(2020). http://www.sciencedirect.com/science/article/pii/S0925231220302903

[14] Goodfellow I, Pouget-Abadie J, Mirza M et al. Generative adversarial nets[C]∥27th International Conference on Neural Information Processing Systems(NIPS), December 8-13, 2014, Montreal, Canada., 2672-2680(2014).

[15] Mirza M, Osindero S[2020-06-20]. Conditional generative adversarial nets [2020-06-20].https:∥arxiv., org/abs/1411, 1784.

[16] Radford A, Metz L, Chintala S[2020-06-24]. Unsupervised representation learning with deep convolutional generative adversarial networks [2020-06-24].https:∥arxiv., org/abs/1511, 06434.

[17] Xuan Q, Chen Z Z, Liu Y et al. Multiview generative adversarial network and its application in pearl classification[J]. IEEE Transactions on Industrial Electronics, 66, 8244-8252(2019). http://ieeexplore.ieee.org/document/8575147

[18] Yi C, Cho J. Improving the performance of multimedia pedestrian classification with images synthesized using a deep convolutional generative adversarial network[J]. Multimedia Tools and Applications, 89, 1-16(2020).

[19] Odena A, Olah C, Shlens J[2020-06-21]. Conditional image synthesis with auxiliary classifier GANs [2020-06-21].https:∥arxiv., org/abs/1610, 09585.

[20] Howard A, Sandler M, Chen B et al. Searching for MobileNetV3[C]∥2019 IEEE/CVF International Conference on Computer Vision (ICCV), October 27-November 2, 2019, Seoul, Korea (South)., 1314-1324(2019).

[21] Song K C, Yan Y H. A noise robust method based on completed local binary patterns for hot-rolled steel strip surface defects[J]. Applied Surface Science, 285, 858-864(2013).