SISTEM INSPEKSI PERMUKAAN BAJA BERBASIS DEEP LEARNING MENGGUNAKAN METODE ANCHOR-FREE
DOI:
https://doi.org/10.51903/juritek.v2i3.364Keywords:
anchor-free, FoveaBox, object detection, single-stage detection, surface defect detectionAbstract
Steel is one of the important materials in the industry. Steel may have defects in the production process that can affect the steel products. Therefore, the detection of steel surface defects is an important process to control the quality of steel products. An efficient steel surface detection process is carried out by automating steel images taken using a camera. We use an anchor-free model FoveaBox. FoveaBox is an accurate and flexible model for detecting objects and has a simple architecture. This study uses the NEU-DET dataset consists of six types of steel surface defects, namely crazing, inclusion, patches, pitted surface, rolled-in scale, and scratches, each with a total of 300 data.. The test results on the system show that the method used has a good detection performance with a mean average precision of 0.834 or 83.4% at a learning rate of 0.001, Optimizer SGD, sigma 0.6, and the number of epochs 24. This detection method can detect steel surface defects. This detection method can effectively detect steel surface defects with similar foreground and background characteristics. With an accuracy threshold of 80%, the method used in this study has an adequate precision value.
References
[2] X. Chen, J. Lv, Y. Fang, dan S. Du, “Online Detection of Surface Defects Based on Improved YOLOV3,” Sensors, vol. 22, no. 3, hal. 817, 2022.
[3] R. Hao, B. Lu, Y. Cheng, X. Li, dan B. Huang, “A steel surface defect inspection approach towards smart industrial monitoring,” J. Intell. Manuf., 2020, doi: 10.1007/s10845-020-01670-2.
[4] C. Y. Lin, C. H. Chen, C. Y. Yang, F. Akhyar, C. Y. Hsu, dan H. F. Ng, “Cascading Convolutional Neural Network for Steel Surface Defect Detection,” Adv. Intell. Syst. Comput., vol. 965, hal. 202–212, 2020, doi: 10.1007/978-3-030-20454-9_20.
[5] Y. He, K. Song, Q. Meng, dan Y. Yan, “An End-to-End Steel Surface Defect Detection Approach via Fusing Multiple Hierarchical Features,” IEEE Trans. Instrum. Meas., vol. 69, no. 4, hal. 1493–1504, 2020, doi: 10.1109/TIM.2019.2915404.
[6] Z. Zou, Z. Shi, Y. Guo, dan J. Ye, “Object detection in 20 years: A survey,” arXiv Prepr. arXiv1905.05055, 2019.
[7] H. Ma, S. T. Acton, dan Z. Lin, “CAT: Centerness-Aware Anchor-Free Tracker,” Sensors (Basel)., vol. 22, no. 1, hal. 354, Jan 2022, doi: 10.3390/s22010354.
[8] Z. Tian, C. Shen, H. Chen, dan T. He, “Fcos: A simple and strong anchor-free object detector,” IEEE Trans. Pattern Anal. Mach. Intell., 2020.
[9] X. Zhou, D. Wang, dan P. Krähenbühl, “Objects as points,” arXiv Prepr. arXiv1904.07850, 2019.
[10] H. Law dan J. Deng, “Cornernet: Detecting objects as paired keypoints,” in Proceedings of the European conference on computer vision (ECCV), 2018, hal. 734–750.
[11] Z. Dong, G. Li, Y. Liao, F. Wang, P. Ren, dan C. Qian, “CentripetalNet: Pursuing High-quality Keypoint Pairs for Object Detection,” Mar 2020, Diakses: Apr 08, 2022. [Daring]. Tersedia pada: http://arxiv.org/abs/2003.09119.
[12] T. Kong, F. Sun, H. Liu, Y. Jiang, L. Li, dan J. Shi, “FoveaBox : Beyound Anchor-Based Object Detection,” vol. 29, hal. 7389–7398, 2020.
[13] J. Gu dkk., “Recent advances in convolutional neural networks,” Pattern Recognit., vol. 77, hal. 354–377, 2018.
[14] Z. Q. Zhao, P. Zheng, S. T. Xu, dan X. Wu, “Object Detection with Deep Learning: A Review,” IEEE Trans. Neural Networks Learn. Syst., vol. 30, no. 11, hal. 3212–3232, 2019, doi: 10.1109/TNNLS.2018.2876865.
[15] H. Andrew dkk., “Searching for mobilenetv3,” in Proceedings of the IEEE International Conference on Computer Vision, 2019, hal. 1314–1324.
[16] K. Chen dkk., “MMDetection: Open mmlab detection toolbox and benchmark,” arXiv Prepr. arXiv1906.07155, 2019.
[17] K. Song dan Y. Yan, “A noise robust method based on completed local binary patterns for hot-rolled steel strip surface defects,” Appl. Surf. Sci., vol. 285, hal. 858–864, 2013, doi: https://doi.org/10.1016/j.apsusc.2013.09.002.
[18] S. Gonzalez, C. Arellano, dan J. E. Tapia, “Deepblueberry: Quantification of blueberries in the wild using instance segmentation,” Ieee Access, vol. 7, hal. 105776–105788, 2019.
[19] P. Malhotra, S. Gupta, D. Koundal, A. Zaguia, M. Kaur, dan H.-N. Lee, “Deep Learning-Based Computer-Aided Pneumothorax Detection Using Chest X-ray Images,” Sensors (Basel)., vol. 22, no. 6, hal. 2278, Mar 2022, doi: 10.3390/s22062278.
.png)
