Metal parçaların yüzey kusurlarını tespit için k-dedektörü ile küçük nesne tespit yöntemi

Year 2024, , 538 - 549, 15.06.2024

Yavuz Selim Balcıoğlu

https://doi.org/10.17714/gumusfenbil.1391054

Abstract

Gelişim sürecinde, akıllı imalat genellikle üretim esnekliğine, müşteriye özel üretime ve kalite kontrolüne odaklanmaktadır, bunların hepsi toz bazlı metalurji üretimi için gereklidir. Özellikle, toz bazlı metalurjide üretim süreçlerinde hataların tespiti ve kategorize edilmesi kritik adımlardır. Metal parçalardaki hataları tespit etmek için akıllı stratejiler, otomatik endüstriyel üretim hatlarında hala bir meydan okumadır. Bu teknikler, özellikle mikroskopik metal bileşen üreticileri için uzun zamandır özel bir endişe kaynağı olmuştur. Hassasiyeti ve hızı nedeniyle, YOLOv4 yaklaşımı nesne tespiti amacıyla yaygın olarak kullanılmıştır. Öte yandan, özellikle metal parçaların yüzeyindeki kusurlar gibi küçük hedeflerin tanımlanması, birçok engel ve zorluk sunmaya devam etmektedir. Bu araştırma, tespit performansını genel olarak artırmak için, YOLOv4'e dayalı küçük nesnelerin tespiti için bir teknik sunmaktadır. Tespit sürecinin etkinliğini artırmak için, bu, YOLO baş ağının gereksiz dallarının kaldırılması ile k detektörünün boyutunun genişletilmesini içermektedir. Deneyler, KD-YOLO modelinin toplam parametre sayısı, sınıflandırma doğruluğu ve tespit hassasiyeti açısından önceki modelleri YOLOv4, YOLOv5 ve PP-YOLO'dan daha iyi performans gösterdiğini göstermiştir.

Keywords

Obje tanıma, Yüzey tespiti, Kalite kontrol

Small object detection method with k-detector for metal parts surface defect detection

Abstract

In the process of its development, intelligent manufacturing often focuses on production flexibility, client customization, and quality control, all of which are required for the manufacture of powder-based metallurgy. In particular, the identification and categorization of defects are crucial steps in the production processes involved in powder-based metallurgy. Intelligent strategies to detect faults in metal parts continue to be a challenge in automated industrial production lines. These techniques have been a particular concern for microscopic metal component producers for a long time. Due to its precision and speed, the YOLOv4 approach has been widely used for object detection. On the other hand, the identification of tiny targets, particularly imperfections on the surface of metal parts, continues to present a number of obstacles and difficulties. To increase the overall performance of detection, this research provided a technique for the detection of tiny objects based on YOLOv4 for such objects. To increase the effectiveness of the detection process, this involves expanding the size of the k detector while simultaneously eliminating unnecessary branches of the YOLO head network. Experiments have shown that the KD-YOLO model performs better than its predecessors, YOLOv4, YOLOv5, and PP-YOLO, in terms of the total number of parameters, classification accuracy and detection precision.

Keywords

Object detection, Surface detection, Quality control

References

• Atwood, J., & Towsley, D. (2016). Diffusion-convolutional neural networks. Advances in neural information processing systems, 29.
• Cao, D., Dang, J., & Zhong, Y. (2021). Towards accurate scene text detection with bidirectional feature pyramid network. Symmetry, 13(3), 486.
• Cao, Z., Yang, H., Zhao, J., Pan, X., Zhang, L., & Liu, Z. (2019). A new region proposal network for far-infrared pedestrian detection. IEEE Access, 7, 135023-135030.
• Chi, W., Ma, L., Wu, J., Chen, M., Lu, W., & Gu, X. (2020). Deep learning-based medical image segmentation with limited labels. Physics in Medicine & Biology, 65(23), 235001.
• Chu, P., Li, Z., Lammers, K., Lu, R., & Liu, X. (2021). Deep learning-based apple detection using a suppression mask R-CNN. Pattern Recognition Letters, 147, 206-211.
• Girshick, R. (2015). Fast r-cnn. In Proceedings of the IEEE international conference on computer vision (pp. 1440-1448).
• He, K., Zhang, X., Ren, S., & Sun, J. (2015). Spatial pyramid pooling in deep convolutional networks for visual recognition. IEEE transactions on pattern analysis and machine intelligence, 37(9), 1904-1916.
• He, K., Girshick, R., & Dollár, P. (2019). Rethinking imagenet pre-training. In Proceedings of the IEEE/CVF International Conference on Computer Vision (pp. 4918-4927).
• Liao, X., Lv, S., Li, D., Luo, Y., Zhu, Z., & Jiang, C. (2021). YOLOv4-MN3 for PCB surface defect detection. Applied Sciences, 11(24), 11701.
• Lin, T. Y., Dollár, P., Girshick, R., He, K., Hariharan, B., & Belongie, S. (2017). Feature pyramid networks for object detection. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 2117-2125).
• Liu, S., Qi, L., Qin, H., Shi, J., & Jia, J. (2018). Path aggregation network for instance segmentation. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 8759-8768).
• Liu, Y., Wang, Q., Zhao, K., & Liu, Y. (2021). Real-time defect detection of hot rolling steel bar based on convolution neural network. Chin. J. Sci. Instrum, 42, 211-219.
• MathWorks.com (2019) ‘R-cnn, fast r-cnn, and faster r-cnn basics’, ©1994-2019 The MathWorks, Inc.
• Monteiro, A. M., Vale, J. M., Cepêda, C. M., & de Almeida Leite, E. M. (2021). Internal control system quality and decision-making success: The role of the financial information quality. Universal Journal of Accounting and Finance, 8(10), 3310-3322.
• Panda, A., Dobránsky, J., Jančík, M., Pandová, I., & Kačalová, M. (2018). Advantages and effectiveness of the powder metallurgy in manufacturing technologies. Metalurgija, 57(4), 353-356.
• Parico, A. I. B., & Ahamed, T. (2021). Real time pear fruit detection and counting using YOLOv4 models and deep SORT. Sensors, 21(14), 4803.
• Punn, N. S., & Agarwal, S. (2020). Inception u-net architecture for semantic segmentation to identify nuclei in microscopy cell images. ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM), 16(1), 1-15.
• Silvius, A. J., & Schipper, R. P. (2014). Sustainability in project management: A literature review and impact analysis. Social business, 4(1), 63-96.
• Śmietańska, K., & Podziewski, P. (2019). A human quality control system in furniture manufacturing–a pilot study. Annals of Warsaw University of Life Sciences SGGW Forestry and Wood Technology, 108, 93-96.
• Wang, C., & Zhong, C. (2021). Adaptive feature pyramid networks for object detection. IEEE Access, 9, 107024-107032.