Abstract
A strip steel surface defect detection method called YOLOv5-ABS is developed in order to address the issues of low detection accuracy, insufficient feature extraction ability, and insufficient feature fusion of YOLOv5. Firstly, in order to enhance the backbone network's capacity for feature extraction, the C3 module is swapped out for the SeC3 module with an attention mechanism. Secondly, in order to improve the network feature fusion capability, the bidirectional weighted feature pyramid network BiFPN is added in the Neck section. Finally, by introducing the SPPFCSPC spatial pyramid pooling structure, speed and accuracy are improved while kee** the receptive field unchanged. According to the experimental findings, the revised YOLOv5-ABS algorithm’s mAP on the NEU-DET dataset is 78.6%, 3.8% larger compared to the initial YOLOv5s algorithm, and the detection speed is 142.8 FPS, enabling the quick and precise identification of strip steel surface defects.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Li YJ, Zhu PY, Sun XP (2017) Shape defect detection algorithm of stam** parts based on shape template matching. J Guangzhou Univ (Natural Science Edition) 16(5):62–66
Liu Y, **a CL (2021) An image edge detection algorithm for strip steel surface defects based on Sobel opera-tor. Electronic Measurement Technol 44(3):138–143
Liu L, Wang C, Zhao SW (2018) Research on solar cells defect detection technology based on machine vision. J Electronic Measurement Instrument 32(10):47–52
Zhang T, Liu YT, Yang YN (2020) Review of surface defect detection based on machine vision. Sci Technol Eng 20(35):14366–14376
Dai XH, Chen HJ, Zhu CP (2020) Surface defect detection and realization of metal workpiece based on improved faster RCNN. Surface Technol 49(10):362–371
Kou XP, Liu SJ, Cheng KQ (2021) Development of a YOLO-V3-based model for detecting defects on steel strip surface. Measurement 182(2):109–119
Zhang BY, Leng YB (2022) Detection of metal surface scratch based on YOLOv4 network model. Acta Armamentarii 43(1):214–221
Wang K, Teng ZX, Zou TY (2022) Metal defect detection based on Yolov5. J Phys: Conf Ser 2218(1):120–128
Shao Y, Zhang D, Chu H (2022) A review of YOLO object detection based on deep learning. J Electron Inf Technol 44(2):1–12
Hu J, Shen L, Albanie S (2020) Squeeze-and-excitation networks. IEEE Trans Pattern Anal Mach Intell 42(8):2011–2023
Lin TY, Dollar P, Girshick R (2017) Feature pyramid networks for object detection. In: Computer vision and pattern recognition
Liu S, Qi L, Qin H (2018) Path aggregation network for instance segmentation
Tan M, Pang R, Le QV (2020) EfficientDet: scalable and efficient object detection. In: IEEE conference on computer vision and pattern recognition
He TJ, Li H (2023) The pavement damage detection model based on improved YOLOv5. Chin Civil Eng J 17(2):1–12
Acknowledgements
This work was also supported by The Key project of natural science research in colleges and universities of Anhui Province (2022AH052365, KJ2020A1102) and Wuhu Engineering Technology Research Center (KJCXPT202204) and The Open Research Fund of Anhui Province Key Laboratory of Machine Vision Inspection.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Wang, B., Juanatas, R., Niguidula, J., Luo, H. (2024). Surface Defect Detection Method of Strip Steel Based on Improved YOLOv5. In: Wang, W., Liu, X., Na, Z., Zhang, B. (eds) Communications, Signal Processing, and Systems. CSPS 2023. Lecture Notes in Electrical Engineering, vol 1032. Springer, Singapore. https://doi.org/10.1007/978-981-99-7505-1_27
Download citation
DOI: https://doi.org/10.1007/978-981-99-7505-1_27
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-7539-6
Online ISBN: 978-981-99-7505-1
eBook Packages: EngineeringEngineering (R0)