{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T08:52:49Z","timestamp":1781599969512,"version":"3.54.5"},"reference-count":53,"publisher":"PeerJ","license":[{"start":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T00:00:00Z","timestamp":1781568000000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Anhui Province University Major Science and Technology Project","award":["2024AH040229"],"award-info":[{"award-number":["2024AH040229"]}]},{"name":"Anhui Provincial University Key Science and Technology Project","award":["2024AH053415"],"award-info":[{"award-number":["2024AH053415"]}]},{"name":"Tongling University School-Level Scientific Research Plan Project, Provincial-level Scientific Research Platform Special Key Project","award":["2023tlxyptZD04"],"award-info":[{"award-number":["2023tlxyptZD04"]}]},{"name":"Excellent Innovative Research Team of Universities in Anhui Province","award":["2023AH010056"],"award-info":[{"award-number":["2023AH010056"]}]},{"name":"Research on Key Technologies for Intelligent Decision Making in Copper Processing Production Lines Driven by Manufacturing Big Data","award":["GXXT-2023-050"],"award-info":[{"award-number":["GXXT-2023-050"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"abstract":"<jats:p>The surface quality of shaped copper strips plays an essential role in the quality of the product. Currently, detecting defects on shaped copper strips primarily relies on manual visual inspection. However, inspectors\u2019 subjective judgment and fatigue may affect the inspection results, leading to poor inspection accuracy and high misdetection rates. This study proposes an algorithm (YOLOv8-cop) to mitigate these issues. Considering the scarcity of datasets, a defect dataset of shaped copper strips was first constructed based on real scenarios, and data augmentation was employed to expand the dataset. Then, the algorithm introduces Adaptive Spatial Feature Fusion (ASFF) to optimize the model detection head, minimizing information loss during multi-layer feature transfer and improving target defect detection ability. A lightweight slim-neck module was used to replace the original YOLOv8\u2019s neck module, thereby reducing computational complexity. Furthermore, the Inner-SIoU was utilized to improve the model\u2019s ability to identify small defects on the surface of shaped copper strips. The proposed algorithm increased the mean Average Precision (mAP) by 4.3% over the original YOLOv8\u00a0model. Compared with YOLOv5n, YOLOv7, and YOLOv10n, YOLOv8-cop improved mAP@0.5 by 3.9, 38.0, and 7.5 percentage points, respectively. Meanwhile, this algorithm surpasses the YOLOv8\u00a0model in detection speed, satisfying the real-time inspection of shaped copper strip.<\/jats:p>","DOI":"10.7717\/peerj-cs.3771","type":"journal-article","created":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T08:07:00Z","timestamp":1781597220000},"page":"e3771","source":"Crossref","is-referenced-by-count":0,"title":["YOLOv8-cop: an improved YOLOv8-based surface defect detection algorithm for special-shaped copper strips"],"prefix":"10.7717","volume":"12","author":[{"given":"Fucheng","family":"Wang","sequence":"first","affiliation":[{"name":"Tongling University, School of Mathematics and Computer Science, Tongling, Anhui, China"},{"name":"Tongling University, Anhui Engineering Research Center of Intelligent Manufacturing of Copper-based Materials, Tongling, Anhui, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenqian","family":"Zhang","sequence":"additional","affiliation":[{"name":"Tongling University, School of Mathematics and Computer Science, Tongling, Anhui, China"},{"name":"Tongling University, Anhui Engineering Research Center of Intelligent Manufacturing of Copper-based Materials, Tongling, Anhui, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ming","family":"Chen","sequence":"additional","affiliation":[{"name":"Tongling University, School of Mathematics and Computer Science, Tongling, Anhui, China"},{"name":"Tongling University, Anhui Engineering Research Center of Intelligent Manufacturing of Copper-based Materials, Tongling, Anhui, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gen","family":"Liu","sequence":"additional","affiliation":[{"name":"Anhui Luke Optoelectronic Technology Co., Ltd, Tongling, Anhui, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhiyue","family":"Shi","sequence":"additional","affiliation":[{"name":"Henan Normal University, College of Software, Xinxiang, Henan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ping","family":"Qi","sequence":"additional","affiliation":[{"name":"Tongling University, School of Mathematics and Computer Science, Tongling, Anhui, China"},{"name":"Tongling University, Anhui Engineering Research Center of Intelligent Manufacturing of Copper-based Materials, Tongling, Anhui, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"4443","published-online":{"date-parts":[[2026,6,16]]},"reference":[{"key":"10.7717\/peerj-cs.3771\/ref-1","doi-asserted-by":"publisher","first-page":"103551","DOI":"10.1016\/j.compind.2021.103551","article-title":"Improved faster R-CNN for fabric defect detection based on Gabor filter with genetic algorithm optimization","volume":"134","author":"Chen","year":"2022","journal-title":"Computers in Industry"},{"issue":"1","key":"10.7717\/peerj-cs.3771\/ref-2","doi-asserted-by":"publisher","first-page":"107917","DOI":"10.1016\/j.compbiomed.2024.107917","article-title":"Accurate leukocyte detection based on deformable-DETR and multi-level feature fusion for aiding diagnosis of blood diseases","volume":"170","author":"Chen","year":"2024","journal-title":"Computers in Biology and Medicine"},{"key":"10.7717\/peerj-cs.3771\/ref-3","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2101.03697","article-title":"RepVGG: making VGG-style ConvNets great again","author":"Ding","year":"2021"},{"issue":"18","key":"10.7717\/peerj-cs.3771\/ref-4","doi-asserted-by":"publisher","first-page":"5315","DOI":"10.3390\/s20185315","article-title":"Detecting defects on solid wood panels based on an improved SSD algorithm","volume":"20","author":"Ding","year":"2020","journal-title":"Sensors"},{"key":"10.7717\/peerj-cs.3771\/ref-5","doi-asserted-by":"publisher","first-page":"31","DOI":"10.16629\/j.cnki.1674-2796.2024.04.007","article-title":"A fast defect detection algorithm for labels based on improved template matching","volume":"4","author":"Fang","year":"2024","journal-title":"Electric Tools"},{"key":"10.7717\/peerj-cs.3771\/ref-6","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2205.12740","article-title":"SIoU loss: more powerful learning for bounding box regression","author":"Gevorgyan","year":"2022"},{"key":"10.7717\/peerj-cs.3771\/ref-7","doi-asserted-by":"publisher","first-page":"580","DOI":"10.1109\/CVPR.2014.81","article-title":"Rich feature hierarchies for accurate object detection and semantic segmentation","author":"Girshick","year":"2014"},{"issue":"2","key":"10.7717\/peerj-cs.3771\/ref-8","doi-asserted-by":"publisher","first-page":"397","DOI":"10.53106\/160792642022032302018","article-title":"Detection method of photovoltaic panel defect based on improved mask R-CNN","volume":"23","author":"Guo","year":"2022","journal-title":"Journal of Internet Technology"},{"key":"10.7717\/peerj-cs.3771\/ref-9","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1703.06870","article-title":"Mask R-CNN","author":"He","year":"2018"},{"issue":"10","key":"10.7717\/peerj-cs.3771\/ref-10","doi-asserted-by":"publisher","first-page":"1817","DOI":"10.3390\/electronics13101817","article-title":"Automotive parts defect detection based on YOLOv7","volume":"13","author":"Huang","year":"2024","journal-title":"Electronics"},{"issue":"3","key":"10.7717\/peerj-cs.3771\/ref-11","doi-asserted-by":"publisher","first-page":"52","DOI":"10.1007\/s11554-024-01415-x","article-title":"Deeplab-YOLO: a method for detecting hot-spot defects in infrared image PV panels by combining segmentation and detection","volume":"21","author":"Lei","year":"2024","journal-title":"Journal of Real-Time Image Processing"},{"key":"10.7717\/peerj-cs.3771\/ref-12","article-title":"Research on key technology of surface defect detection in aluminum\/copper strip","author":"Li","year":"2019"},{"issue":"3","key":"10.7717\/peerj-cs.3771\/ref-13","doi-asserted-by":"publisher","first-page":"62","DOI":"10.1007\/s11554-024-01436-6","article-title":"Slim-neck by GSConv: a lightweight-design for real-time detector architectures","volume":"21","author":"Li","year":"2024","journal-title":"Journal of Real-Time Image Processing"},{"key":"10.7717\/peerj-cs.3771\/ref-14","doi-asserted-by":"publisher","first-page":"12147","DOI":"10.1088\/1742-6596\/1069\/1\/012147","article-title":"Cracked insulator detection based on R-FCN","volume":"1069","author":"Li","year":"2018","journal-title":"Journal of Physics: Conference Series"},{"key":"10.7717\/peerj-cs.3771\/ref-15","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1512.02325","article-title":"SSD: single shot multibox detector","author":"Liu","year":"2016"},{"key":"10.7717\/peerj-cs.3771\/ref-16","doi-asserted-by":"publisher","first-page":"209","DOI":"10.1007\/978-3-030-73216-5_15","article-title":"Surface defect detection method of hot rolling strip based on improved SSD model","volume-title":"Database Systems for Advanced Applications. DASFAA 2021 International Workshops","volume":"12680","author":"Liu","year":"2021"},{"key":"10.7717\/peerj-cs.3771\/ref-17","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1911.09516","article-title":"Learning spatial fusion for single-shot object detection","author":"Liu","year":"2019"},{"key":"10.7717\/peerj-cs.3771\/ref-18","doi-asserted-by":"publisher","first-page":"337","DOI":"10.16559\/j.cnki.2095-2295.2023.04.007","article-title":"Simulation of electromagnetic ultrasonic and eddy current composite detection probe","volume":"42","author":"Liu","year":"2023","journal-title":"Journal of Inner Mongolia University of Science and Technology"},{"issue":"3","key":"10.7717\/peerj-cs.3771\/ref-19","doi-asserted-by":"publisher","first-page":"35701","DOI":"10.1088\/1361-6501\/aca34a","article-title":"Low-pass U-Net: a segmentation method to improve strip steel defect detection","volume":"34","author":"Liu","year":"2022","journal-title":"Measurement Science and Technology"},{"issue":"4","key":"10.7717\/peerj-cs.3771\/ref-20","doi-asserted-by":"publisher","first-page":"701","DOI":"10.3390\/pr10040701","article-title":"Object detection algorithm for surface defects based on a novel YOLOv3\u00a0model","volume":"10","author":"Lv","year":"2022","journal-title":"Processes"},{"key":"10.7717\/peerj-cs.3771\/ref-21","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2307.07662","article-title":"MPDIoU: a loss for efficient and accurate bounding box regression","author":"Ma","year":"2023"},{"key":"10.7717\/peerj-cs.3771\/ref-22","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1912.01703","article-title":"PyTorch: an imperative style, high performance deep learning library","author":"Paszke","year":"2019"},{"issue":"2","key":"10.7717\/peerj-cs.3771\/ref-23","doi-asserted-by":"publisher","first-page":"100","DOI":"10.19721\/j.cnki.1001-7372.2024.02.009","article-title":"Intelligent recognition of multiple diseases in steel bridges based on improved mask R-CNN","volume":"37","author":"Peng","year":"2024","journal-title":"China Journal of Highway and Transport"},{"issue":"2","key":"10.7717\/peerj-cs.3771\/ref-24","doi-asserted-by":"publisher","first-page":"35","DOI":"10.1007\/s41651-023-00163-z","article-title":"An improved faster R-CNN method for landslide detection in remote sensing images","volume":"8","author":"Qin","year":"2024","journal-title":"Journal of Geovisualization and Spatial Analysis"},{"key":"10.7717\/peerj-cs.3771\/ref-25","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1506.02640","article-title":"You Only Look Once: unified, real-time object detection","author":"Redmon","year":"2016"},{"key":"10.7717\/peerj-cs.3771\/ref-26","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1506.01497","article-title":"Faster R-CNN: towards real-time object detection with region proposal networks","author":"Ren","year":"2016"},{"key":"10.7717\/peerj-cs.3771\/ref-27","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1902.09630","article-title":"Generalized intersection over union: a metric and a loss for bounding box regression","author":"Rezatofighi","year":"2019"},{"key":"10.7717\/peerj-cs.3771\/ref-28","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1610.02391","article-title":"Grad-CAM: visual explanations from deep networks via gradient-based localization","author":"Selvaraju","year":"2019"},{"issue":"8","key":"10.7717\/peerj-cs.3771\/ref-29","first-page":"8","article-title":"Research on edge detection of train bearing surface defect image","author":"Shi","year":"2024","journal-title":"Mechanical Engineer"},{"key":"10.7717\/peerj-cs.3771\/ref-30","doi-asserted-by":"publisher","first-page":"10778","DOI":"10.1109\/CVPR42600.2020.01079","article-title":"EfficientDet: scalable and efficient object detection","author":"Tan","year":"2020"},{"key":"10.7717\/peerj-cs.3771\/ref-31","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2405.14458","article-title":"YOLOv10: real-time end-to-end object detection","author":"Wang","year":"2024a"},{"issue":"3","key":"10.7717\/peerj-cs.3771\/ref-32","doi-asserted-by":"publisher","first-page":"413","DOI":"10.3724\/SP.J.1089.2024.19832","article-title":"Refined segmentation network for leather surface defect detection based on improved U-Net","volume":"36","author":"Wang","year":"2024b","journal-title":"Journal of Computer-Aided Design & Computer Graphics"},{"issue":"3","key":"10.7717\/peerj-cs.3771\/ref-33","doi-asserted-by":"publisher","first-page":"108269","DOI":"10.1016\/j.compeleceng.2022.108269","article-title":"Rail surface defect detection based on improved Mask R-CNN","volume":"102","author":"Wang","year":"2022","journal-title":"Computers and Electrical Engineering"},{"key":"10.7717\/peerj-cs.3771\/ref-34","doi-asserted-by":"publisher","first-page":"1","DOI":"10.19892\/j.cnki.csjz.2024.12.01","article-title":"Intelligent detection method for damage to concrete structures in railway stations based on infrared thermal imaging","volume":"21","author":"Wang","year":"2024c","journal-title":"Urban Architecture"},{"issue":"20","key":"10.7717\/peerj-cs.3771\/ref-35","doi-asserted-by":"publisher","first-page":"2015004","DOI":"10.3788\/LOP223132","article-title":"Improved faster R-CNN-based contact lens surface defect detection","volume":"60","author":"Wang","year":"2023","journal-title":"Laser & Optoelectronics Progress"},{"issue":"S1","key":"10.7717\/peerj-cs.3771\/ref-36","doi-asserted-by":"publisher","first-page":"181","DOI":"10.14504\/ajr.8.S1.22","article-title":"An improved fabric defect detection method based on SSD","volume":"8","author":"Xie","year":"2022","journal-title":"AATCC Journal of Research"},{"key":"10.7717\/peerj-cs.3771\/ref-37","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2211.15444","article-title":"DAMO-YOLO: a report on real-time object detection design","author":"Xu","year":"2023"},{"issue":"4","key":"10.7717\/peerj-cs.3771\/ref-38","doi-asserted-by":"publisher","first-page":"109316","DOI":"10.1016\/j.measurement.2021.109316","article-title":"Automatic defect detection and segmentation of tunnel surface using modified mask R-CNN","volume":"178","author":"Xu","year":"2021a","journal-title":"Measurement"},{"issue":"19","key":"10.7717\/peerj-cs.3771\/ref-39","doi-asserted-by":"publisher","first-page":"8945","DOI":"10.3390\/app11198945","article-title":"Copper strip surface defect detection model based on deep convolutional neural network","volume":"11","author":"Xu","year":"2021b","journal-title":"Applied Sciences"},{"issue":"1","key":"10.7717\/peerj-cs.3771\/ref-40","doi-asserted-by":"publisher","first-page":"19","DOI":"10.54097\/2r4jz792","article-title":"Detection method for bolt missing pins of transmission line based on improved SSD network","volume":"3","author":"Xu","year":"2024","journal-title":"Mathematical Modeling and Algorithm Application"},{"issue":"1","key":"10.7717\/peerj-cs.3771\/ref-41","doi-asserted-by":"publisher","first-page":"208","DOI":"10.19554\/j.cnki.1001-3563.2024.01.024","article-title":"Region segmentation algorithm based on proportional features for defect detection of aluminum plastic blister medicine plates","volume":"45","author":"Yan","year":"2024","journal-title":"Packaging Engineering"},{"issue":"9","key":"10.7717\/peerj-cs.3771\/ref-42","doi-asserted-by":"publisher","first-page":"7820","DOI":"10.1109\/TCSVT.2024.3376773","article-title":"Asymptotic feature pyramid network for labeling pixels and regions","volume":"34","author":"Yang","year":"2024a","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"10.7717\/peerj-cs.3771\/ref-43","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1145\/3647649.3647656","article-title":"DCS-YOLOv8: an improved steel surface defect detection algorithm based on YOLOv8","volume":"33","author":"Yang","year":"2024b","journal-title":"ICIGP"},{"key":"10.7717\/peerj-cs.3771\/ref-44","doi-asserted-by":"publisher","DOI":"10.27692\/d.cnki.gsydx.2024.000249","article-title":"Research on metal surface defect detection methods based on computer vision","author":"Yin","year":"2024"},{"issue":"2001611","key":"10.7717\/peerj-cs.3771\/ref-45","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TIM.2024.3351241","article-title":"YOLO-HMC: an improved method for PCB surface defect detection","volume":"73","author":"Yuan","year":"2024","journal-title":"IEEE Transactions on Instrumentation and Measurement"},{"issue":"4","key":"10.7717\/peerj-cs.3771\/ref-46","doi-asserted-by":"publisher","first-page":"839","DOI":"10.3390\/ma17040839","article-title":"Quantitative detection of defects in multi-layer lightweight composite structures using THz-TDS based on a U-Net-BiLSTM network","volume":"17","author":"Zhang","year":"2024","journal-title":"Materials"},{"key":"10.7717\/peerj-cs.3771\/ref-47","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2101.08158","article-title":"Focal and efficient IOU loss for accurate bounding box regression","author":"Zhang","year":"2022"},{"issue":"10","key":"10.7717\/peerj-cs.3771\/ref-48","doi-asserted-by":"publisher","first-page":"2503","DOI":"10.3390\/agronomy13102503","article-title":"Evaluation method of potato storage external defects based on improved U-Net","volume":"13","author":"Zhang","year":"2023","journal-title":"Agronomy"},{"key":"10.7717\/peerj-cs.3771\/ref-49","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2311.02877","article-title":"Inner-IoU: more effective intersection over union loss with auxiliary bounding box","author":"Zhang","year":"2023"},{"key":"10.7717\/peerj-cs.3771\/ref-50","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2304.08069","article-title":"DETRs beat YOLOs on real-time object detection","author":"Zhao","year":"2024"},{"key":"10.7717\/peerj-cs.3771\/ref-51","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2005.03572","article-title":"Enhancing geometric factors in model learning and inference for object detection and instance segmentation","author":"Zheng","year":"2021"},{"issue":"13","key":"10.7717\/peerj-cs.3771\/ref-52","doi-asserted-by":"publisher","first-page":"6633","DOI":"10.3390\/app12136633","article-title":"IA-Mask R-CNN: improved anchor design mask R-CNN for surface defect detection of automotive engine parts","volume":"12","author":"Zhu","year":"2022","journal-title":"Applied Sciences"},{"issue":"2","key":"10.7717\/peerj-cs.3771\/ref-53","doi-asserted-by":"publisher","first-page":"413","DOI":"10.1080\/17480272.2024.2352605","article-title":"An accurate object detection of wood defects using an improved faster R-CNN model","volume":"20","author":"Zou","year":"2024","journal-title":"Wood Material Science & Engineering"}],"container-title":["PeerJ Computer Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/peerj.com\/articles\/cs-3771.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/cs-3771.xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/cs-3771.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/cs-3771.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T08:07:10Z","timestamp":1781597230000},"score":1,"resource":{"primary":{"URL":"https:\/\/peerj.com\/articles\/cs-3771"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,16]]},"references-count":53,"alternative-id":["10.7717\/peerj-cs.3771"],"URL":"https:\/\/doi.org\/10.7717\/peerj-cs.3771","archive":["CLOCKSS","LOCKSS","Portico"],"relation":{},"ISSN":["2376-5992"],"issn-type":[{"value":"2376-5992","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,16]]},"article-number":"e3771"}}