{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T12:00:54Z","timestamp":1775217654648,"version":"3.50.1"},"reference-count":38,"publisher":"Institution of Engineering and Technology (IET)","issue":"1","license":[{"start":{"date-parts":[[2025,4,29]],"date-time":"2025-04-29T00:00:00Z","timestamp":1745884800000},"content-version":"vor","delay-in-days":118,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"content-domain":{"domain":["ietresearch.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["IET Image Processing"],"published-print":{"date-parts":[[2025,1]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:p>To address the accuracy limitations of current methods in detecting aluminum surface defects, particularly those with small sizes and high variation, an aluminum surface defect detection algorithm named DAS\u2010YOLO, based on an improved YOLOv8n, is proposed. The C2f module in YOLOv8's backbone is enhanced by incorporating DCNv2, which improves the model's ability to handle irregular shapes and geometric transformations during feature extraction. An auxiliary training head (Aux Head) is added to capture multi\u2010scale and multi\u2010level features, significantly boosting small defect detection. Additionally, the traditional CIoU loss function is replaced with the Wise\u2010SIoU loss, accelerating convergence and enhancing both detection and regression accuracy. Experimental results on the Alibaba Tianchi aluminum surface defect dataset show that DAS\u2010YOLO achieves a mean average precision (mAP) of 85.3%. Compared to YOLOv8n, mAP50 improves by 3%, while precision and recall increase by 1.1% and 4.6%, respectively. Furthermore, to validate the model's performance on small defects and its generalization ability, it achieves a detection accuracy of 94.8% on the PCB dataset, with an mAP increase of 3.1% compared to YOLOv8n. These results demonstrate that DAS\u2010YOLO significantly enhances detection accuracy while maintaining speed and exhibits outstanding performance in small defect\u00a0detection.<\/jats:p>","DOI":"10.1049\/ipr2.70090","type":"journal-article","created":{"date-parts":[[2025,4,29]],"date-time":"2025-04-29T06:25:32Z","timestamp":1745907932000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Aluminum Surface Defect Detection Method Based on DAS\u2010YOLO Network"],"prefix":"10.1049","volume":"19","author":[{"given":"Jun","family":"Tie","sequence":"first","affiliation":[{"name":"College of Computer Science South\u2010Central Minzu University  Wuhan Hubei China"},{"name":"Hubei Provincial Engineering Research Center of Agricultural Blockchain and Intelligent Management  Wuhan Hubei China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-5953-9269","authenticated-orcid":false,"given":"Jiating","family":"Ma","sequence":"additional","affiliation":[{"name":"College of Computer Science South\u2010Central Minzu University  Wuhan Hubei China"},{"name":"Hubei Provincial Engineering Research Center for Intelligent Management of Manufacturing Enterprises  Wuhan Hubei China"}]},{"given":"Lu","family":"Zheng","sequence":"additional","affiliation":[{"name":"College of Computer Science South\u2010Central Minzu University  Wuhan Hubei China"},{"name":"Hubei Provincial Engineering Research Center of Agricultural Blockchain and Intelligent Management  Wuhan Hubei China"}]},{"given":"Chengao","family":"Zhu","sequence":"additional","affiliation":[{"name":"College of Computer Science South\u2010Central Minzu University  Wuhan Hubei China"},{"name":"Hubei Provincial Engineering Research Center for Intelligent Management of Manufacturing Enterprises  Wuhan Hubei China"}]},{"given":"Mian","family":"Wu","sequence":"additional","affiliation":[{"name":"Dong Feng Machine Tool Plant Co., Ltd.  ShiYan Hubei China"}]},{"given":"HaiJiao","family":"Wang","sequence":"additional","affiliation":[{"name":"Dong Feng Machine Tool Plant Co., Ltd.  ShiYan Hubei China"}]},{"given":"ChongWei","family":"Ruan","sequence":"additional","affiliation":[{"name":"Dong Feng Machine Tool Plant Co., Ltd.  ShiYan Hubei China"}]},{"given":"Shuangyang","family":"Li","sequence":"additional","affiliation":[{"name":"College of Computer Science South\u2010Central Minzu University  Wuhan Hubei China"},{"name":"Hubei Provincial Engineering Research Center for Intelligent Management of Manufacturing Enterprises  Wuhan Hubei China"}]}],"member":"265","published-online":{"date-parts":[[2025,4,29]]},"reference":[{"key":"e_1_2_9_2_1","first-page":"1","article-title":"ADDet: An Efficient Multiscale Perceptual Enhancement Network for Aluminum Defect Detection","volume":"73","author":"Zhu J.","year":"2024","journal-title":"IEEE Transactions on Instrumentation and Measurement"},{"issue":"10","key":"e_1_2_9_3_1","first-page":"362","article-title":"Research on Surface Defect Detection and Implementation of Metal Workpiece Based on Improved Faster R\u2010CNN","volume":"40","author":"Dai X.","year":"2020","journal-title":"Surface Technology"},{"key":"e_1_2_9_4_1","doi-asserted-by":"crossref","unstructured":"Q.LiandX.Li \u201cResearch on Rail Surface Defect Detection Algorithm Based on Improved YOLOv8 \u201d in2024 IEEE 4th International Conference on Information Technology Big Data and Artificial Intelligence (ICIBA)(IEEE 2024) 1159\u20131162.","DOI":"10.1109\/ICIBA62489.2024.10868615"},{"key":"e_1_2_9_5_1","doi-asserted-by":"crossref","unstructured":"S.LiandZ.Wang \u201cResearch on Surface Defect Detection Method of Aluminum Profile Based on Machine Vision \u201d in2023 8th International Conference on Intelligent Informatics and Biomedical Sciences (ICIIBMS)(IEEE 2023).","DOI":"10.1109\/ICIIBMS60103.2023.10347859"},{"key":"e_1_2_9_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3462738"},{"issue":"21","key":"e_1_2_9_7_1","article-title":"Improved Lightweight X\u2010Ray Aluminum Alloy Weld Defects Detection Algorithm Based on YOLOv5","volume":"49","author":"Song C.","year":"2022","journal-title":"Chinese Journal of Lasers"},{"key":"e_1_2_9_8_1","doi-asserted-by":"publisher","DOI":"10.2355\/isijinternational.ISIJINT-2019-335"},{"key":"e_1_2_9_9_1","doi-asserted-by":"publisher","DOI":"10.1111\/mice.12263"},{"issue":"19","key":"e_1_2_9_10_1","first-page":"235","article-title":"Strip Steel Surface Defect Detection Based on Improved Mask R\u2010CNN Algorithm","volume":"57","author":"Weng Y.","year":"2021","journal-title":"Computer Engineering and Applications"},{"key":"e_1_2_9_11_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2018.09.412"},{"key":"e_1_2_9_12_1","doi-asserted-by":"crossref","unstructured":"Y.Yu M.Wang Z.Wang andP.Zhou \u201cSurface Defect Detection of Hight\u2010Speed Railway hub Based on Improved YOLOv3 Algorithm \u201d in2021 IEEE 4th Advanced Information Management Communicates Electronic and Automation Control Conference (IMCEC)(IEEE 2021) 1386\u20131390.","DOI":"10.1109\/IMCEC51613.2021.9482386"},{"issue":"4","key":"e_1_2_9_13_1","article-title":"Surface Defect Detection of Aluminium Profiles Based on KCC\u2010YOLOv5","volume":"61","author":"Deng G.","year":"2024","journal-title":"Advances in Lasers and Optoelectronics"},{"key":"e_1_2_9_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2021.3070507"},{"key":"e_1_2_9_15_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.measurement.2023.112776"},{"key":"e_1_2_9_16_1","doi-asserted-by":"publisher","DOI":"10.3390\/s23167112"},{"key":"e_1_2_9_17_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.optlaseng.2024.108174"},{"key":"e_1_2_9_18_1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TIM.2021.3092510","article-title":"FPCB Surface Defect Detection: A Decoupled Two\u2010Stage Object Detection Framework","volume":"70","author":"Luo J.","year":"2021","journal-title":"IEEE Transactions on Instrumentation and Measurement"},{"key":"e_1_2_9_19_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2022.01.135"},{"key":"e_1_2_9_20_1","doi-asserted-by":"publisher","DOI":"10.3390\/app14010386"},{"issue":"15","key":"e_1_2_9_21_1","first-page":"318","article-title":"Lightweight DCN\u2010YOLO for Strip Surface Defect Detection in Complex Environments","volume":"59","author":"LU J.","year":"2023","journal-title":"Computer Engineering and Applications"},{"key":"e_1_2_9_22_1","first-page":"1","article-title":"FHENet: Lightweight Feature Hierarchical Exploration Network for Real\u2010Time Rail Surface Defect Inspection in RGB\u2010D Images","volume":"72","author":"Zhou W.","year":"2023","journal-title":"IEEE Transactions on Instrumentation and Measurement"},{"key":"e_1_2_9_23_1","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6501\/ad66fe"},{"key":"e_1_2_9_24_1","doi-asserted-by":"publisher","DOI":"10.3390\/math11102344"},{"key":"e_1_2_9_25_1","doi-asserted-by":"publisher","DOI":"10.3389\/fphy.2024.1419998"},{"key":"e_1_2_9_26_1","doi-asserted-by":"publisher","DOI":"10.1177\/00405175241285596"},{"key":"e_1_2_9_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2021.3109723"},{"key":"e_1_2_9_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3291598"},{"key":"e_1_2_9_29_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.measurement.2023.112614"},{"key":"e_1_2_9_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3262264"},{"key":"e_1_2_9_31_1","doi-asserted-by":"crossref","unstructured":"X.Zhu H.Hu S.Lin andJ.Dai \u201cDeformable Convnets v2: More Deformable Better Results \u201d in2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)(IEEE 2019) 9308\u20139316.","DOI":"10.1109\/CVPR.2019.00953"},{"key":"e_1_2_9_32_1","doi-asserted-by":"crossref","unstructured":"X.Dai Y.Chen B.Xiao et\u00a0al. \u201cDynamic Head: Unifying Object Detection Heads with Attentions \u201d inProceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition(IEEE 2021) 7373\u20137382.","DOI":"10.1109\/CVPR46437.2021.00729"},{"key":"e_1_2_9_33_1","article-title":"Wise\u2010IoU: Bounding Box Regression Loss with Dynamic Focusing Mechanism","volume":"2301","author":"Tong Z.","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"e_1_2_9_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCER55570.2022.00038"},{"key":"e_1_2_9_35_1","doi-asserted-by":"crossref","unstructured":"K.Ye Y.Gao X.Ye andA.Ye \u201cDC\u2010YOLO: Improved YOLOv7 Based on Deformable Convolution and Attention Mechanism for Fabric Defect Detection \u201d in2023 Eleventh International Conference on Advanced Cloud and Big Data (CBD)(IEEE 2023) 162\u2013167.","DOI":"10.1109\/CBD63341.2023.00037"},{"key":"e_1_2_9_36_1","doi-asserted-by":"crossref","unstructured":"M.Kawaguchi \u201cFabric Defect Detection System Using Yolo \u201d in2023 14th IIAI International Congress on Advanced Applied Informatics (IIAI\u2010AAI)(IEEE 2023) 277\u2013280.","DOI":"10.1109\/IIAI-AAI59060.2023.00062"},{"key":"e_1_2_9_37_1","doi-asserted-by":"crossref","unstructured":"Z.Li Z.Zhang J.Ma andL.Tian \u201cImproved YOLOV5 Based Industrial Surface Defect Detection Method \u201d in2023 International Conference on Computers Information Processing and Advanced Education (CIPAE)(IEEE 2023) 367\u2013370.","DOI":"10.1109\/CIPAE60493.2023.00077"},{"key":"e_1_2_9_38_1","doi-asserted-by":"crossref","unstructured":"T.Yang Y.Liu C.Jin et\u00a0al. \u201cPrinted Circuit Board Defect Detection Based on Improved YOLOv5 \u201d in2023 6th International Conference on Information and Computer Technologies (ICICT)(IEEE 2023) 72\u201377.","DOI":"10.1109\/ICICT58900.2023.00019"},{"key":"e_1_2_9_39_1","doi-asserted-by":"crossref","unstructured":"H.Zhang \u201cIntelligent Defect Detection System Based on Cloud\u2010Edge Synergy Technology \u201d in2024 IEEE 9th International Conference on Smart Cloud (SmartCloud)(IEEE 2024) 103\u2013108.","DOI":"10.1109\/SmartCloud62736.2024.00026"}],"container-title":["IET Image Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/pdf\/10.1049\/ipr2.70090","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/full-xml\/10.1049\/ipr2.70090","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/pdf\/10.1049\/ipr2.70090","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T11:19:01Z","timestamp":1775215141000},"score":1,"resource":{"primary":{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/10.1049\/ipr2.70090"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1]]},"references-count":38,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2025,1]]}},"alternative-id":["10.1049\/ipr2.70090"],"URL":"https:\/\/doi.org\/10.1049\/ipr2.70090","archive":["Portico"],"relation":{},"ISSN":["1751-9659","1751-9667"],"issn-type":[{"value":"1751-9659","type":"print"},{"value":"1751-9667","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1]]},"assertion":[{"value":"2024-12-20","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-04-17","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-04-29","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70090"}}