{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T23:23:41Z","timestamp":1781652221291,"version":"3.54.5"},"reference-count":41,"publisher":"Institution of Engineering and Technology (IET)","issue":"1","license":[{"start":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T00:00:00Z","timestamp":1750118400000},"content-version":"vor","delay-in-days":167,"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>X\u2010ray detection of contraband is crucial for public safety; however, it often faces challenges due to cluttered backgrounds and overlapping objects in security inspection images. This study proposes a novel detection framework based on You Only Look Once version 8 (YOLOv8), incorporating three key innovations: multi\u2010scale cross\u2010axis attention (MCA), which captures global dependencies through horizontal and vertical collaborative attention, effectively mitigating irrelevant features in complex X\u2010ray scenarios; a lightweight bottleneck architecture using partial convolution (PConv), which significantly reduces floating point operations (FLOPs) while preserving positional sensitivity; and the focal\u2010enhanced intersection over union (Focaler\u2010IoU) loss function, which dynamically weights difficult samples to enhance regression accuracy. Experiments on the prohibited item detection in the X\u2010ray dataset revealed that our model achieves a mean average precision (IoU = 0.5) (mAP@0.5) of 97.3%, outperforming YOLOv8s by 1.2 percentage points, and maintains real\u2010time performance of 121 frames per second, surpassing YOLOv10\u2010S (96.5%) and YOLOv12\u2010S (96.8%). Ablation studies highlight the contribution of each module: MCA enhances mAP by 0.7%, PConv decreases FLOPs by 31%, and Focaler\u2010IoU increases precision by 0.9% and recall by 2.4%. The proposed method exhibits substantial potential for real\u2010time security inspections.<\/jats:p>","DOI":"10.1049\/ipr2.70135","type":"journal-article","created":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T07:01:21Z","timestamp":1750143681000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["An X\u2010Ray Contraband Detection Method Based on Improved YOLOv8"],"prefix":"10.1049","volume":"19","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-1217-8929","authenticated-orcid":false,"given":"Jianing","family":"Chen","sequence":"first","affiliation":[{"name":"School of Information Engineering Hebei University of Architecture  Zhangjiakou China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Juan","family":"Hao","sequence":"additional","affiliation":[{"name":"School of Information Engineering Hebei University of Architecture  Zhangjiakou China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoqun","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Information Engineering Hebei University of Architecture  Zhangjiakou China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"265","published-online":{"date-parts":[[2025,6,17]]},"reference":[{"key":"e_1_2_9_2_1","doi-asserted-by":"publisher","DOI":"10.3788\/LOP202158.0810003"},{"key":"e_1_2_9_3_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.108245"},{"key":"e_1_2_9_4_1","doi-asserted-by":"publisher","DOI":"10.3390\/s24041158"},{"key":"e_1_2_9_5_1","doi-asserted-by":"crossref","unstructured":"C.Miao L.Xie F.Wan et\u00a0al \u201cSIXray: A Large\u2010Scale Security Inspection X\u2010Ray Benchmark for Prohibited Item Discovery in Overlapping Images \u201d inProceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)(IEEE 2019) 2119\u20132128.https:\/\/doi.org\/10.48550\/arXiv.1901.00303.","DOI":"10.1109\/CVPR.2019.00222"},{"key":"e_1_2_9_6_1","doi-asserted-by":"crossref","unstructured":"Z.QiaoandH.Zhang \u201cX\u2010Ray Security Inspection Image Detection Based on a Multi\u2010Scale Feature Fusion Network \u201d inProceedings of the International Conference on Natural Computation Fuzzy Systems and Knowledge Discovery(Springer 2022) 814\u2013821.https:\/\/doi.org\/10.1007\/978\u20103\u2010030\u201089698\u20100_83.","DOI":"10.1007\/978-3-030-89698-0_83"},{"key":"e_1_2_9_7_1","doi-asserted-by":"publisher","DOI":"10.3390\/electronics13081530"},{"key":"e_1_2_9_8_1","doi-asserted-by":"crossref","unstructured":"R.Tao Y.Wei X.Jiang et\u00a0al \u201cTowards Real\u2010World X\u2010Ray Security Inspection: A High\u2010Quality Benchmark and Lateral Inhibition Module for Prohibited Items Detection \u201d inProceedings of the 2021 IEEE\/CVF International Conference on Computer Vision (ICCV)(IEEE 2021) 10903\u201310912.https:\/\/doi.org\/10.48550\/arXiv.2108.09917.","DOI":"10.1109\/ICCV48922.2021.01074"},{"key":"e_1_2_9_9_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2302.13390"},{"key":"e_1_2_9_10_1","unstructured":"H.Shao Q.Zeng Q.Hou andJ.Yang \u201cMCANet: Medical Image Segmentation With Multi\u2010Scale Cross\u2010Axis Attention \u201d arXiv:2312.08866 December 14 2023 https:\/\/doi.org\/10.48550\/arXiv:2312.08866."},{"key":"e_1_2_9_11_1","doi-asserted-by":"crossref","unstructured":"J.Chen S.\u2010h.Kao H.He et\u00a0al \u201cRun Don't Walk: Chasing Higher FLOPS for Faster Neural Networks \u201d inProceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)(IEEE 2023) 12021\u201312031.https:\/\/doi.org\/10.48550\/arXiv.2303.03667.","DOI":"10.1109\/CVPR52729.2023.01157"},{"key":"e_1_2_9_12_1","unstructured":"H.ZhangandS.Zhang \u201cFocaler\u2010IoU: More Focused Intersection Over Union Loss \u201d arXiv.2401.10525 2024 January 19 2024 https:\/\/doi.org\/10.48550\/arXiv.2401.10525."},{"key":"e_1_2_9_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2023.3238524"},{"key":"e_1_2_9_14_1","doi-asserted-by":"crossref","unstructured":"M.Tan R.Pang andQ.Le \u201cEfficientDet: Scalable and Efficient Object Detection \u201d inProceedings of the 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)(IEEE 2020) 10778\u201310787 https:\/\/doi.org\/10.1109\/CVPR42600.2020.01079.","DOI":"10.1109\/CVPR42600.2020.01079"},{"key":"e_1_2_9_15_1","doi-asserted-by":"publisher","DOI":"10.3390\/rs16010149"},{"key":"e_1_2_9_16_1","doi-asserted-by":"publisher","DOI":"10.5755\/j01.itc.50.1.25094"},{"key":"e_1_2_9_17_1","doi-asserted-by":"publisher","DOI":"10.1088\/1742\u20106596\/1976\/1\/012023"},{"key":"e_1_2_9_18_1","unstructured":"A.Bochkovskiy C. Y.Wang andH. Y. M.Liao \u201cYOLOv4: Optimal Speed and Accuracy of Object Detection \u201d arXiv:2004.10934 April 23 2020 https:\/\/doi.org\/10.48550\/arXiv.2004.10934."},{"key":"e_1_2_9_19_1","unstructured":"G.Jocher A.Chaurasia andJ.Borovec \u201cYOLOv5 by Ultralytics \u201d (2023) accessed July 5 2024 https:\/\/github.com\/ultralytics\/yolov5."},{"key":"e_1_2_9_20_1","unstructured":"G.Jocher A.Chaurasia andJ.Qiu \u201cYOLOv8 by Ultralytics \u201d (2023) accessed July 21 2024 https:\/\/github.com\/ultralytics\/ultralytics."},{"key":"e_1_2_9_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3378568"},{"key":"e_1_2_9_22_1","unstructured":"V.Mnih N.Heess A.Graves andK.Kavukcuoglu \u201cRecurrent Models of Visual Attention \u201d inProceedings of the 28th International Conference on Neural Information Processing Systems(MIT Press 2014) 2204\u20132212 https:\/\/doi.org\/10.48550\/arXiv.1406.6247."},{"key":"e_1_2_9_23_1","unstructured":"M.Jaderberg K.Simonyan Z.Andrew andK.Koray \u201cSpatial Transformer Networks \u201d arXiv:1506.02025 June 5 2015 https:\/\/doi.org\/10.48550\/arXiv.1506.02025."},{"key":"e_1_2_9_24_1","doi-asserted-by":"crossref","unstructured":"J.Hu L.Shen S.Albanie G.Sun andJ.Wu \u201cSqueeze\u2010and\u2010Excitation Networks \u201d inProceedings of the 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition(IEEE 2018) 7132\u20137141.https:\/\/doi.org\/10.48550\/arXiv.2308.13343.","DOI":"10.1109\/CVPR.2018.00745"},{"key":"e_1_2_9_25_1","doi-asserted-by":"crossref","unstructured":"S.Woo J.Park J. Y.Lee andI. S.Kweon \u201cCBAM: Convolutional Block Attention Module \u201d inProceedings of the European Conference on Computer Vision (ECCV)(Springer 2018) 3\u201319.https:\/\/doi.org\/10.48550\/arXiv.1807.06521.","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"e_1_2_9_26_1","unstructured":"D.Bahdanau K.Cho andY.Bengio \u201cNeural Machine Translation by Jointly Learning to Align and Translate \u201d arXiv:1409.0473 September 1 2014 https:\/\/doi.org\/10.48550\/arXiv.1409.0476."},{"key":"e_1_2_9_27_1","unstructured":"A.Vaswani N.Shazeer N.Parmar et\u00a0al \u201cAttention is All You Need \u201d inProceedings of the 31st International Conference on Neural Information Processing Systems(Curran Associates Inc. 2017) 5998\u20136008.https:\/\/doi.org\/10.48550\/arXiv.1706.03762."},{"key":"e_1_2_9_28_1","doi-asserted-by":"publisher","DOI":"10.1007\/s41095\u2010022\u20100271\u2010y"},{"key":"e_1_2_9_29_1","unstructured":"Y.Zhang Y.Liu H.Yuan et\u00a0al. \u201cTensor Product Attention Is All You Need \u201d arXiv:2501.06125 January 11 2025 https:\/\/doi.org\/10.48550\/arXiv:2501.06125."},{"key":"e_1_2_9_30_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598\u2010025\u201099165\u20108"},{"key":"e_1_2_9_31_1","doi-asserted-by":"publisher","DOI":"10.3390\/biomimetics10050288"},{"key":"e_1_2_9_32_1","doi-asserted-by":"publisher","DOI":"10.7693\/wl20210804"},{"key":"e_1_2_9_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2022.3154287"},{"key":"e_1_2_9_34_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2024.109382"},{"key":"e_1_2_9_35_1","doi-asserted-by":"crossref","unstructured":"B.Wang L.Zhang L.Wen X.Liu andY.Wu \u201cTowards Real\u2010world Prohibited Item Detection: A Large\u2010scale X\u2010Ray Benchmark \u201d inProceedings of the IEEE\/CVF International Conference on Computer Vision(IEEE 2021) 5412\u20135421.https:\/\/doi.org\/10.48550\/arXiv.2108.07020.","DOI":"10.1109\/ICCV48922.2021.00536"},{"key":"e_1_2_9_36_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10921\u2010015\u20100315\u20107"},{"key":"e_1_2_9_37_1","first-page":"267","volume-title":"Digital Image Processing","author":"Gonzalez R. C.","year":"2017"},{"key":"e_1_2_9_38_1","unstructured":"A.Howard M.Sandler G.Chu et\u00a0al. \u201cSearching for MobileNetV3 \u201d preprint arXiv:1905.02244 May 6 2021 https:\/\/doi.org\/10.48550\/arXiv.1905.02244."},{"key":"e_1_2_9_39_1","unstructured":"Y.Liu Z.Shao andN.Hoffmann \u201cGlobal Attention Mechanism: Retain Information to Enhance Channel\u2010Spatial Interactions \u201d preprint arXiv:2112.05561 December 10 2021 https:\/\/doi.org\/10.48550\/arXiv.2112.05561."},{"key":"e_1_2_9_40_1","doi-asserted-by":"crossref","unstructured":"D.Misra T.Nalamada A.Arasanipalai andQ.Hou \u201cRotate to Attend: Convolutional Triplet Attention Module \u201d inProceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)(IEEE 2021) 3139\u20133148.https:\/\/doi.org\/10.48550\/arXiv.2010.03045.","DOI":"10.1109\/WACV48630.2021.00318"},{"key":"e_1_2_9_41_1","unstructured":"W.Ao L.Lihao C.Hui et\u00a0al. \u201cYOLOv10: Real\u2010Time End\u2010to\u2010End Object Detection \u201d preprint arXiv:2405.14458 May 23 2024 https:\/\/doi.org\/10.48550\/arXiv.2503.14458."},{"key":"e_1_2_9_42_1","unstructured":"T.Yunjie Y.Qixiang andD.Doermann \u201cYOLOv12: Attention\u2010Centric Real\u2010Time Object Detectors \u201d preprint arXiv.2502.12524 February 18 2025 https:\/\/doi.org\/10.48550\/arXiv.2502.12524."}],"container-title":["IET Image Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/pdf\/10.1049\/ipr2.70135","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/full-xml\/10.1049\/ipr2.70135","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/pdf\/10.1049\/ipr2.70135","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T23:58:46Z","timestamp":1778284726000},"score":1,"resource":{"primary":{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/10.1049\/ipr2.70135"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1]]},"references-count":41,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2025,1]]}},"alternative-id":["10.1049\/ipr2.70135"],"URL":"https:\/\/doi.org\/10.1049\/ipr2.70135","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":"2025-03-13","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-06-08","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-06-17","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70135"}}