{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,8]],"date-time":"2026-01-08T20:46:51Z","timestamp":1767905211247,"version":"3.49.0"},"reference-count":46,"publisher":"Springer Science and Business Media LLC","issue":"7","license":[{"start":{"date-parts":[[2023,7,26]],"date-time":"2023-07-26T00:00:00Z","timestamp":1690329600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,7,26]],"date-time":"2023-07-26T00:00:00Z","timestamp":1690329600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"DOI":"10.1007\/s11042-023-16352-3","type":"journal-article","created":{"date-parts":[[2023,7,26]],"date-time":"2023-07-26T03:23:45Z","timestamp":1690341825000},"page":"19181-19197","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Detection of irregular small defects on metal base surface of infrared laser diode based on deep learning"],"prefix":"10.1007","volume":"83","author":[{"given":"Xingfei","family":"Zhu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiayi","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xingyu","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shanhua","family":"Qian","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3763-2509","authenticated-orcid":false,"given":"Jinghu","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,7,26]]},"reference":[{"key":"16352_CR1","first-page":"1","volume":"70","author":"Y Bao","year":"2021","unstructured":"Bao Y, Song K, Liu J, Wang Y, Yan Y, Han Y, Li X (2021) Triplet-graph reasoning network for few-shot metal generic surface defect segmentation. IEEE Trans Instrum Meas 70:1\u201311","journal-title":"IEEE Trans Instrum Meas"},{"issue":"9","key":"16352_CR2","first-page":"198","volume":"17","author":"A Bochkovskiy","year":"2020","unstructured":"Bochkovskiy A, Wang C-Y, Liao H-YM (2020) YOLOv4: optimal speed and accuracy of object detection.\u00a0In: arXiv:\u00a0Computer Vision and Pattern Recognition (CVPR) 17(9):198\u2013215","journal-title":"Comput Vis Pattern Recognit"},{"key":"16352_CR3","unstructured":"Cheng-Yang F, Liu W, Ranga A, Tyagi A, Berg AC (2017) DSSD: deconvolutional single shot detector.\u00a0In: arXiv: Computer\u00a0Vision and Pattern Recognition (CVPR), arXiv:1701.06659"},{"issue":"1","key":"16352_CR4","first-page":"577","volume":"28","author":"J Chorowski","year":"2015","unstructured":"Chorowski J, Bahdanau D, Serdyuk D, Cho K, Bengio Y (2015) Attention-based models for speech recognition.\u00a0In: Neural Information Processing Systems (NIPS) 28(1):577\u2013585","journal-title":"Neural Information Processing Systems (NIPS)"},{"key":"16352_CR5","doi-asserted-by":"publisher","first-page":"273","DOI":"10.1007\/BF00994018","volume":"20","author":"C Cortes","year":"1995","unstructured":"Cortes C, Vapnik V (1995) Support-vector networks. Mach Learn 20:273\u2013297","journal-title":"Mach Learn"},{"key":"16352_CR6","first-page":"379","volume-title":"R-FCN: object detection via region-based fully convolutional networks neural information processing systems (NIPS)","author":"J Dai","year":"2016","unstructured":"Dai J, Li Y, He K, Sun J (2016) R-FCN: object detection via region-based fully convolutional networks neural information processing systems (NIPS), pp 379\u2013387"},{"key":"16352_CR7","first-page":"886","volume-title":"Computer vision and pattern recognition (CVPR)","author":"N Dalal","year":"2005","unstructured":"Dalal N, Triggs B (2005) Histograms of oriented gradients for human detection. In: Computer vision and pattern recognition (CVPR), pp 886\u2013893"},{"key":"16352_CR8","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","volume":"88","author":"M Everingham","year":"2010","unstructured":"Everingham M, Van Gool L, Williams CKI, Winn J, Zisserman A (2010) The Pascal visual object classes (VOC) challenge. Int J Comput Vis 88:303\u2013338","journal-title":"Int J Comput Vis"},{"key":"16352_CR9","doi-asserted-by":"publisher","first-page":"1627","DOI":"10.1109\/TPAMI.2009.167","volume":"32","author":"PF Felzenszwalb","year":"2010","unstructured":"Felzenszwalb PF, Girshick R, McAllester D, Ramanan D (2010) Object detection with discriminatively trained part-based models. IEEE Trans Pattern Anal Mach Intell 32:1627\u20131645","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"16352_CR10","doi-asserted-by":"publisher","unstructured":"Freund Y, Schapire RE (1997) A decision-theoretic generalization of on-line learning and an application to boosting.\u00a0J Comput Syst Sci 55:119\u2013139.\u00a0https:\/\/doi.org\/10.1006\/jcss.1997.1504","DOI":"10.1006\/jcss.1997.1504"},{"key":"16352_CR11","first-page":"1440","volume-title":"In: International Conference on Computer Vision (ICCV)","author":"R Girshick","year":"2015","unstructured":"Girshick R (2015) Fast R-CNN. In: International Conference on Computer Vision (ICCV), pp 1440\u20131448. arXiv:1504.08083"},{"key":"16352_CR12","doi-asserted-by":"crossref","unstructured":"Girshick R, Donahue J, Darrell T, Malik J (2014) Rich feature hierarchies for accurate object detection and semantic segmentation. In: Computer Vision and Pattern Recognition (CVPR), pp 580\u2013587. arXiv:1311.2524","DOI":"10.1109\/CVPR.2014.81"},{"key":"16352_CR13","doi-asserted-by":"publisher","first-page":"1657","DOI":"10.1109\/TIP.2010.2044957","volume":"19","author":"Z Guo","year":"2010","unstructured":"Guo Z, Zhang L, Zhang D (2010) A completed modeling of local binary pattern operator for texture classification. IEEE Trans Image Process 19:1657\u20131663","journal-title":"IEEE Trans Image Process"},{"key":"16352_CR14","doi-asserted-by":"publisher","first-page":"1904","DOI":"10.1109\/TPAMI.2015.2389824","volume":"37","author":"K He","year":"2015","unstructured":"He K, Zhang X, Ren S, Sun J (2015) Spatial pyramid pooling in deep convolutional networks for visual recognition. IEEE Trans Pattern Anal Mach Intell 37:1904\u20131916","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"16352_CR15","first-page":"2961","volume-title":"International conference on computer vision (ICCV)","author":"K He","year":"2017","unstructured":"He K, Gkioxari G, Doll\u00e1r P, Girshick R (2017) Mask R-CNN. In: International Conference on Computer Vision (ICCV), pp 2961\u20132969. arXiv:1703.06870"},{"issue":"4","key":"16352_CR16","doi-asserted-by":"publisher","first-page":"1493","DOI":"10.1109\/TIM.2019.2915404","volume":"69","author":"Y He","year":"2020","unstructured":"He Y, Song K, Meng Q, Yan Y (2020) An end-to-end steel surface defect detection approach via fusing multiple hierarchical features. IEEE Trans Instrum Meas 69(4):1493\u20131504","journal-title":"IEEE Trans Instrum Meas"},{"key":"16352_CR17","doi-asserted-by":"crossref","unstructured":"Hu J, Shen L, Albanie S, Sun G, Wu E (2018) Squeeze-and-excitation networks. In: Computer Vision and Pattern Recognition (CVPR) 42(8):2011\u20132023","DOI":"10.1109\/TPAMI.2019.2913372"},{"issue":"5","key":"16352_CR18","doi-asserted-by":"publisher","first-page":"3324","DOI":"10.1049\/iet-ipr.2019.0772","volume":"14","author":"S Huang","year":"2020","unstructured":"Huang S, Mengxing Huang Y, Zhang JC, Bhatti U (2020) Medical image segmentation using deep learning with feature enhancement. IET Image Process 14(5):3324\u20133332","journal-title":"IET Image Process"},{"key":"16352_CR19","first-page":"448","volume-title":"Proceedings of the 32nd international conference on machine learning (ICML-15)","author":"S Ioffe","year":"2015","unstructured":"Ioffe S, Szegedy C (2015) Batch normalization: accelerating deep network training by reducing internal covariate shift. In: Proceedings of the 32nd International Conference on Machine Learning (ICML-15) 37:448\u2013456"},{"key":"16352_CR20","doi-asserted-by":"publisher","first-page":"1254","DOI":"10.1109\/34.730558","volume":"20","author":"L Itti","year":"1998","unstructured":"Itti L, Koch C, Niebur E (1998) A model of saliency-based visual attention for rapid scene analysis. IEEE Trans Pattern Anal Mach Intell 20:1254\u20131259","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"16352_CR21","doi-asserted-by":"crossref","unstructured":"Kisantal M, Wojna Z, Murawski J, Naruniec J, Cho K (2019) Augmentation for small object detection. arXiv:1902.07296","DOI":"10.5121\/csit.2019.91713"},{"key":"16352_CR22","doi-asserted-by":"crossref","unstructured":"Kong T, Sun F, Huang W, Liu H (2018) Deep feature pyramid reconfiguration for object detection. In: European Conference on Computer Vision (ECCV), pp 172\u2013188. arXiv:1808.07993","DOI":"10.1007\/978-3-030-01228-1_11"},{"key":"16352_CR23","unstructured":"Krizhevsky A Hinton G (2009) Learning multiple layers of features from tiny images. Handbook of Systemic Autoimmune Diseases, 1(4)"},{"key":"16352_CR24","first-page":"740","volume-title":"European conference on computer vision (ECCV)","author":"T-Y Lin","year":"2014","unstructured":"Lin T-Y, Maire M, Belongie S, Hays J, Perona P, Ramanan D, Doll\u00e1r P, Lawrence Zitnick C (2014) Microsoft COCO: common objects in context. In: European Conference on Computer Vision (ECCV) 8693:740\u2013755"},{"key":"16352_CR25","doi-asserted-by":"crossref","unstructured":"Lin G, Milan A, Shen C, Reid I (2017) RefineNet: multi-path refinement networks for high-resolution semantic segmentation.\u00a0In: Computer Vision and Pattern Recognition (CVPR) 1(2):5168\u20135177","DOI":"10.1109\/CVPR.2017.549"},{"key":"16352_CR26","doi-asserted-by":"crossref","unstructured":"Lin T-Y, Doll\u00e1r P, Girshick R, He K, Hariharan B, Belongie S (2017) Feature pyramid networks for object detection. In: Computer Vision and Pattern Recognition (CVPR), pp 936\u2013944. arXiv:1612.03144","DOI":"10.1109\/CVPR.2017.106"},{"key":"16352_CR27","doi-asserted-by":"crossref","unstructured":"Liu W, Anguelov D, Erhan D, Szegedy C, Reed S, Cheng-Yang F, Berg AC (2016) SSD: single shot MultiBox detector. In: European Conference on Computer Vision 9905:21\u201337","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"16352_CR28","doi-asserted-by":"crossref","unstructured":"Liu S, Lu Q, Qin H, Shi J, Jia J (2018) Path aggregation network for instance segmentation. In: Computer Vision and Pattern Recognition (CVPR), no.116: 8759\u20138768","DOI":"10.1109\/CVPR.2018.00913"},{"key":"16352_CR29","first-page":"1150","volume-title":"International conference on computer vision (ICCV)","author":"DG Lowe","year":"1999","unstructured":"Lowe DG (1999) Object recognition from local scale-invariant features. In: International Conference on Computer Vision (ICCV) 2:1150\u20131157"},{"key":"16352_CR30","first-page":"555","volume-title":"International conference on computer vision (ICCV)","author":"C Papageorgiou","year":"1998","unstructured":"Papageorgiou C, Oren M, Poggio T (1998) A general framework for object detection. In: International Conference on Computer Vision (ICCV) 5(2):555\u2013562"},{"key":"16352_CR31","first-page":"6517","volume-title":"Computer vision and pattern recognition (CVPR)","author":"J Redmon","year":"2017","unstructured":"Redmon J, Farhadi A (2017) YOLO9000: better, faster, stronger. In: Computer Vision and Pattern Recognition (CVPR), pp 6517\u20136525. arXiv.1612.08242"},{"key":"16352_CR32","first-page":"1","volume-title":"arXiv: computer vision and pattern recognition (CVPR)","author":"J Redmon","year":"2018","unstructured":"Redmon J, Farhadi A (2018) YOLOv3: an incremental improvement. In: arXiv: Computer Vision and Pattern Recognition (CVPR), pp 1\u20136. arXiv:1804.02767"},{"key":"16352_CR33","doi-asserted-by":"publisher","first-page":"779","DOI":"10.1109\/CVPR.2016.91","volume-title":"Computer vision and pattern recognition (CVPR)","author":"J Redmon","year":"2016","unstructured":"Redmon J, Divvala SK, Girshick R, Farhadi A (2016) You only look once: unified, real-time object detection. In: Computer Vision and Pattern Recognition (CVPR), pp 779\u2013788. https:\/\/doi.org\/10.1109\/CVPR.2016.91"},{"key":"16352_CR34","first-page":"91","volume-title":"Neural information processing systems (NIPS)","author":"S Ren","year":"2015","unstructured":"Ren S, He K, Girshick R, Sun J (2015) Faster R-CNN: towards real-time object detection with region proposal networks. In: Neural Information Processing Systems (NIPS) 28:91\u201399"},{"key":"16352_CR35","first-page":"17","volume-title":"The dynamic representation of scenes visual cognition","author":"RA Rensink","year":"2000","unstructured":"Ronald A. Rensink (2000) The dynamic representation of scenes visual cognition 7:17-42"},{"key":"16352_CR36","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky O, Deng J, Hao S, Krause J, Satheesh S, Ma S, Huang Z, Karpathy A, Khosla A, Bernstein MS, Berg AC, Fei-Fei L (2015) ImageNet large scale visual recognition challenge. Int J Comput Vis 115:211\u2013252","journal-title":"Int J Comput Vis"},{"key":"16352_CR37","doi-asserted-by":"publisher","unstructured":"Sean B, Lawrence Zitnick C, Bala K, Girshick R (2016) Inside-outside net: detecting objects in context with skip pooling and recurrent neural networks. Computer vision and pattern recognition (CVPR). https:\/\/doi.org\/10.1109\/CVPR.2016.314","DOI":"10.1109\/CVPR.2016.314"},{"key":"16352_CR38","first-page":"3626","volume-title":"Computer vision and pattern recognition (CVPR)","author":"P Sermanet","year":"2013","unstructured":"Sermanet P, Kavukcuoglu K,Chintala S, LeCun Y (2013) Pedestrian detection with unsupervised multi-stage feature learning. In: Computer Vision and Pattern Recognition (CVPR), pp 3626\u20133533. arXiv:1212.0142"},{"key":"16352_CR39","first-page":"958","volume-title":"International conference on document analysis and recognition","author":"PY Simard","year":"2003","unstructured":"Simard PY, Steinkraus DW, Platt J (2003) Best practices for convolutional neural networks applied to visual document analysis. In: International conference on document analysis and recognition. IEEE Computer Society, Los Alamitos, 3:958\u2013962"},{"key":"16352_CR40","doi-asserted-by":"publisher","first-page":"858","DOI":"10.1016\/j.apsusc.2013.09.002","volume":"285","author":"K Song","year":"2013","unstructured":"Song K, Yan Y (2013) A noise robust method based on completed local binary patterns for hot-rolled steel strip surface defects. Appl Surf Sci 285:858\u2013864","journal-title":"Appl Surf Sci"},{"key":"16352_CR41","first-page":"3104","volume-title":"Neural information processing systems (NIPS)","author":"I Sutskever","year":"2014","unstructured":"Sutskever I, Vinyals O, Le QV (2014) Sequence to sequence learning with neural networks. In: Neural Information Processing Systems (NIPS) 27:3104\u20133112"},{"key":"16352_CR42","doi-asserted-by":"publisher","unstructured":"van de Sande KEA, Uijlings J, Gevers T, Smeulders AWM (2011) Segmentation as selective search for object recognition. In: International Conference on Computer Vision (ICCV), pp 1879\u20131886. https:\/\/doi.org\/10.1109\/ICCV.2011.6126456","DOI":"10.1109\/ICCV.2011.6126456"},{"key":"16352_CR43","first-page":"5998","volume-title":"Neural information processing systems (NIPS)","author":"A Vaswani","year":"2017","unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser L, Polosukhin I (2017) Attention is all you need. In: Neural Information Processing systems (NIPS) 30:5998\u20136008"},{"key":"16352_CR44","doi-asserted-by":"crossref","unstructured":"Wang C-Y, Liao H-YM, Wu Y-H, Chen P-Y, Hsieh J-W, Yeh I-H (2020) CSPNet: a new backbone that can enhance learning capability of CNN. In: Computer Vision and Pattern Recognition (CVPR), pp 390\u2013391. arXiv:1911.11929","DOI":"10.1109\/CVPRW50498.2020.00203"},{"key":"16352_CR45","first-page":"818","volume-title":"European conference on computer vision (ECCV)","author":"MD Zeiler","year":"2014","unstructured":"Zeiler MD, Fergus R (2014) Visualizing and understanding convolutional networks. In: European Conference on Computer Vision (ECCV) 8689:818\u2013833"},{"key":"16352_CR46","doi-asserted-by":"publisher","first-page":"3776","DOI":"10.3390\/rs13183776","volume":"13","author":"L Zhu","year":"2021","unstructured":"Zhu L, Geng X, Li Z, Liu C (2021) Improving YOLOv5 with attention mechanism for detecting boulders from planetary images. Remote Sens 13:3776","journal-title":"Remote Sens"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-023-16352-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-023-16352-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-023-16352-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,15]],"date-time":"2024-02-15T10:08:49Z","timestamp":1707991729000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-023-16352-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,26]]},"references-count":46,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2024,2]]}},"alternative-id":["16352"],"URL":"https:\/\/doi.org\/10.1007\/s11042-023-16352-3","relation":{},"ISSN":["1573-7721"],"issn-type":[{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,7,26]]},"assertion":[{"value":"3 March 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 May 2023","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 July 2023","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 July 2023","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declared that there is no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}