{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T14:42:26Z","timestamp":1778251346019,"version":"3.51.4"},"reference-count":41,"publisher":"Wiley","issue":"1","license":[{"start":{"date-parts":[[2021,3,22]],"date-time":"2021-03-22T00:00:00Z","timestamp":1616371200000},"content-version":"vor","delay-in-days":80,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Opening Project of Key Laboratory of Power Electronics and Motion Control of Anhui Higher Education Institutions","award":["PEMC1902"],"award-info":[{"award-number":["PEMC1902"]}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Computational Intelligence and Neuroscience"],"published-print":{"date-parts":[[2021,1]]},"abstract":"<jats:p>In recent years, more and more scholars devoted themselves to the research of the target detection algorithm due to the continuous development of deep learning. Among them, the detection and recognition of small and complex targets are still a problem to be solved. The authors of this article have understood the shortcomings of the deep learning detection algorithm in detecting small and complex defect targets and would like to share a new improved target detection algorithm in steel surface defect detection. The steel surface defects will affect the quality of steel seriously. We find that most of the current detection algorithms for NEU\u2010DET dataset detection accuracy are low, so we choose to verify a steel surface defect detection algorithm based on machine vision on this dataset for the problem of defect detection in steel production. A series of improvement measures are carried out in the traditional Faster R\u2010CNN algorithm, such as reconstructing the network structure of Faster R\u2010CNN. Based on the small features of the target, we train the network with multiscale fusion. For the complex features of the target, we replace part of the conventional convolution network with a deformable convolution network. The experimental results show that the deep learning network model trained by the proposed method has good detection performance, and the mean average precision is 0.752, which is 0.128 higher than the original algorithm. Among them, the average precision of crazing, inclusion, patches, pitted surface, rolled in scale and scratches is 0.501, 0.791, 0.792, 0.874, 0.649, and 0.905, respectively. The detection method is able to identify small target defects on the steel surface effectively, which can provide a reference for the automatic detection of steel defects.<\/jats:p>","DOI":"10.1155\/2021\/5592878","type":"journal-article","created":{"date-parts":[[2021,3,22]],"date-time":"2021-03-22T22:20:09Z","timestamp":1616451609000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":233,"title":["A New Steel Defect Detection Algorithm Based on Deep Learning"],"prefix":"10.1155","volume":"2021","author":[{"given":"Weidong","family":"Zhao","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5622-3073","authenticated-orcid":false,"given":"Feng","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Hancheng","family":"Huang","sequence":"additional","affiliation":[]},{"given":"Dan","family":"Li","sequence":"additional","affiliation":[]},{"given":"Wei","family":"Cheng","sequence":"additional","affiliation":[]}],"member":"311","published-online":{"date-parts":[[2021,3,22]]},"reference":[{"key":"e_1_2_7_1_2","first-page":"1417","article-title":"Classification and formation mechanism of typical press in scale of hot rolled steel plate","volume":"31","author":"Sun B.","year":"2010","journal-title":"Journal of Northeastern University (Natural Science)"},{"key":"e_1_2_7_2_2","doi-asserted-by":"publisher","DOI":"10.1364\/ao.55.000047"},{"key":"e_1_2_7_3_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jmapro.2019.12.015"},{"key":"e_1_2_7_4_2","doi-asserted-by":"publisher","DOI":"10.1364\/AO.53.008002"},{"key":"e_1_2_7_5_2","doi-asserted-by":"publisher","DOI":"10.1109\/tim.2019.2915404"},{"key":"e_1_2_7_6_2","doi-asserted-by":"publisher","DOI":"10.1016\/S2095-3119(20)63168-9"},{"key":"e_1_2_7_7_2","doi-asserted-by":"publisher","DOI":"10.1364\/ao.56.000184"},{"key":"e_1_2_7_8_2","first-page":"1338","article-title":"A review on object detection based on deep convoltional neural networks for autonomous driving","volume":"2019","author":"Lu J.","year":"2019","journal-title":"2019 Chinese Control and Decision Conference (CCDC)"},{"key":"e_1_2_7_9_2","doi-asserted-by":"publisher","DOI":"10.5573\/ieiespc.2015.4.1.035"},{"key":"e_1_2_7_10_2","first-page":"12","article-title":"Improved Gabor filter for detection of strip surface defects","volume":"45","author":"Qu E.","year":"2017","journal-title":"Journal of Huazhong University of Science and Technology (Natural Science Edition)"},{"key":"e_1_2_7_11_2","first-page":"65","article-title":"Design of surface defect detection system for cold rolled strip","volume":"1","author":"Xu S.","year":"2017","journal-title":"Instrument Technique and Sensor"},{"key":"e_1_2_7_12_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10566-6_7"},{"key":"e_1_2_7_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/tii.2019.2958826"},{"key":"e_1_2_7_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/tim.2020.3030167"},{"key":"e_1_2_7_15_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.optlaseng.2019.05.005"},{"key":"e_1_2_7_16_2","doi-asserted-by":"publisher","DOI":"10.3390\/s20061562"},{"key":"e_1_2_7_17_2","doi-asserted-by":"crossref","unstructured":"VannocciM. RitaccoA. andCastellanoA. Flatness defect detection and classification in hot rolled steel strips using convolutional neural networks 2019.","DOI":"10.1007\/978-3-030-20518-8_19"},{"key":"e_1_2_7_18_2","article-title":"EDRNet: Encoder-decoder residual network for salient object detection of strip steel surface defects","volume":"99","author":"Song G.","year":"2020","journal-title":"IEEE Transactions on Instrumentation and Measurement"},{"key":"e_1_2_7_19_2","article-title":"Research on surface defect detection of metal sheet and strip based on multi-level feature Faster R-CNN","volume":"2020","author":"Wang H.","year":"2020","journal-title":"Mechanical Science and Technology for Aerospace Engineering"},{"key":"e_1_2_7_20_2","first-page":"362","article-title":"Research on surface defect detection and implementation of metal workpiece based on improved Faster R-CNN","volume":"49","author":"Dai X.","year":"2020","journal-title":"Surface Technology"},{"key":"e_1_2_7_21_2","article-title":"Deep residual learning for image recognition","volume":"2016","author":"He K.","year":"2016","journal-title":"IEEE Computer Society"},{"key":"e_1_2_7_22_2","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/1642\/1\/012011"},{"key":"e_1_2_7_23_2","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/1576\/1\/012040"},{"key":"e_1_2_7_24_2","doi-asserted-by":"publisher","DOI":"10.1007\/s42979-020-0114-9"},{"key":"e_1_2_7_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2016.2577031"},{"key":"e_1_2_7_26_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2020.08.026"},{"key":"e_1_2_7_27_2","doi-asserted-by":"publisher","DOI":"10.3390\/s20164353"},{"key":"e_1_2_7_28_2","doi-asserted-by":"crossref","unstructured":"LinT. Doll\u00e1rP. 0 andGirshickR. Feature pyramid networks for object detection 2016.","DOI":"10.1109\/CVPR.2017.106"},{"key":"e_1_2_7_29_2","doi-asserted-by":"publisher","DOI":"10.3390\/s20082360"},{"key":"e_1_2_7_30_2","doi-asserted-by":"publisher","DOI":"10.1080\/2150704x.2020.1784491"},{"key":"e_1_2_7_31_2","doi-asserted-by":"crossref","unstructured":"BodlaN. SinghB. andChellappaR. Soft-NMS-improving object detection with one line of code 2017.","DOI":"10.1109\/ICCV.2017.593"},{"key":"e_1_2_7_32_2","volume-title":"SSD: Single Shot Multi Box Detector","author":"Liu W.","year":"2016"},{"key":"e_1_2_7_33_2","doi-asserted-by":"publisher","DOI":"10.1587\/elex.11.20140535"},{"key":"e_1_2_7_34_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11390-019-1975-z"},{"key":"e_1_2_7_35_2","doi-asserted-by":"publisher","DOI":"10.3390\/rs11030286"},{"key":"e_1_2_7_36_2","doi-asserted-by":"crossref","unstructured":"DaiJ.andXiongY. Deformable convolutional networks Proceedings of the 2017 IEEE International Conference on Computer Vision 2017 Venice Italy.","DOI":"10.1109\/ICCV.2017.89"},{"key":"e_1_2_7_37_2","doi-asserted-by":"publisher","DOI":"10.3390\/s20174939"},{"key":"e_1_2_7_38_2","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2018.2858826"},{"key":"e_1_2_7_39_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11063-020-10197-9"},{"key":"e_1_2_7_40_2","doi-asserted-by":"publisher","DOI":"10.12677\/JISP.2020.92013"},{"key":"e_1_2_7_41_2","article-title":"Adaptive image contrast enhancement by computing distances into a 4-dimensional fuzzy unit hypercube","volume":"1","author":"Versaci M.","year":"2017","journal-title":"IEEE Access"}],"container-title":["Computational Intelligence and Neuroscience"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/downloads.hindawi.com\/journals\/cin\/2021\/5592878.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/downloads.hindawi.com\/journals\/cin\/2021\/5592878.xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1155\/2021\/5592878","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,6]],"date-time":"2024-08-06T12:09:42Z","timestamp":1722946182000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1155\/2021\/5592878"}},"subtitle":[],"editor":[{"given":"Mario","family":"Versaci","sequence":"additional","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2021,1]]},"references-count":41,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2021,1]]}},"alternative-id":["10.1155\/2021\/5592878"],"URL":"https:\/\/doi.org\/10.1155\/2021\/5592878","archive":["Portico"],"relation":{},"ISSN":["1687-5265","1687-5273"],"issn-type":[{"value":"1687-5265","type":"print"},{"value":"1687-5273","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,1]]},"assertion":[{"value":"2021-01-31","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-03-09","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-03-22","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"5592878"}}