{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T03:44:39Z","timestamp":1782791079204,"version":"3.54.5"},"reference-count":52,"publisher":"ASME International","issue":"4","license":[{"start":{"date-parts":[[2023,11,24]],"date-time":"2023-11-24T00:00:00Z","timestamp":1700784000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.asme.org\/publications-submissions\/publishing-information\/legal-policies"}],"funder":[{"DOI":"10.13039\/501100004614","name":"China Institute of Water Resources and Hydropower Research","doi-asserted-by":"publisher","award":["the National Key R & D Program of China \/ 2022ZD0115401"],"award-info":[{"award-number":["the National Key R & D Program of China \/ 2022ZD0115401"]}],"id":[{"id":"10.13039\/501100004614","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["asmedigitalcollection.asme.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,4,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>In contemporary industrial systems, ensuring the quality of object surfaces has become an essential and inescapable aspect of factory inspections. Cascade regional convolutional neural network (cascade R-CNN), an object detection and instance segmentation algorithm based on deep learning, has been widely applied in numerous industrial applications. Nonetheless, there is still space for improving the detection of defects on metal surfaces. The cascade R-CNN does not currently have good results in metal defect detection, but after improving it by combining some newly proposed modules, cascade R-CNN has a good performance. This article proposes an enhanced metal defect detection method based on cascade R-CNN. Specifically, the improved backbone network is employed to acquire the features of images, which enables more precise localization. Additionally, up and down sampling is combined to extract multiscale defect feature maps, and contrast histogram equalization enhancement is utilized to tackle the issue of unclear contrast in the data. Experimental results demonstrate that the proposed approach achieves a mean average precision (mAP) of 0.754 on the NEU-DET dataset and outperforms the cascade R-CNN model by 9.2%.<\/jats:p>","DOI":"10.1115\/1.4063860","type":"journal-article","created":{"date-parts":[[2023,10,20]],"date-time":"2023-10-20T12:02:37Z","timestamp":1697803357000},"update-policy":"https:\/\/doi.org\/10.1115\/crossmarkpolicy-asme","source":"Crossref","is-referenced-by-count":31,"title":["Metal Surface Defect Detection Method Based on Improved Cascade R-CNN"],"prefix":"10.1115","volume":"24","author":[{"given":"Yani","family":"Wang","sequence":"first","affiliation":[{"name":"Tsinghua University Department of Automation, , Beijing 100084 , China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiang","family":"Wang","sequence":"additional","affiliation":[{"name":"Tsinghua University Department of Automation, , Beijing 100084 , China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruiyang","family":"Hao","sequence":"additional","affiliation":[{"name":"Tsinghua University Department of Automation, , Beijing 100084 , China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bingyu","family":"Lu","sequence":"additional","affiliation":[{"name":"Tsinghua University Department of Automation, , Beijing 100084 , China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Biqing","family":"Huang","sequence":"additional","affiliation":[{"name":"Tsinghua University Department of Automation, , Beijing 100084 , China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"33","published-online":{"date-parts":[[2023,11,24]]},"reference":[{"issue":"2","key":"2023112407031442900_CIT0001","doi-asserted-by":"publisher","first-page":"311","DOI":"10.3390\/met12020311","article-title":"Strip Steel Surface Defects Classification Based on Generative Adversarial Network and Attention Mechanism","volume":"12","author":"Hao","year":"2022","journal-title":"Metals"},{"key":"2023112407031442900_CIT0002","first-page":"327","article-title":"Defect Detection and Classification of Strip Steel Based on Improved VIT Model","author":"Xing","year":"2022"},{"key":"2023112407031442900_CIT0003","first-page":"257","article-title":"Real-Time Classification of Steel Strip Surface Defects Based on Deep CNNs","author":"Liu","year":"2018"},{"issue":"8","key":"2023112407031442900_CIT0004","doi-asserted-by":"publisher","first-page":"924","DOI":"10.3139\/146.101121","article-title":"Stretch-Zone Analysis by Image Processing for the Evaluation of Initiation Fracture Toughness of a HSLA Steel","volume":"96","author":"Tarafder","year":"2005","journal-title":"Z. Metallkunde"},{"issue":"10","key":"2023112407031442900_CIT0005","first-page":"56","article-title":"Steel Strip Surface Defects Detection Based on Mathematical Morphology","volume":"22","author":"Bo","year":"2010","journal-title":"J. Iron Steel Res."},{"key":"2023112407031442900_CIT0006","doi-asserted-by":"crossref","DOI":"10.4028\/www.scientific.net\/AMM.411-414.1218","article-title":"Fault Automatic Detection Method of Steel Cord Conveyor Belt Based on Gabor Filter Bank","author":"Zhang","year":"2013"},{"key":"2023112407031442900_CIT0007","first-page":"479","article-title":"Surface Defects Detection on Rolled Steel Strips by Gabor Filters","author":"Medina","year":"2008"},{"issue":"1","key":"2023112407031442900_CIT0008","first-page":"124","article-title":"Strip Steel Defect Detection Based on Morphological Enhancement and Image Fusion","volume":"48","author":"Wang","year":"2018","journal-title":"Laser Infrared."},{"key":"2023112407031442900_CIT0009","doi-asserted-by":"crossref","first-page":"474","DOI":"10.1016\/B978-0-12-336156-1.50061-6","volume-title":"Graphics Gems.","author":"Zuiderveld","year":"1994","edition":"P. S. Heckbert"},{"issue":"3","key":"2023112407031442900_CIT0010","doi-asserted-by":"publisher","first-page":"355","DOI":"10.1016\/S0734-189X(87)80186-X","article-title":"Adaptive Histogram Equalization and Its Variations","volume":"39","author":"Pizer","year":"1987","journal-title":"Comput. Vis. Graph. Image Process."},{"key":"2023112407031442900_CIT0011","first-page":"2735","article-title":"ResNeSt: Split-Attention Networks","author":"Zhang","year":"2022"},{"key":"2023112407031442900_CIT0012","first-page":"8759","article-title":"Path Aggregation Network for Instance Segmentation","author":"Liu","year":"2018"},{"key":"2023112407031442900_CIT0013","first-page":"936","article-title":"Feature Pyramid Networks for Object Detection","author":"Lin","year":"2017"},{"issue":"2","key":"2023112407031442900_CIT0014","doi-asserted-by":"publisher","first-page":"386","DOI":"10.1109\/TPAMI.2018.2844175","article-title":"Mask R-CNN","volume":"42","author":"He","year":"2020","journal-title":"IEEE. Trans. Pattern. Anal. Mach. Intell."},{"issue":"8","key":"2023112407031442900_CIT0015","doi-asserted-by":"publisher","first-page":"1611","DOI":"10.1093\/ietfec\/e90-a.8.1611","article-title":"High Accuracy Bicubic Interpolation Using Image Local Features","volume":"E90A","author":"Yuan","year":"2007","journal-title":"IEICE Trans. Fundam. Electron. Comput. Sci."},{"issue":"2","key":"2023112407031442900_CIT0016","doi-asserted-by":"publisher","first-page":"201","DOI":"10.1016\/0304-3991(81)90061-9","article-title":"Bilinear Interpolation of Digital Images","volume":"6","author":"SMITH","year":"1981","journal-title":"Ultramicroscopy"},{"key":"2023112407031442900_CIT0017","article-title":"Cascade RPN: Delving Into High-Quality Region Proposal Network With Adaptive Convolution","author":"Vu","year":"2019"},{"key":"2023112407031442900_CIT0018","first-page":"2989","article-title":"Rank & Sort Loss for Object Detection and Instance Segmentation","author":"Oksuz","year":"2021"},{"issue":"4","key":"2023112407031442900_CIT0019","doi-asserted-by":"publisher","first-page":"040801","DOI":"10.1115\/1.4049535","article-title":"Image-Based Surface Defect Detection Using Deep Learning: A Review","volume":"21","author":"Bhatt","year":"2021","journal-title":"ASME J. Comput. Inf. Sci. Eng."},{"issue":"2, SI","key":"2023112407031442900_CIT0020","doi-asserted-by":"publisher","first-page":"020301","DOI":"10.1115\/1.4046427","article-title":"Special Issue: Machine Learning Applications in Manufacturing","volume":"20","author":"Liu","year":"2020","journal-title":"ASME J. Comput. Inf. Sci. Eng."},{"key":"2023112407031442900_CIT0021","first-page":"1","article-title":"Defect Detection of Steel Surface Using Entropy Segmentation","author":"Nand","year":"2014"},{"key":"2023112407031442900_CIT0022","first-page":"1","article-title":"Based on Gabor and Texture Suppression Scratch Detection for Cell Phone Accessories","volume":"40","author":"Di","year":"2014","journal-title":"Comput. Eng."},{"issue":"May 5","key":"2023112407031442900_CIT0023","doi-asserted-by":"publisher","first-page":"70","DOI":"10.1016\/j.jvcir.2015.04.005","article-title":"Genetic Algorithm and Mathematical Morphology Based Binarization Method for Strip Steel Defect Image with Non-Uniform Illumination","volume":"37","author":"Liu","year":"2016","journal-title":"J. Vis. Commun. Image Represent."},{"issue":"5","key":"2023112407031442900_CIT0024","doi-asserted-by":"publisher","first-page":"053108","DOI":"10.1117\/1.OE.56.5.053108","article-title":"Vision-Based Surface Defect Inspection for Thick Steel Plates","volume":"56","author":"Yun","year":"2017","journal-title":"Opt. Eng."},{"key":"2023112407031442900_CIT0025","first-page":"779","article-title":"You Only Look Once: Unified, Real-Time Object Detection","author":"Redmon","year":"2016"},{"issue":"15","key":"2023112407031442900_CIT0026","doi-asserted-by":"publisher","first-page":"3127","DOI":"10.3390\/app9153127","article-title":"Periodic Surface Defect Detection in Steel Plates Based on Deep Learning","volume":"9","author":"Liu","year":"2019","journal-title":"Appl. Sci."},{"issue":"2, SI","key":"2023112407031442900_CIT0027","doi-asserted-by":"publisher","first-page":"021010","DOI":"10.1115\/1.4045719","article-title":"Image Data-Based Surface Texture Characterization and Prediction Using Machine Learning Approaches for Additive Manufacturing","volume":"20","author":"Akhil","year":"2020","journal-title":"ASME J. Comput. Inf. Sci. Eng."},{"issue":"6","key":"2023112407031442900_CIT0028","doi-asserted-by":"publisher","first-page":"1562","DOI":"10.3390\/s20061562","article-title":"Deep Metallic Surface Defect Detection: The New Benchmark and Detection Network","volume":"20","author":"Lv","year":"2020","journal-title":"Sensors"},{"key":"2023112407031442900_CIT0029","first-page":"858","volume-title":"Computer Vision \u2013 ECCV 2016","author":"Liu","year":"2016"},{"issue":"1","key":"2023112407031442900_CIT0030","doi-asserted-by":"publisher","first-page":"142","DOI":"10.1109\/TPAMI.2015.2437384","article-title":"Region-Based Convolutional Networks for Accurate Object Detection and Segmentation","volume":"38","author":"Girshick","year":"2016","journal-title":"IEEE. Trans. Pattern. Anal. Mach. Intell."},{"issue":"3","key":"2023112407031442900_CIT0031","doi-asserted-by":"publisher","first-page":"031005","DOI":"10.1115\/1.4053078","article-title":"Segmentation of Additive Manufacturing Defects Using U-Net","volume":"22","author":"Wong","year":"2022","journal-title":"ASME J. Comput. Inf. Sci. Eng."},{"issue":"3","key":"2023112407031442900_CIT0032","doi-asserted-by":"publisher","first-page":"539","DOI":"10.2355\/isijinternational.ISIJINT-2019-335","article-title":"Enhanced Faster Region Convolutional Neural Networks for Steel Surface Defect Detection","volume":"60","author":"Wei","year":"2020","journal-title":"ISIJ. Int."},{"issue":"1","key":"2023112407031442900_CIT0033","doi-asserted-by":"publisher","first-page":"014501","DOI":"10.1115\/1.4051435","article-title":"Steel Surface Defect Detection Using an Ensemble of Deep Residual Neural Networks","volume":"22","author":"Konovalenko","year":"2022","journal-title":"ASME J. Comput. Inf. Sci. Eng."},{"key":"2023112407031442900_CIT0034","first-page":"6154","article-title":"Cascade R-CNN: Delving Into High Quality Object Detection","author":"Cai","year":"2018"},{"key":"2023112407031442900_CIT0035","first-page":"1440","article-title":"Fast R-CNN","author":"Girshick","year":"2015"},{"issue":"6","key":"2023112407031442900_CIT0036","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","article-title":"Faster R-CNN: Towards Real-Time Object Detection With Region Proposal Networks","volume":"39","author":"Ren","year":"2017","journal-title":"IEEE. Trans. Pattern. Anal. Mach. Intell."},{"key":"2023112407031442900_CIT0037","article-title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","author":"Simonyan","year":"2015"},{"key":"2023112407031442900_CIT0038","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR.2016.90","article-title":"Deep Residual Learning for Image Recognition","author":"He","year":"2016"},{"key":"2023112407031442900_CIT0039","doi-asserted-by":"publisher","first-page":"708097","DOI":"10.3389\/fphy.2021.708097","article-title":"A Lightweight One-Stage Defect Detection Network for Small Object Based on Dual Attention Mechanism and PAFPN","volume":"9","author":"Zhang","year":"2021","journal-title":"Front. Phys."},{"key":"2023112407031442900_CIT0040","volume-title":"MIPPR 2019: Pattern Recognition and Computer Vision, Vol. 11430 of Proceedings of SPIE","author":"Liu","year":"2020"},{"key":"2023112407031442900_CIT0041","doi-asserted-by":"publisher","first-page":"2153","DOI":"10.1109\/TMM.2022.3143707","article-title":"Latent Feature Pyramid Network for Object Detection","volume":"25","author":"Xie","year":"2023","journal-title":"IEEE Trans. Multimed."},{"issue":"27","key":"2023112407031442900_CIT0042","doi-asserted-by":"publisher","first-page":"26161","DOI":"10.1364\/OE.19.026161","article-title":"Bilinear and Bicubic Interpolation Methods for Division of Focal Plane Polarimeters","volume":"19","author":"Gao","year":"2011","journal-title":"Opt. Express"},{"issue":"4","key":"2023112407031442900_CIT0043","first-page":"23","article-title":"Bicubic Interpolation Algorithm Implementation for Image Appearance Enhancement","volume":"8","author":"Rajarapollu","year":"2017","journal-title":"Ijcst"},{"key":"2023112407031442900_CIT0044","first-page":"918","article-title":"Class-Agnostic Object Detection","author":"Jaiswal","year":"2021"},{"issue":"Part B","key":"2023112407031442900_CIT0045","doi-asserted-by":"publisher","first-page":"858","DOI":"10.1016\/j.apsusc.2013.09.002","article-title":"A Noise Robust Method Based on Completed Local Binary Patterns for Hot-Rolled Steel Strip Surface Defects","volume":"285","author":"Song","year":"2013","journal-title":"Appl. Surf. Sci."},{"issue":"2","key":"2023112407031442900_CIT0046","doi-asserted-by":"publisher","first-page":"125","DOI":"10.3390\/info11020125","article-title":"Albumentations: Fast and Flexible Image Augmentations","volume":"11","author":"Buslaev","year":"2020","journal-title":"Information"},{"key":"2023112407031442900_CIT0047","article-title":"Yolov3: An Incremental Improvement","volume-title":"arXiv, abs\/1804.02767.","author":"Redmon","year":"2018"},{"issue":"2","key":"2023112407031442900_CIT0048","doi-asserted-by":"publisher","first-page":"318","DOI":"10.1109\/TPAMI.2018.2858826","article-title":"Focal Loss for Dense Object Detection","volume":"42","author":"Lin","year":"2020","journal-title":"IEEE. Trans. Pattern. Anal. Mach. Intell."},{"key":"2023112407031442900_CIT0049","first-page":"765","article-title":"Cornernet: detecting objects as paired keypoints","author":"Law","year":"2018"},{"key":"2023112407031442900_CIT0050","first-page":"6568","article-title":"Centernet: Keypoint Triplets for Object Detection","author":"Duan","year":"2019"},{"key":"2023112407031442900_CIT0051","first-page":"1","article-title":"Defective Surface Detection Based on Improved Faster R-cnn","author":"Duan","year":"2022"},{"key":"2023112407031442900_CIT0052","article-title":"MMDetection: Open MMLAB Detection Toolbox and Benchmark","volume-title":"arXiv preprint arXiv:1906.07155.","author":"Chen","year":"2019"}],"container-title":["Journal of Computing and Information Science in Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/asmedigitalcollection.asme.org\/computingengineering\/article-pdf\/24\/4\/041002\/7062945\/jcise_24_4_041002.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/asmedigitalcollection.asme.org\/computingengineering\/article-pdf\/24\/4\/041002\/7062945\/jcise_24_4_041002.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,24]],"date-time":"2023-11-24T07:03:30Z","timestamp":1700809410000},"score":1,"resource":{"primary":{"URL":"https:\/\/asmedigitalcollection.asme.org\/computingengineering\/article\/24\/4\/041002\/1169612\/Metal-Surface-Defect-Detection-Method-Based-on"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,24]]},"references-count":52,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2024,4,1]]}},"URL":"https:\/\/doi.org\/10.1115\/1.4063860","relation":{},"ISSN":["1530-9827","1944-7078"],"issn-type":[{"value":"1530-9827","type":"print"},{"value":"1944-7078","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,11,24]]},"article-number":"041002"}}