Real-time Detection of Steel Strip Surface Defects Based on Improved YOLO Detection Network
The surface defects of steel strip have diverse and complex features, and surface defects caused by different production lines tend to have different characteristics. Therefore, the detection algorithms for the surface defects of steel strip should have good generalization performance. Aiming at det...
Saved in:
| Published in | IFAC-PapersOnLine Vol. 51; no. 21; pp. 76 - 81 |
|---|---|
| Main Authors | , , , |
| Format | Journal Article |
| Language | English |
| Published |
Elsevier Ltd
2018
|
| Subjects | |
| Online Access | Get full text |
Cover
Loading…
| Abstract | The surface defects of steel strip have diverse and complex features, and surface defects caused by different production lines tend to have different characteristics. Therefore, the detection algorithms for the surface defects of steel strip should have good generalization performance. Aiming at detecting surface defects of steel strip, we established a dataset of six types of surface defects on cold-rolled steel strip and augmented it in order to reduce over-fitting. We improved the You Only Look Once (YOLO) network and made it all convolutional. Our improved network, which consists of 27 convolution layers, provides an end-to-end solution for the surface defects detection of steel strip. We evaluated the six types of defects with our network and reached performance of 97.55% mAP and 95.86% recall rate. Besides, our network achieves 99% detection rate with speed of 83 FPS, which provides methodological support for real-time surface defects detection of steel strip. It can also predict the location and size information of defect regions, which is of great significance for evaluating the quality of an entire steel strip production line. |
|---|---|
| AbstractList | The surface defects of steel strip have diverse and complex features, and surface defects caused by different production lines tend to have different characteristics. Therefore, the detection algorithms for the surface defects of steel strip should have good generalization performance. Aiming at detecting surface defects of steel strip, we established a dataset of six types of surface defects on cold-rolled steel strip and augmented it in order to reduce over-fitting. We improved the You Only Look Once (YOLO) network and made it all convolutional. Our improved network, which consists of 27 convolution layers, provides an end-to-end solution for the surface defects detection of steel strip. We evaluated the six types of defects with our network and reached performance of 97.55% mAP and 95.86% recall rate. Besides, our network achieves 99% detection rate with speed of 83 FPS, which provides methodological support for real-time surface defects detection of steel strip. It can also predict the location and size information of defect regions, which is of great significance for evaluating the quality of an entire steel strip production line. |
| Author | Geng, Jiahui Su, Zhenfeng Li, Jiangyun Yin, Yixin |
| Author_xml | – sequence: 1 givenname: Jiangyun surname: Li fullname: Li, Jiangyun email: leejy@ustb.edu.cn organization: Key Laboratory of Knowledge Automation for Industrial Processes, Ministry of Education,School of Automation & Electrical Engineering, University of Science and Technology Beijing, Beijing 100083, China – sequence: 2 givenname: Zhenfeng surname: Su fullname: Su, Zhenfeng organization: Key Laboratory of Knowledge Automation for Industrial Processes, Ministry of Education,School of Automation & Electrical Engineering, University of Science and Technology Beijing, Beijing 100083, China – sequence: 3 givenname: Jiahui surname: Geng fullname: Geng, Jiahui organization: Key Laboratory of Knowledge Automation for Industrial Processes, Ministry of Education,School of Automation & Electrical Engineering, University of Science and Technology Beijing, Beijing 100083, China – sequence: 4 givenname: Yixin surname: Yin fullname: Yin, Yixin email: yyx@ies.ustb.edu.cn organization: School of Automation & Electrical Engineering, University of Science and Technology Beijing, Beijing 100083, China |
| BookMark | eNqFkL9OwzAQhy1UJErpGzDkBRKcOE5iBiQo_ypVVKIwIAbLvZwll7SubFPE2-OoDIgBlvMNv-_u_B2TwcZukJDTnGY5zauzVWa0AttlBc2bjIqszIsDMixKytNGVGzwoz8iY-9XlNJCVGUtmiF5fUTVpcGsMbnGgBCM3SRWJ4uA2MXqzDZZvLu4oQ_oGPDJlfLYJjE3XW-d3cX-ZT6b_-AfMHxY93ZCDrXqPI6_3xF5vr15mtyns_nddHI5S6HMm5DqWgAHaHkjCg4c6yWtgKoGK15RUWvNWEt5oRgrmRK8rRVwoVipKSwLzoCNyPl-LjjrvUMtwQTVXxKcMp3MqexNyZXcm5K9KUmFjKYiXP6Ct86slfv8D7vYYxg_tjPopAeDG8DWuGhBttb8PeAL5JuGyw |
| CitedBy_id | crossref_primary_10_1016_j_egyr_2021_01_095 crossref_primary_10_1016_j_eswa_2023_122361 crossref_primary_10_1088_1361_6501_acb073 crossref_primary_10_1109_JSEN_2024_3356356 crossref_primary_10_3390_designs7030070 crossref_primary_10_3390_a14090257 crossref_primary_10_3233_JIFS_223041 crossref_primary_10_1016_j_measurement_2022_112208 crossref_primary_10_3390_app121910097 crossref_primary_10_1155_jece_2935790 crossref_primary_10_1038_s41598_024_58643_1 crossref_primary_10_1016_j_autcon_2022_104448 crossref_primary_10_1007_s11042_024_19565_2 crossref_primary_10_1038_s41598_024_83430_3 crossref_primary_10_3390_s21217264 crossref_primary_10_1155_2021_7272928 crossref_primary_10_3390_s23177619 crossref_primary_10_3390_s25030828 crossref_primary_10_1155_2022_4405162 crossref_primary_10_3390_s24144630 crossref_primary_10_1109_TIM_2022_3144224 crossref_primary_10_1007_s10462_023_10438_y crossref_primary_10_2174_2352096516666230428103829 crossref_primary_10_1109_ACCESS_2024_3447035 crossref_primary_10_3390_electronics13050976 crossref_primary_10_1007_s00371_022_02442_0 crossref_primary_10_1093_jigpal_jzae053 crossref_primary_10_3390_s24051555 crossref_primary_10_3390_sym16040458 crossref_primary_10_1088_1742_6596_1631_1_012081 crossref_primary_10_1007_s11709_021_0725_9 crossref_primary_10_1080_08839514_2024_2349981 crossref_primary_10_1007_s00521_022_08112_5 crossref_primary_10_1007_s10586_023_04181_w crossref_primary_10_1002_rob_22356 crossref_primary_10_1016_j_matdes_2023_112600 crossref_primary_10_3390_app12126049 crossref_primary_10_1177_09544062231187606 crossref_primary_10_17780_ksujes_1285080 crossref_primary_10_1002_srin_202300421 crossref_primary_10_1007_s11760_024_03355_2 crossref_primary_10_1109_TIM_2019_2947800 crossref_primary_10_3390_ma13245755 crossref_primary_10_1080_10589759_2024_2393205 crossref_primary_10_1016_j_eswa_2023_122225 crossref_primary_10_1088_1361_6501_ad1228 crossref_primary_10_1109_TIM_2021_3127648 crossref_primary_10_1007_s13369_024_09744_6 crossref_primary_10_26599_Jic_2024_9180037 crossref_primary_10_1016_j_patrec_2023_06_010 crossref_primary_10_1155_2022_2549683 crossref_primary_10_3390_biomimetics9010028 crossref_primary_10_1007_s11633_023_1459_z crossref_primary_10_32604_cmc_2024_050884 crossref_primary_10_1109_ACCESS_2023_3336426 crossref_primary_10_3390_s23177443 crossref_primary_10_3390_s20051459 crossref_primary_10_1007_s00521_022_07990_z crossref_primary_10_1038_s41598_024_64080_x crossref_primary_10_3390_ma14071641 crossref_primary_10_3390_s21206868 crossref_primary_10_1109_TMECH_2021_3058147 crossref_primary_10_1007_s10845_022_01963_8 crossref_primary_10_1109_ACCESS_2024_3417391 crossref_primary_10_1007_s12555_020_0118_1 crossref_primary_10_1109_TIM_2024_3370962 crossref_primary_10_1371_journal_pone_0292082 crossref_primary_10_1007_s12204_024_2723_2 crossref_primary_10_1109_TIM_2023_3272033 crossref_primary_10_1360_SSI_2021_0336 crossref_primary_10_1109_TNNLS_2023_3324188 crossref_primary_10_1111_mice_13087 crossref_primary_10_1007_s11042_023_15465_z crossref_primary_10_1155_2022_9911905 crossref_primary_10_1007_s12204_022_2471_0 crossref_primary_10_3390_coatings13010017 crossref_primary_10_1016_j_ndteint_2021_102549 crossref_primary_10_1016_j_procs_2022_12_285 crossref_primary_10_1109_TIM_2019_2963555 crossref_primary_10_1109_JSEN_2021_3112698 crossref_primary_10_3390_electronics12112440 crossref_primary_10_1108_EC_11_2019_0502 crossref_primary_10_1016_j_mineng_2021_107020 crossref_primary_10_1109_JSEN_2020_2977366 crossref_primary_10_1109_ACCESS_2020_2977821 crossref_primary_10_3390_s22249897 crossref_primary_10_1016_j_jmsy_2022_06_011 crossref_primary_10_1016_j_ultramic_2025_114116 crossref_primary_10_1049_ipr2_12647 crossref_primary_10_3390_app142411953 crossref_primary_10_3390_met11030388 crossref_primary_10_1016_j_sciaf_2024_e02066 crossref_primary_10_1155_2022_9595286 crossref_primary_10_1016_j_matpr_2022_06_474 crossref_primary_10_1109_ACCESS_2022_3224037 crossref_primary_10_1002_adc2_196 crossref_primary_10_3390_s21155039 crossref_primary_10_1541_ieejjia_23006878 crossref_primary_10_1016_j_aei_2021_101456 crossref_primary_10_1016_j_aei_2024_102727 crossref_primary_10_1016_j_compeleceng_2019_05_009 crossref_primary_10_3390_app12041883 crossref_primary_10_3390_ma17235873 crossref_primary_10_1007_s13369_022_07567_x crossref_primary_10_1016_j_measurement_2021_109185 crossref_primary_10_1016_j_compmedimag_2020_101732 crossref_primary_10_3390_rs16162953 crossref_primary_10_1007_s12541_019_00269_9 crossref_primary_10_1088_1742_6596_1755_1_012041 crossref_primary_10_3390_electronics12081856 crossref_primary_10_1088_1742_6596_2560_1_012007 crossref_primary_10_1049_ipr2_12935 crossref_primary_10_3390_app12126276 crossref_primary_10_32628_CSEIT2172122 crossref_primary_10_3390_app12126004 crossref_primary_10_1007_s00170_022_10763_6 crossref_primary_10_1088_1742_6596_1952_2_022043 crossref_primary_10_3390_app13126898 crossref_primary_10_3390_app14135503 crossref_primary_10_3390_met13030507 crossref_primary_10_1088_1402_4896_adb358 crossref_primary_10_3390_make5040083 crossref_primary_10_3390_app15052484 crossref_primary_10_1007_s00170_022_08841_w crossref_primary_10_1007_s10845_023_02317_8 crossref_primary_10_1007_s10462_023_10475_7 crossref_primary_10_1016_j_jmapro_2024_02_006 crossref_primary_10_1007_s00170_023_11963_4 crossref_primary_10_1007_s44196_024_00559_9 crossref_primary_10_1016_j_eswa_2022_118966 crossref_primary_10_1016_j_mlwa_2022_100413 crossref_primary_10_1080_03019233_2022_2078262 crossref_primary_10_1016_j_eswa_2021_116108 crossref_primary_10_1109_TIM_2021_3112784 crossref_primary_10_7717_peerj_cs_1453 crossref_primary_10_3390_s24113610 crossref_primary_10_1016_j_jmapro_2023_12_064 crossref_primary_10_1088_2631_8695_ad5e34 crossref_primary_10_1016_j_engappai_2025_110448 crossref_primary_10_3390_app11146368 crossref_primary_10_1109_TIM_2023_3246499 crossref_primary_10_3390_electronics14061104 crossref_primary_10_3390_sym13091731 crossref_primary_10_1016_j_compeleceng_2024_109090 crossref_primary_10_1016_j_jare_2021_03_015 crossref_primary_10_1007_s00170_021_08399_z crossref_primary_10_3390_electronics11162603 crossref_primary_10_1109_TIM_2022_3176239 crossref_primary_10_1007_s00170_021_06592_8 crossref_primary_10_1016_j_heliyon_2025_e42433 crossref_primary_10_1016_j_rcim_2022_102470 crossref_primary_10_2355_isijinternational_ISIJINT_2020_451 crossref_primary_10_1016_j_engappai_2024_108482 crossref_primary_10_1007_s11668_023_01695_8 crossref_primary_10_1016_j_aei_2022_101530 crossref_primary_10_3390_met13111809 crossref_primary_10_3390_app10041206 crossref_primary_10_1007_s13369_023_08240_7 crossref_primary_10_1109_TIM_2024_3390198 crossref_primary_10_1109_ACCESS_2024_3349628 crossref_primary_10_1016_j_optlaseng_2024_108035 crossref_primary_10_3390_informatics11020025 crossref_primary_10_32604_cmc_2023_041600 crossref_primary_10_47164_ijngc_v14i1_1020 |
| Cites_doi | 10.1109/TPAMI.2013.50 10.1038/nature14539 10.1016/j.neucom.2015.05.134 10.3788/AOS201131.0312004 10.1109/CVPR.2016.91 10.1109/CCDC.2017.7979072 |
| ContentType | Journal Article |
| Copyright | 2018 |
| Copyright_xml | – notice: 2018 |
| DBID | AAYXX CITATION |
| DOI | 10.1016/j.ifacol.2018.09.412 |
| DatabaseName | CrossRef |
| DatabaseTitle | CrossRef |
| DatabaseTitleList | |
| DeliveryMethod | fulltext_linktorsrc |
| EISSN | 2405-8963 |
| EndPage | 81 |
| ExternalDocumentID | 10_1016_j_ifacol_2018_09_412 S2405896318321001 |
| GroupedDBID | 0R~ 0SF 457 AAJQP AALRI AAXUO ABMAC ACGFS ADBBV AFTJW AGHFR AITUG ALMA_UNASSIGNED_HOLDINGS AMRAJ ATDSJ EBS EJD FDB HX~ KQ8 O9- ROL AAYWO AAYXX ADVLN AEXQZ CITATION |
| ID | FETCH-LOGICAL-c418t-f79c5ccd58925c5e7b06c0a8e656097ff33d052a3343a95d7ac59a34f0cb253c3 |
| ISSN | 2405-8963 |
| IngestDate | Thu Apr 24 23:12:34 EDT 2025 Tue Jul 01 04:35:07 EDT 2025 Fri Feb 23 02:20:49 EST 2024 |
| IsDoiOpenAccess | false |
| IsOpenAccess | true |
| IsPeerReviewed | false |
| IsScholarly | false |
| Issue | 21 |
| Keywords | Convolutional Neural Network Surface quality Improved YOLO Network Steel Strip Defect Detection |
| Language | English |
| License | https://www.elsevier.com/tdm/userlicense/1.0 |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-c418t-f79c5ccd58925c5e7b06c0a8e656097ff33d052a3343a95d7ac59a34f0cb253c3 |
| OpenAccessLink | https://doi.org/10.1016/j.ifacol.2018.09.412 |
| PageCount | 6 |
| ParticipantIDs | crossref_citationtrail_10_1016_j_ifacol_2018_09_412 crossref_primary_10_1016_j_ifacol_2018_09_412 elsevier_sciencedirect_doi_10_1016_j_ifacol_2018_09_412 |
| ProviderPackageCode | CITATION AAYXX |
| PublicationCentury | 2000 |
| PublicationDate | 2018 2018-00-00 |
| PublicationDateYYYYMMDD | 2018-01-01 |
| PublicationDate_xml | – year: 2018 text: 2018 |
| PublicationDecade | 2010 |
| PublicationTitle | IFAC-PapersOnLine |
| PublicationYear | 2018 |
| Publisher | Elsevier Ltd |
| Publisher_xml | – name: Elsevier Ltd |
| References | Redmon, J. and Farhadi, A. (2016). Yolo9000: better, faster, stronger. arXiv preprint, 1612. Ke, Lei, Wang (bib0007) 2016 Redmon, J., Divvala, S., Girshick, R., and Farhadi, A. (2016). You only look once: Unified, real-time object detection. In Proceedings of the IEEE conference on computer vision and pattern recognition, 779-788. Zhang (bib00021) 2011; 31 Hu, Liu, Liu, Nie (bib0005) 2016; 181 Springenberg, J.T., Dosovitskiy, A., Brox, T., and Riedmiller, M. (2014). Striving for simplicity: The all convolutional net. arXiv preprint arXiv:1412.6806. Xu, Ai, Zhou, Yang (bib00020) 2013; 35 Ren, He, Girshick, Sun (bib00017) 2015 Krizhevsky, Sutskever, Hinton (bib0008) 2012 Girshick, R. (2015). Fast r-cnn. arXiv preprint arXiv:1504.08083. Guo, Shao, Zhou (bib0004) 2017; 38 Sermanet, P., Eigen, D., Zhang, X., Mathieu, M., Fergus, R., and LeCun, Y. (2013). Overfeat: Integrated recognition, localization and detection using convolutional networks. arXiv preprint arXiv:1312.6229. Chu, M., Zhao, J., Gong, R., and Liu, L. (2017). Steel surface defects recognition based on multi-label classifier with hyper-sphere support vector machine. In Control And Decision Conference (CCDC), 2017 29th Chinese, 3276-3281. IEEE. Radford, A., Metz, L., and Chintala, S. (2015). Unsupervised representation learning with deep convolutional generative adversarial networks. arXiv preprint arXiv:1511.06434. Ioffe, S. and Szegedy, C. (2015). Batch normalization: Accelerating deep network training by reducing internal covariate shift. In International conference on machine learning, 448-456. Masci, J., Meier, U., Ciresan, D., Schmidhuber, J., and Fricout, G. (2012). Steel defect classification with maxpooling convolutional neural networks. In Neural Networks (IJCNN), The 2012 International Joint Conference on, 1-6. IEEE. LeCun, Bengio, Hinton (bib0009) 2015; 521 Lin, M., Chen, Q., and Yan, S. (2013). Network in network. arXiv preprint arXiv:1312.4400. Bengio, Courville, Vincent (bib0001) 2013; 35 Lin, Dollár, Girshick, He, Hariharan, Belongie (bib00011) 2017; 1 Ma, Li, He, Yan, Xi (bib00012) 2017 Guo (10.1016/j.ifacol.2018.09.412_bib0004) 2017; 38 LeCun (10.1016/j.ifacol.2018.09.412_bib0009) 2015; 521 Zhang (10.1016/j.ifacol.2018.09.412_bib00021) 2011; 31 Ren (10.1016/j.ifacol.2018.09.412_bib00017) 2015 Ke (10.1016/j.ifacol.2018.09.412_bib0007) 2016 10.1016/j.ifacol.2018.09.412_bib00013 Krizhevsky (10.1016/j.ifacol.2018.09.412_bib0008) 2012 Xu (10.1016/j.ifacol.2018.09.412_bib00020) 2013; 35 10.1016/j.ifacol.2018.09.412_bib00010 10.1016/j.ifacol.2018.09.412_bib00016 10.1016/j.ifacol.2018.09.412_bib00015 10.1016/j.ifacol.2018.09.412_bib00014 10.1016/j.ifacol.2018.09.412_bib0002 10.1016/j.ifacol.2018.09.412_bib0003 Hu (10.1016/j.ifacol.2018.09.412_bib0005) 2016; 181 10.1016/j.ifacol.2018.09.412_bib00019 10.1016/j.ifacol.2018.09.412_bib00018 10.1016/j.ifacol.2018.09.412_bib0006 Ma (10.1016/j.ifacol.2018.09.412_bib00012) 2017 Bengio (10.1016/j.ifacol.2018.09.412_bib0001) 2013; 35 Lin (10.1016/j.ifacol.2018.09.412_bib00011) 2017; 1 |
| References_xml | – volume: 521 start-page: 436 year: 2015 ident: bib0009 article-title: Deep learning publication-title: nature – year: 2017 ident: bib00012 article-title: Adaptive segmentation algorithm for metal surface defects publication-title: Chinese Journal of scientific Instrument – volume: 31 start-page: 0312004 year: 2011 ident: bib00021 article-title: Vision inspection of metal surface defects based on infrared imaging publication-title: Acta Optica Sinica – volume: 38 start-page: 2797 year: 2017 end-page: 2804 ident: bib0004 article-title: Novel defect recognition method based on adaptive global threshold for highlight mental surface publication-title: Chinese Journal of Scientific Instrument – volume: 35 start-page: 1195 year: 2013 end-page: 1200 ident: bib00020 article-title: Recognition of surface defects in continuous casting slabs based on contourlet transform publication-title: Journal of University of Science Technology Beijing – reference: Ioffe, S. and Szegedy, C. (2015). Batch normalization: Accelerating deep network training by reducing internal covariate shift. In International conference on machine learning, 448-456. – volume: 35 start-page: 1798 year: 2013 end-page: 1828 ident: bib0001 article-title: Representation learning: A review and new perspectives publication-title: IEEE transactions on pattern analysis and machine intelligence – reference: Girshick, R. (2015). Fast r-cnn. arXiv preprint arXiv:1504.08083. – start-page: 1097 year: 2012 end-page: 1105 ident: bib0008 article-title: Imagenet classification with deep convolutional neural networks publication-title: Advances in neural information processing systems – volume: 1 start-page: 4 year: 2017 ident: bib00011 article-title: Feature pyramid networks for object detection publication-title: CVPR – volume: 181 start-page: 86 year: 2016 end-page: 95 ident: bib0005 article-title: Surface defect classification in large-scale strip steel image collection via hybrid chromosome genetic algorithm publication-title: Neurocomputing – year: 2016 ident: bib0007 article-title: Surface defect recognition of hot-rolled steel plates based on tetrolet transform publication-title: Journal of Mechanical Engineering – reference: Redmon, J., Divvala, S., Girshick, R., and Farhadi, A. (2016). You only look once: Unified, real-time object detection. In Proceedings of the IEEE conference on computer vision and pattern recognition, 779-788. – reference: Chu, M., Zhao, J., Gong, R., and Liu, L. (2017). Steel surface defects recognition based on multi-label classifier with hyper-sphere support vector machine. In Control And Decision Conference (CCDC), 2017 29th Chinese, 3276-3281. IEEE. – start-page: 91 year: 2015 end-page: 99 ident: bib00017 article-title: Faster r-cnn: Towards real-time object detection with region proposal networks publication-title: Advances in neural information processing systems – reference: Masci, J., Meier, U., Ciresan, D., Schmidhuber, J., and Fricout, G. (2012). Steel defect classification with maxpooling convolutional neural networks. In Neural Networks (IJCNN), The 2012 International Joint Conference on, 1-6. IEEE. – reference: Redmon, J. and Farhadi, A. (2016). Yolo9000: better, faster, stronger. arXiv preprint, 1612. – reference: Springenberg, J.T., Dosovitskiy, A., Brox, T., and Riedmiller, M. (2014). Striving for simplicity: The all convolutional net. arXiv preprint arXiv:1412.6806. – reference: Lin, M., Chen, Q., and Yan, S. (2013). Network in network. arXiv preprint arXiv:1312.4400. – reference: Radford, A., Metz, L., and Chintala, S. (2015). Unsupervised representation learning with deep convolutional generative adversarial networks. arXiv preprint arXiv:1511.06434. – reference: Sermanet, P., Eigen, D., Zhang, X., Mathieu, M., Fergus, R., and LeCun, Y. (2013). Overfeat: Integrated recognition, localization and detection using convolutional networks. arXiv preprint arXiv:1312.6229. – volume: 1 start-page: 4 year: 2017 ident: 10.1016/j.ifacol.2018.09.412_bib00011 article-title: Feature pyramid networks for object detection publication-title: CVPR – volume: 35 start-page: 1798 issue: 8 year: 2013 ident: 10.1016/j.ifacol.2018.09.412_bib0001 article-title: Representation learning: A review and new perspectives publication-title: IEEE transactions on pattern analysis and machine intelligence doi: 10.1109/TPAMI.2013.50 – ident: 10.1016/j.ifacol.2018.09.412_bib00010 – volume: 521 start-page: 436 issue: 7553 year: 2015 ident: 10.1016/j.ifacol.2018.09.412_bib0009 article-title: Deep learning publication-title: nature doi: 10.1038/nature14539 – ident: 10.1016/j.ifacol.2018.09.412_bib00014 – year: 2016 ident: 10.1016/j.ifacol.2018.09.412_bib0007 article-title: Surface defect recognition of hot-rolled steel plates based on tetrolet transform publication-title: Journal of Mechanical Engineering – year: 2017 ident: 10.1016/j.ifacol.2018.09.412_bib00012 article-title: Adaptive segmentation algorithm for metal surface defects publication-title: Chinese Journal of scientific Instrument – volume: 181 start-page: 86 year: 2016 ident: 10.1016/j.ifacol.2018.09.412_bib0005 article-title: Surface defect classification in large-scale strip steel image collection via hybrid chromosome genetic algorithm publication-title: Neurocomputing doi: 10.1016/j.neucom.2015.05.134 – ident: 10.1016/j.ifacol.2018.09.412_bib00013 – ident: 10.1016/j.ifacol.2018.09.412_bib00016 – ident: 10.1016/j.ifacol.2018.09.412_bib00019 – start-page: 1097 year: 2012 ident: 10.1016/j.ifacol.2018.09.412_bib0008 article-title: Imagenet classification with deep convolutional neural networks publication-title: Advances in neural information processing systems – ident: 10.1016/j.ifacol.2018.09.412_bib00018 – volume: 31 start-page: 0312004 issue: 3 year: 2011 ident: 10.1016/j.ifacol.2018.09.412_bib00021 article-title: Vision inspection of metal surface defects based on infrared imaging publication-title: Acta Optica Sinica doi: 10.3788/AOS201131.0312004 – ident: 10.1016/j.ifacol.2018.09.412_bib0006 – ident: 10.1016/j.ifacol.2018.09.412_bib00015 doi: 10.1109/CVPR.2016.91 – ident: 10.1016/j.ifacol.2018.09.412_bib0003 – volume: 35 start-page: 1195 issue: 9 year: 2013 ident: 10.1016/j.ifacol.2018.09.412_bib00020 article-title: Recognition of surface defects in continuous casting slabs based on contourlet transform publication-title: Journal of University of Science Technology Beijing – volume: 38 start-page: 2797 issue: 11 year: 2017 ident: 10.1016/j.ifacol.2018.09.412_bib0004 article-title: Novel defect recognition method based on adaptive global threshold for highlight mental surface publication-title: Chinese Journal of Scientific Instrument – ident: 10.1016/j.ifacol.2018.09.412_bib0002 doi: 10.1109/CCDC.2017.7979072 – start-page: 91 year: 2015 ident: 10.1016/j.ifacol.2018.09.412_bib00017 article-title: Faster r-cnn: Towards real-time object detection with region proposal networks publication-title: Advances in neural information processing systems |
| SSID | ssj0002964798 |
| Score | 2.2755897 |
| Snippet | The surface defects of steel strip have diverse and complex features, and surface defects caused by different production lines tend to have different... |
| SourceID | crossref elsevier |
| SourceType | Enrichment Source Index Database Publisher |
| StartPage | 76 |
| SubjectTerms | Convolutional Neural Network Defect Detection Improved YOLO Network Steel Strip Surface quality |
| Title | Real-time Detection of Steel Strip Surface Defects Based on Improved YOLO Detection Network |
| URI | https://dx.doi.org/10.1016/j.ifacol.2018.09.412 |
| Volume | 51 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1Nb9QwELWgXLggqoIoH5UPXF0lsR0nx1JRlbLqAttKrThEjmPTVFW6qrIS8OuZsZ00iFWBXqJsFG-imZfxePxmhpC3RqS2aGTOuBGCCScKVqeNZEkOy2eY4ZQ1niB7nB-eiqMzeXbLn_fZJX29a36uzSu5j1bhGugVs2T_Q7Pjn8IFOAf9whE0DMd_0vEX8PIYdocHs9FbMzh_i95av9_cLsEw3Dht8IbA23gHs1aDOwQhmgDn5_PZfDL-OPDCp07rh4O9ffZJL8FTnHezyUb8zFMBjgBh336sRpQtVn7H48J2zsZ5EQk-NnJ_W32xakdjE0oYnLffYwXwGICI1tLHw4acmFsCEpgtcBEkK8potqKNjUVlA5ZCSnS0mCqfzr3pWqseAgyXu63DUt7IxyuwOK2IBOzf62Uv8AXw-WissMLUQ_IogzUEtrf4-LkYA3C436x8r-TxjYfUSs__-_Nh612XiTty8pQ8iesIuhdAsUke2G6LfB0BQUeF0mtHPSCoBwSNgKARENQDgsJ9AyAoAmIyPgLiGTk9eH-yf8hi9wwG31_RM6dKI41pQBaZNNKqOslNoguL5ZZK5RznTSIzzbngupSN0kaWmguXmDqT3PDnZKO77uwLQnWqjLG5qoWSolaZTvMS-7UkJk1U2fBtwgfBVCaWlscOJ1fVwCG8rII4KxRnlZQViHObsHHUMpRW-cv9apB5Fd3D4PZVgJM7R76898hX5DH-CjG312Sjv1nZN-CF9vWOR9MvqrGGwg |
| linkProvider | Colorado Alliance of Research Libraries |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Real-time+Detection+of+Steel+Strip+Surface+Defects+Based+on+Improved+YOLO+Detection+Network&rft.jtitle=IFAC-PapersOnLine&rft.au=Li%2C+Jiangyun&rft.au=Su%2C+Zhenfeng&rft.au=Geng%2C+Jiahui&rft.au=Yin%2C+Yixin&rft.date=2018&rft.pub=Elsevier+Ltd&rft.issn=2405-8963&rft.volume=51&rft.issue=21&rft.spage=76&rft.epage=81&rft_id=info:doi/10.1016%2Fj.ifacol.2018.09.412&rft.externalDocID=S2405896318321001 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2405-8963&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2405-8963&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2405-8963&client=summon |