{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,29]],"date-time":"2026-07-29T13:00:35Z","timestamp":1785330035799,"version":"3.55.0"},"reference-count":39,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2024,6,19]],"date-time":"2024-06-19T00:00:00Z","timestamp":1718755200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2024,6,19]],"date-time":"2024-06-19T00:00:00Z","timestamp":1718755200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Intell Syst"],"abstract":"<jats:title>Abstract<\/jats:title><jats:p>The identification of imperfections on steel surfaces is vital for ensuring the quality of industrial products. It requires the capability of real-time detection with high accuracy. This paper proposes the CRGF-YOLO (Contextual Reparameterized Generalized Feature) model based on YOLOv5. In the network, BottleneckCSP structures and depthwise separable convolutions utilizing the structural reparameterization are introduced to reduce the model size and improve performance. In addition, contextual transformer modules are employed as self-attention mechanisms to improve feature representations by capturing long-range dependencies, outperforming conventional convolutional networks. Furthermore, the simplified generalized feature pyramid network is embedded to aggregate multi-scale feature maps and enhance the network\u2019s robustness. Finally, four prediction heads with different sizes are employed to predict defects, which are supported by prior bounding boxes generated using k-means clustering algorithm. The Focal-EIOU (Exponential Intersection over Union) loss function is introduced to improve detection accuracy and expedite model convergence. The improved model achieves a mean average precision (mAP) of 82.2% on the NEU-DET dataset, outperforming the baseline YOLOv5s by 7.7% mAP while maintaining real-time speeds. Comparative evaluations demonstrate CRGF-YOLO\u2019s superior performance over previous state-of-the-art methods like Faster R-CNN (77.4% mAP), YOLOv3 (77.4% mAP), YOLOv7s (72.1% mAP), and YOLOv8s (78.7% mAP) for steel surface defect detection. Overall, this study provides valuable insights and practical guidance for the advancement of defect detection technology.<\/jats:p>","DOI":"10.1007\/s44196-024-00559-9","type":"journal-article","created":{"date-parts":[[2024,6,19]],"date-time":"2024-06-19T10:02:13Z","timestamp":1718791333000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":23,"title":["CRGF-YOLO: An Optimized Multi-Scale Feature Fusion Model Based on YOLOv5 for Detection of Steel Surface Defects"],"prefix":"10.1007","volume":"17","author":[{"given":"Tao","family":"Yu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xu","family":"Luo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qiang","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-9194-3145","authenticated-orcid":false,"given":"Lei","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,6,19]]},"reference":[{"key":"559_CR1","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1049\/ipr2.12647","volume":"17","author":"B Tang","year":"2023","unstructured":"Tang, B., Chen, L., Sun, W., Lin, Z.K.: Review of surface defect detection of steel products based on machine vision. Iet Image Process. 17, 303\u2013322 (2023)","journal-title":"Iet Image Process."},{"key":"559_CR2","doi-asserted-by":"publisher","first-page":"16741","DOI":"10.1007\/s11042-017-5238-0","volume":"77","author":"YL Wang","year":"2018","unstructured":"Wang, Y.L., Xia, H.B., Yuan, X.F., Li, L., Sun, B.: Distributed defect recognition on steel surfaces using an improved random forest algorithm with optimal multi-feature-set fusion. Multimed. Tools Appl. 77, 16741\u201316770 (2018)","journal-title":"Multimed. Tools Appl."},{"key":"559_CR3","doi-asserted-by":"publisher","DOI":"10.3390\/app9204222","author":"Y Liu","year":"2019","unstructured":"Liu, Y., Xu, K., Xu, J.W.: An improved MB-LBP defect recognition approach for the surface of steel plates. Appl. Sci. Basel (2019). https:\/\/doi.org\/10.3390\/app9204222","journal-title":"Appl. Sci. Basel"},{"key":"559_CR4","doi-asserted-by":"publisher","DOI":"10.1117\/1.3284779","author":"C Park","year":"2010","unstructured":"Park, C., Choi, S., Won, S.: Vision-based inspection for periodic defects in steel wire rod production. Opt. Eng. (2010). https:\/\/doi.org\/10.1117\/1.3284779","journal-title":"Opt. Eng."},{"key":"559_CR5","doi-asserted-by":"publisher","first-page":"5122","DOI":"10.1364\/AO.50.005122","volume":"50","author":"DC Choi","year":"2011","unstructured":"Choi, D.C., Jeon, Y.J., Yun, J.P., Kim, S.W.: Pinhole detection in steel slab images using Gabor filter and morphological features. Appl. Optics 50, 5122\u20135129 (2011)","journal-title":"Appl. Optics"},{"key":"559_CR6","doi-asserted-by":"publisher","first-page":"3137","DOI":"10.12733\/jics20105934","volume":"12","author":"J Hou","year":"2015","unstructured":"Hou, J., Xia, K., Fan, Y., Aslam, N.: Surface defects detection of strip steel based on semi-definite programming SVM. J. Inf. Comput. Sci. 12, 3137\u20133145 (2015)","journal-title":"J. Inf. Comput. Sci."},{"key":"559_CR7","doi-asserted-by":"publisher","DOI":"10.1088\/2053-1591\/ac5a38","author":"CX Zhu","year":"2022","unstructured":"Zhu, C.X., Yuan, H.T., Ma, G.H.: An active visual monitoring method for GMAW weld surface defects based on random forest model. Mater. Res. Express (2022). https:\/\/doi.org\/10.1088\/2053-1591\/ac5a38","journal-title":"Mater. Res. Express"},{"key":"559_CR8","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1145\/3065386","volume":"60","author":"A Krizhevsky","year":"2017","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. Commun. Acm 60, 84\u201390 (2017)","journal-title":"Commun. Acm"},{"key":"559_CR9","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","volume":"39","author":"S Ren","year":"2017","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. Ieee Trans. Pattern Anal. Mach. Intell. 39, 1137\u20131149 (2017)","journal-title":"Ieee Trans. Pattern Anal. Mach. Intell."},{"key":"559_CR10","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.C., Meng, Q.G., Yan, Y.H.: An End-to-end steel surface defect detection approach via fusing multiple hierarchical features. Ieee Trans. Instrum. Meas. 69, 1493\u20131504 (2020)","journal-title":"Ieee Trans. Instrum. Meas."},{"key":"559_CR11","doi-asserted-by":"crossref","unstructured":"Xie, Y., Dong, Y., He, H.: Defect detection of printed circuit board based on small target recognition network. In: the 23rd International Conference on electronic packaging technology (ICEPT), pp. 1\u20135. 10\u201313 August 2022","DOI":"10.1109\/ICEPT56209.2022.9873220"},{"key":"559_CR12","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: unified, real-time object detection. In: proceedings of the IEEE Conference on computer vision and pattern recognition, pp. 779-788. Las Vegas, NV, USA, 27\u201330 June 2016","DOI":"10.1109\/CVPR.2016.91"},{"key":"559_CR13","doi-asserted-by":"crossref","unstructured":"Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C., Berg, A.C.: SSD: single shot multibox detector. In: the European Conference on computer vision, Amsterdam, Netherlands, pp. 21\u201337. (2016)","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"559_CR14","doi-asserted-by":"publisher","first-page":"76","DOI":"10.1016\/j.ifacol.2018.09.412","volume":"51","author":"JY Li","year":"2018","unstructured":"Li, J.Y., Su, Z.F., Geng, J.H., Yin, Y.X.: Real-time detection of steel strip surface defects based on improved YOLO detection network. Ifac Papersonline 51, 76\u201381 (2018)","journal-title":"Ifac Papersonline"},{"key":"559_CR15","doi-asserted-by":"publisher","first-page":"182","DOI":"10.14504\/ajr.8.S1.22","volume":"8","author":"HS Xie","year":"2021","unstructured":"Xie, H.S., Zhang, Y.F., Wu, Z.S.: An improved fabric defect detection method based on SSD. Aatcc J. Res. 8, 182\u2013191 (2021)","journal-title":"Aatcc J. Res."},{"key":"559_CR16","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., Uszkoreit, J., Houlsby, N.: An image is worth 16 \u00d7 16 words: transformers for image recognition at scale. In: the 9th International Conference on learning representations, Virtual, Online, 3\u20137 May 2021"},{"key":"559_CR17","doi-asserted-by":"crossref","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. arXiv, arXiv: 2005.12872 (2020)","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"559_CR18","doi-asserted-by":"crossref","unstructured":"Wang, X., Girshick, R., Gupta, A., He, K.: Non-local neural networks. In: the 2018 IEEE\/CVF Conference on computer vision and pattern recognition, pp. 7794\u20137803. 18\u201323 June 2018","DOI":"10.1109\/CVPR.2018.00813"},{"key":"559_CR19","doi-asserted-by":"crossref","unstructured":"Bello, I., Zoph, B., Le, Q., Vaswani, A., Shlens, J.: Attention augmented convolutional networks. In: the 2019 IEEE\/CVF International Conference on computer vision (ICCV), pp. 3285\u20133294. Seoul, Korea (South), 27 October\u20132 November 2019","DOI":"10.1109\/ICCV.2019.00338"},{"key":"559_CR20","doi-asserted-by":"crossref","unstructured":"Srinivas, A., Lin, T., Parmar, N., Shlens, J., Abbeel, P., Vaswani, A.: Bottleneck transformers for visual recognition. In: the 2021 IEEE\/CVF Conference on computer vision and pattern recognition (CVPR), pp. 16514\u201316524. 20\u201325 June 2021","DOI":"10.1109\/CVPR46437.2021.01625"},{"key":"559_CR21","doi-asserted-by":"publisher","first-page":"1489","DOI":"10.1109\/TPAMI.2022.3164083","volume":"45","author":"Y Li","year":"2023","unstructured":"Li, Y., Yao, T., Pan, Y., Mei, T.: Contextual transformer networks for visual recognition. Ieee Trans. Pattern Anal. Mach. Intell. 45, 1489\u20131500 (2023)","journal-title":"Ieee Trans. Pattern Anal. Mach. Intell."},{"key":"559_CR22","doi-asserted-by":"publisher","first-page":"9099","DOI":"10.1109\/TIP.2021.3118953","volume":"30","author":"PY Chen","year":"2021","unstructured":"Chen, P.Y., Chang, M.C., Hsieh, J.W., Chen, Y.S.: Parallel residual bi-fusion feature pyramid network for accurate single-shot object detection. Ieee Trans. Image Process. 30, 9099\u20139111 (2021)","journal-title":"Ieee Trans. Image Process."},{"key":"559_CR23","doi-asserted-by":"crossref","unstructured":"Ghiasi, G., Lin, T., Le, Q.V.: NAS-FPN: learning scalable feature pyramid architecture for object detection. In: the 2019 IEEE\/CVF Conference on computer vision and pattern recognition (CVPR), pp. 7029\u20137038. 15\u201320 June 2019","DOI":"10.1109\/CVPR.2019.00720"},{"key":"559_CR24","doi-asserted-by":"crossref","unstructured":"Yilmaz, M.A., Tekalp, A.M.: DFPN: deformable frame prediction network. In: the 2021 IEEE International Conference on image processing (ICIP), pp. 1944\u20131948. Anchorage, AK, United States, 19\u201322 September 2021","DOI":"10.1109\/ICIP42928.2021.9506210"},{"key":"559_CR25","doi-asserted-by":"crossref","unstructured":"Tan, M., Pang, R., Le, Q.V.: EfficientDet: scalable and efficient object detection. In: the 2020 IEEE\/CVF Conference on computer vision and pattern recognition (CVPR), pp. 10778\u201310787. 13\u201319 June 2020","DOI":"10.1109\/CVPR42600.2020.01079"},{"key":"559_CR26","unstructured":"Jiang, Y., Tan, Z., Wang, J., Sun, X., Lin, M., Li, H.: GiraffeDet: a heavy-neck paradigm for object detection. arXiv, arXiv: 2202.04256 (2022)"},{"key":"559_CR27","doi-asserted-by":"crossref","unstructured":"Ding, X., Zhang, X., Ma, N., Han, J., Ding, G., Sun, J.: RepVgg: making VGG-style ConvNets great again. InUnited states, pp. 13728-13737. (2021)","DOI":"10.1109\/CVPR46437.2021.01352"},{"key":"559_CR28","unstructured":"Howard, A.G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., Andreetto, M., Adam, H.: Mobilenets: efficient convolutional neural networks for mobile vision applications. arXiv, arXiv: 1704.04861 (2017)"},{"key":"559_CR29","doi-asserted-by":"publisher","first-page":"146","DOI":"10.1016\/j.neucom.2022.07.042","volume":"506","author":"YF Zhang","year":"2022","unstructured":"Zhang, Y.F., Ren, W.Q., Zhang, Z., Jia, Z., Wang, L., Tan, T.N.: Focal and efficient IOU loss for accurate bounding box regression. Neurocomputing 506, 146\u2013157 (2022)","journal-title":"Neurocomputing"},{"key":"559_CR30","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.: A noise robust method based on completed local binary patterns for hot-rolled steel strip surface defects. Appl. Surf. Sci. 285, 858\u2013864 (2013)","journal-title":"Appl. Surf. Sci."},{"key":"559_CR31","doi-asserted-by":"publisher","first-page":"336","DOI":"10.1007\/s11263-019-01228-7","volume":"128","author":"RR Selvaraju","year":"2020","unstructured":"Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., Batra, D.: Grad-CAM: visual explanations from deep networks via gradient-based localization. Int. J. Comput. Vis. 128, 336\u2013359 (2020)","journal-title":"Int. J. Comput. Vis."},{"key":"559_CR32","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., Albanie, S., Sun, G., Wu, E.: Squeeze-and-excitation networks. In: the 2018 IEEE\/CVF Conference on computer vision and pattern recognition, pp. 7132\u20137141. 18\u201323 June 2018","DOI":"10.1109\/CVPR.2018.00745"},{"key":"559_CR33","doi-asserted-by":"crossref","unstructured":"Woo, S., Park, J., Lee, J., Kweon, I.S.: CBAM: convolutional block attention module. In: the 15th European Conference on computer vision (ECCV), pp. 3\u201319. Munich, Germany (2018)","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"559_CR34","unstructured":"Yang, L.X., Zhang, R.Y., Li, L.D., Xie, X.H.: SimAM: a simple, parameter-free attention module for convolutional neural networks. In: the International Conference on machine learning (ICML), vol. 139, Electr Network, 18\u201324 July 2021"},{"key":"559_CR35","doi-asserted-by":"crossref","unstructured":"Wang, Q., Wu, B., Zhu, P., Li, P., Zuo, W., Hu, Q.: ECA-net: efficient channel attention for deep convolutional neural networks. In: the 2020 IEEE\/CVF Conference on computer vision and pattern recognition (CVPR), pp. 11531\u201311539. 13\u201319 June 2020","DOI":"10.1109\/CVPR42600.2020.01155"},{"key":"559_CR36","unstructured":"Redmon, J., Pag, A.F.: YOLOv3: An incremental improvement. arXiv, arXiv:1804.02767 (2018)"},{"key":"559_CR37","doi-asserted-by":"crossref","unstructured":"Wang, C., Bochkovskiy, A., Liao, H.M.: YOLOv7: trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. arXiv, arXiv: 2207.02696 (2022)","DOI":"10.1109\/CVPR52729.2023.00721"},{"key":"559_CR38","unstructured":"Ge, Z., Liu, S., Wang, F., Li, Z., Sun, J., YOLOX: exceeding YOLO series in 2021. arXiv, arXiv: 2107.08430 (2021)"},{"key":"559_CR39","unstructured":"Reis, D., Kupec, J., Hong, J., Daoudi, A.: Real-time flying object detection with YOLOv8. arXiv, arXiv:2305.09972 (2023)"}],"container-title":["International Journal of Computational Intelligence Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s44196-024-00559-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s44196-024-00559-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s44196-024-00559-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,19]],"date-time":"2024-06-19T10:04:22Z","timestamp":1718791462000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s44196-024-00559-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,19]]},"references-count":39,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2024,12]]}},"alternative-id":["559"],"URL":"https:\/\/doi.org\/10.1007\/s44196-024-00559-9","relation":{},"ISSN":["1875-6883"],"issn-type":[{"value":"1875-6883","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,6,19]]},"assertion":[{"value":"5 November 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 June 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 June 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of Interest"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Informed Consent"}},{"value":"Not applicable.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Institutional Review Board Statement"}}],"article-number":"154"}}