{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T01:00:11Z","timestamp":1792717211677,"version":"4.5.0"},"reference-count":47,"publisher":"Springer Science and Business Media LLC","issue":"11","license":[{"start":{"date-parts":[[2024,1,17]],"date-time":"2024-01-17T00:00:00Z","timestamp":1705449600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,17]],"date-time":"2024-01-17T00:00:00Z","timestamp":1705449600000},"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":["Vis Comput"],"published-print":{"date-parts":[[2024,11]]},"DOI":"10.1007\/s00371-023-03225-x","type":"journal-article","created":{"date-parts":[[2024,1,17]],"date-time":"2024-01-17T13:02:00Z","timestamp":1705496520000},"page":"8099-8112","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Defect detection in automotive glass based on modified YOLOv5 with multi-scale feature fusion and dual lightweight strategy"],"prefix":"10.1007","volume":"40","author":[{"given":"Zhe","family":"Chen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-6965-4352","authenticated-orcid":false,"given":"Shihao","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hui","family":"Lv","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhixue","family":"Luo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinhao","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,1,17]]},"reference":[{"key":"3225_CR1","doi-asserted-by":"publisher","first-page":"3491","DOI":"10.3934\/mbe.2021175","volume":"18","author":"Z Huang","year":"2021","unstructured":"Huang, Z., Li, Y., Zhao, T., Ying, P., Fan, Y., Li, J.: Infusion port level detection for intravenous infusion based on yolo v3 neural network. Math. Biosci. Eng. 18, 3491\u20133501 (2021). https:\/\/doi.org\/10.3934\/mbe.2021175","journal-title":"Math. Biosci. Eng."},{"key":"3225_CR2","doi-asserted-by":"publisher","DOI":"10.5120\/11650-7152","author":"T Singh","year":"2013","unstructured":"Singh, T., Dua, R.L., Agrawal, S., Acharya, A.: Detection of defects in glass sheet using cs c based segmentation method. Int. J. Comput. Appl. (2013). https:\/\/doi.org\/10.5120\/11650-7152","journal-title":"Int. J. Comput. Appl."},{"key":"3225_CR3","doi-asserted-by":"publisher","unstructured":"Ojala, T., Pietik\u00e4inen, M., M\u00e4enp\u00e4\u00e4, T.: Gray scale and rotation invariant texture classification with local binary patterns. In: Computer Vision-ECCV 2000: 6th European Conference on Computer Vision Dublin, Ireland, June 26\u2013July 1, 2000 Proceedings, Part I 6, pp. 404\u2013420 (2000). https:\/\/doi.org\/10.1007\/3-540-45054-8_27 . Springer","DOI":"10.1007\/3-540-45054-8_27"},{"key":"3225_CR4","doi-asserted-by":"publisher","unstructured":"Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR\u201905), vol. 1, pp. 886\u2013893 (2005). https:\/\/doi.org\/10.1109\/CVPR.2005.177 . Ieee","DOI":"10.1109\/CVPR.2005.177"},{"key":"3225_CR5","doi-asserted-by":"publisher","DOI":"10.1007\/s00371-023-02980-1","author":"X Zhang","year":"2023","unstructured":"Zhang, X., Zhang, J., Chen, J., Guo, R., Wu, J.: A dual-structure attention-based multi-level feature fusion network for automatic surface defect detection. Vis. Comput. (2023). https:\/\/doi.org\/10.1007\/s00371-023-02980-1","journal-title":"Vis. Comput."},{"key":"3225_CR6","doi-asserted-by":"publisher","unstructured":"Wang, W., Liang, J., Liu, D.: Learning equivariant segmentation with instance-unique querying. ArXiv (2022) https:\/\/doi.org\/10.22215\/etd\/2020-14214","DOI":"10.22215\/etd\/2020-14214"},{"key":"3225_CR7","doi-asserted-by":"publisher","unstructured":"Cui, Y., Yan, L., Cao, Z., Liu, D.: Tf-blender: Temporal feature blender for video object detection. 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), 8118\u20138127 (2021) https:\/\/doi.org\/10.1109\/iccv48922.2021.00803","DOI":"10.1109\/iccv48922.2021.00803"},{"key":"3225_CR8","doi-asserted-by":"publisher","unstructured":"Liu, D., Cui, Y., Tan, W., Chen, Y.: Sg-net: Spatial granularity network for one-stage video instance segmentation. 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 9811\u20139820 (2021) https:\/\/doi.org\/10.1109\/cvpr46437.2021.00969","DOI":"10.1109\/cvpr46437.2021.00969"},{"key":"3225_CR9","doi-asserted-by":"publisher","first-page":"1051","DOI":"10.1007\/s00371-021-02067-9","volume":"38","author":"G Chen","year":"2021","unstructured":"Chen, G., Qin, H.: Class-discriminative focal loss for extreme imbalanced multiclass object detection towards autonomous driving. Vis. Comput. 38, 1051\u20131063 (2021). https:\/\/doi.org\/10.1007\/s00371-021-02067-9","journal-title":"Vis. Comput."},{"key":"3225_CR10","doi-asserted-by":"publisher","unstructured":"Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: 2014 IEEE Conference on Computer Vision and Pattern Recognition, pp. 580\u2013587 (2014). https:\/\/doi.org\/10.1109\/CVPR.2014.81","DOI":"10.1109\/CVPR.2014.81"},{"key":"3225_CR11","doi-asserted-by":"publisher","unstructured":"Girshick, R.: Fast r-cnn. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1440\u20131448 (2015). https:\/\/doi.org\/10.1109\/ICCV.2015.169","DOI":"10.1109\/ICCV.2015.169"},{"key":"3225_CR12","doi-asserted-by":"publisher","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster r-cnn: Towards real-time object detection with region proposal networks. Adv. Neural Inf. Process. Syst. (2015) https:\/\/doi.org\/10.48550\/arXiv.1506.01497","DOI":"10.48550\/arXiv.1506.01497"},{"key":"3225_CR13","doi-asserted-by":"publisher","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\u2013788 (2016). https:\/\/doi.org\/10.48550\/arXiv.1506.02640","DOI":"10.48550\/arXiv.1506.02640"},{"key":"3225_CR14","doi-asserted-by":"publisher","unstructured":"Redmon, J., Farhadi, A.: Yolo9000: better, faster, stronger. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7263\u20137271 (2017). https:\/\/doi.org\/10.48550\/arXiv.1612.08242","DOI":"10.48550\/arXiv.1612.08242"},{"key":"3225_CR15","unstructured":"Redmon, J., Farhadi, A.: Yolov3: An incremental improvement. arXiv preprint arXiv:1804.02767 (2018)"},{"key":"3225_CR16","unstructured":"Bochkovskiy, A., Wang, C.-Y., Liao, H.-Y.M.: Yolov4: Optimal speed and accuracy of object detection. arXiv preprint arXiv:2004.10934 (2020)"},{"key":"3225_CR17","doi-asserted-by":"publisher","unstructured":"Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.-Y., Berg, A.C.: Ssd: Single shot multibox detector. In: Computer Vision\u2013ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11\u201314, 2016, Proceedings, Part I 14, pp. 21\u201337 (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_2 . Springer","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"3225_CR18","unstructured":"Li, Z., Zhou, F.: Fssd: feature fusion single shot multibox detector. arXiv preprint arXiv:1712.00960 (2017)"},{"key":"3225_CR19","unstructured":"Fu, C.-Y., Liu, W., Ranga, A., Tyagi, A., Berg, A.C.: Dssd: Deconvolutional single shot detector. arXiv preprint arXiv:1701.06659 (2017)"},{"issue":"5","key":"3225_CR20","doi-asserted-by":"publisher","first-page":"1426","DOI":"10.3390\/en14051426","volume":"14","author":"C Liu","year":"2021","unstructured":"Liu, C., Wu, Y., Liu, J., Han, J.: Mti-yolo: A light-weight and real-time deep neural network for insulator detection in complex aerial images. Energies 14(5), 1426 (2021). https:\/\/doi.org\/10.3390\/en14051426","journal-title":"Energies"},{"issue":"1","key":"3225_CR21","doi-asserted-by":"publisher","first-page":"98","DOI":"10.1186\/s13634-022-00931-x","volume":"2022","author":"F Wan","year":"2022","unstructured":"Wan, F., Sun, C., He, H., Lei, G., Xu, L., Xiao, T.: Yolo-lrdd: A lightweight method for road damage detection based on improved yolov5s. EURASIP J. Adv. Signal Process. 2022(1), 98 (2022). https:\/\/doi.org\/10.1186\/s13634-022-00931-x","journal-title":"EURASIP J. Adv. Signal Process."},{"issue":"1","key":"3225_CR22","doi-asserted-by":"publisher","first-page":"3542","DOI":"10.1038\/s41598-022-07527-3","volume":"12","author":"K Guo","year":"2022","unstructured":"Guo, K., He, C., Yang, M., Wang, S.: A pavement distresses identification method optimized for yolov5s. Sci. Rep. 12(1), 3542 (2022). https:\/\/doi.org\/10.1038\/s41598-022-07527-3","journal-title":"Sci. Rep."},{"issue":"2","key":"3225_CR23","doi-asserted-by":"publisher","first-page":"365","DOI":"10.3390\/agronomy12020365","volume":"12","author":"Z Chen","year":"2022","unstructured":"Chen, Z., Wu, R., Lin, Y., Li, C., Chen, S., Yuan, Z., Chen, S., Zou, X.: Plant disease recognition model based on improved yolov5. Agronomy 12(2), 365 (2022). https:\/\/doi.org\/10.3390\/agronomy12020365","journal-title":"Agronomy"},{"key":"3225_CR24","doi-asserted-by":"publisher","first-page":"140019","DOI":"10.1109\/ACCESS.2020.3010496","volume":"8","author":"Z Kang","year":"2020","unstructured":"Kang, Z., Yang, J., Li, G., Zhang, Z.: An automatic garbage classification system based on deep learning. IEEE Access 8, 140019\u2013140029 (2020). https:\/\/doi.org\/10.1109\/ACCESS.2020.3010496","journal-title":"IEEE Access"},{"key":"3225_CR25","doi-asserted-by":"publisher","unstructured":"Ali, S., Siddique, A., Ate\u015f, H.F., G\u00fcnt\u00fcrk, B.K.: Improved yolov4 for aerial object detection. In: 2021 29th Signal Processing and Communications Applications Conference (SIU), pp. 1\u20134 (2021). https:\/\/doi.org\/10.1109\/SIU53274.2021.9478027","DOI":"10.1109\/SIU53274.2021.9478027"},{"key":"3225_CR26","doi-asserted-by":"publisher","DOI":"10.1117\/12.2620287.6302053085001","author":"D Zhang","year":"2023","unstructured":"Zhang, D., Hao, X., Wang, D.-C., Qin, C., Zhao, B., Liang, L., Liu, W.: An efficient lightweight convolutional neural network for industrial surface defect detection. Artif. Intell. Rev. (2023). https:\/\/doi.org\/10.1117\/12.2620287.6302053085001","journal-title":"Artif. Intell. Rev."},{"key":"3225_CR27","doi-asserted-by":"publisher","unstructured":"Le, H.-A., Pham, M.-T.: Knowledge distillation for object detection: From generic to remote sensing datasets. In: IGARSS 2023 - 2023 IEEE International Geoscience and Remote Sensing Symposium (2023) https:\/\/doi.org\/10.1109\/igarss52108.2023.10282614","DOI":"10.1109\/igarss52108.2023.10282614"},{"key":"3225_CR28","doi-asserted-by":"publisher","unstructured":"Wang, L., Koniusz, P.: Self-supervising action recognition by statistical moment and subspace descriptors. In: Proceedings of the 29th ACM International Conference on Multimedia (2020) https:\/\/doi.org\/10.1145\/3474085.3475572","DOI":"10.1145\/3474085.3475572"},{"key":"3225_CR29","doi-asserted-by":"publisher","unstructured":"Wang, L., Koniusz, P., Huynh, D.Q.: Hallucinating idt descriptors and i3d optical flow features for action recognition with cnns. In: 2019 IEEE\/CVF International Conference on Computer Vision (ICCV), 8697\u20138707 (2019) https:\/\/doi.org\/10.1109\/iccv.2019.00879","DOI":"10.1109\/iccv.2019.00879"},{"key":"3225_CR30","doi-asserted-by":"publisher","unstructured":"Wang, L., Koniusz, P.: 3mformer: Multi-order multi-mode transformer for skeletal action recognition. 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 5620\u20135631 (2023) https:\/\/doi.org\/10.1109\/cvpr52729.2023.00544","DOI":"10.1109\/cvpr52729.2023.00544"},{"key":"3225_CR31","doi-asserted-by":"publisher","unstructured":"Zhu, L., Wang, X., Ke, Z., Zhang, W., Lau, R.W.H.: Biformer: Vision transformer with bi-level routing attention. 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 10323\u201310333 (2023) https:\/\/doi.org\/10.1109\/cvpr52729.2023.00995","DOI":"10.1109\/cvpr52729.2023.00995"},{"key":"3225_CR32","unstructured":"Yang, J., Li, C., Zhang, P., Dai, X., Xiao, B., Yuan, L., Gao, J.: Focal self-attention for local-global interactions in vision transformers. arXiv:abs\/2107.00641 (2021)"},{"key":"3225_CR33","doi-asserted-by":"publisher","unstructured":"Wang, L., Huynh, D.Q., Mansour, M.R.: Loss switching fusion with similarity search for video classification. 2019 IEEE International Conference on Image Processing (ICIP), 974\u2013978 (2019) https:\/\/doi.org\/10.1109\/icip.2019.8803051","DOI":"10.1109\/icip.2019.8803051"},{"key":"3225_CR34","doi-asserted-by":"publisher","first-page":"3747","DOI":"10.1007\/s00371-021-02211-5","volume":"38","author":"S Bouguezzi","year":"2021","unstructured":"Bouguezzi, S., Fredj, H.B., Faiedh, H., Souani, C.: Improved architecture for traffic sign recognition using a self-regularized activation function: Sigmah. Vis. Comput. 38, 3747\u20133764 (2021). https:\/\/doi.org\/10.1007\/s00371-021-02211-5","journal-title":"Vis. Comput."},{"key":"3225_CR35","doi-asserted-by":"publisher","unstructured":"Liu, D., Cui, Y., Yan, L., Mousas, C., Yang, B., Chen, Y.: Densernet: Weakly supervised visual localization using multi-scale feature aggregation. In: AAAI Conference on Artificial Intelligence (2020). https:\/\/doi.org\/10.1609\/aaai.v35i7.16760","DOI":"10.1609\/aaai.v35i7.16760"},{"key":"3225_CR36","doi-asserted-by":"publisher","unstructured":"Zhao, J., Kong, Q.-J., Zhao, X., Liu, J., Liu, Y.: A method for detection and classification of glass defects in low resolution images. In: 2011 Sixth International Conference on Image and Graphics, pp. 642\u2013647 (2011). https:\/\/doi.org\/10.1109\/ICIG.2011.187 . IEEE","DOI":"10.1109\/ICIG.2011.187"},{"key":"3225_CR37","doi-asserted-by":"publisher","first-page":"348","DOI":"10.1016\/j.asoc.2016.10.030","volume":"52","author":"C Jian","year":"2017","unstructured":"Jian, C., Gao, J., Ao, Y.: Automatic surface defect detection for mobile phone screen glass based on machine vision. Appl. Soft Comput. 52, 348\u2013358 (2017). https:\/\/doi.org\/10.1016\/j.asoc.2016.10.030","journal-title":"Appl. Soft Comput."},{"key":"3225_CR38","doi-asserted-by":"publisher","unstructured":"Yousefian-Jazi, A., Ryu, J.-H., Yoon, S., Liu, J.J.: Decision support in machine vision system for monitoring of tft-lcd glass substrates manufacturing. J. Process Control 24(6), 1015\u20131023 (2014) . Energy Efficient Buildings Special Issue https:\/\/doi.org\/10.1016\/j.jprocont.2013.12.009","DOI":"10.1016\/j.jprocont.2013.12.009"},{"key":"3225_CR39","doi-asserted-by":"publisher","unstructured":"Sar\u0131, F., Ula\u015f, A.B.: Deep learning application in detecting glass defects with color space conversion and adaptive histogram equalization (2022) https:\/\/doi.org\/10.18280\/ts.390238","DOI":"10.18280\/ts.390238"},{"key":"3225_CR40","doi-asserted-by":"publisher","first-page":"801","DOI":"10.1007\/s12541-018-0096-x","volume":"19","author":"Z-C Yuan","year":"2018","unstructured":"Yuan, Z.-C., Zhang, Z.-T., Su, H., Zhang, L., Shen, F., Zhang, F.: Vision-based defect detection for mobile phone cover glass using deep neural networks. Int. J. Precision Eng. Manuf. 19, 801\u2013810 (2018). https:\/\/doi.org\/10.1007\/s12541-018-0096-x","journal-title":"Int. J. Precision Eng. Manuf."},{"key":"3225_CR41","doi-asserted-by":"publisher","unstructured":"Jiang, J., Cao, P., Lu, Z., Lou, W., Yang, Y.: Surface defect detection for mobile phone back glass based on symmetric convolutional neural network deep learning. Appl. Sci. (2020) https:\/\/doi.org\/10.3390\/app10103621","DOI":"10.3390\/app10103621"},{"key":"3225_CR42","doi-asserted-by":"publisher","DOI":"10.3390\/s22249897","author":"X Lang","year":"2022","unstructured":"Lang, X., Ren, Z., Wan, D., Zhang, Y., Shu, S.: Mr-yolo: An improved yolov5 network for detecting magnetic ring surface defects. Sensors (2022). https:\/\/doi.org\/10.3390\/s22249897","journal-title":"Sensors"},{"key":"3225_CR43","doi-asserted-by":"publisher","unstructured":"Howard, A., Sandler, M., Chen, B., Wang, W., Chen, L.-C., Tan, M., Chu, G., Vasudevan, V., Zhu, Y., Pang, R., Adam, H., Le, Q.: Searching for mobilenetv3. In: 2019 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 1314\u20131324 (2019). https:\/\/doi.org\/10.1109\/ICCV.2019.00140","DOI":"10.1109\/ICCV.2019.00140"},{"key":"3225_CR44","doi-asserted-by":"publisher","unstructured":"Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7132\u20137141 (2018). https:\/\/doi.org\/10.1109\/CVPR.2018.00745","DOI":"10.1109\/CVPR.2018.00745"},{"key":"3225_CR45","doi-asserted-by":"publisher","unstructured":"Han, K., Wang, Y., Tian, Q., Guo, J., Xu, C., Xu, C.: Ghostnet: More features from cheap operations. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1577\u20131586 (2020). https:\/\/doi.org\/10.1109\/CVPR42600.2020.00165","DOI":"10.1109\/CVPR42600.2020.00165"},{"key":"3225_CR46","doi-asserted-by":"publisher","unstructured":"Woo, S., Park, J., Lee, J.-Y., Kweon, I.S.: Cbam: Convolutional block attention module. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 3\u201319 (2018). https:\/\/doi.org\/10.1007\/978-3-030-01234-2_1","DOI":"10.1007\/978-3-030-01234-2_1"},{"issue":"1","key":"3225_CR47","doi-asserted-by":"publisher","first-page":"273","DOI":"10.1049\/ipr2.12364","volume":"16","author":"C Xie","year":"2022","unstructured":"Xie, C., Zhu, H., Fei, Y.: Deep coordinate attention network for single image super-resolution. IET Image Process. 16(1), 273\u2013284 (2022). https:\/\/doi.org\/10.1049\/ipr2.12364","journal-title":"IET Image Process."}],"container-title":["The Visual Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-023-03225-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00371-023-03225-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-023-03225-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,6]],"date-time":"2024-11-06T16:12:59Z","timestamp":1730909579000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00371-023-03225-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,1,17]]},"references-count":47,"journal-issue":{"issue":"11","published-print":{"date-parts":[[2024,11]]}},"alternative-id":["3225"],"URL":"https:\/\/doi.org\/10.1007\/s00371-023-03225-x","relation":{},"ISSN":["0178-2789","1432-2315"],"issn-type":[{"value":"0178-2789","type":"print"},{"value":"1432-2315","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,1,17]]},"assertion":[{"value":"8 December 2023","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 January 2024","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"All authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}