{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T01:42:05Z","timestamp":1783993325591,"version":"3.55.0"},"reference-count":54,"publisher":"MDPI AG","issue":"14","license":[{"start":{"date-parts":[[2024,7,21]],"date-time":"2024-07-21T00:00:00Z","timestamp":1721520000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Newly Introduced Talents Scientific Research Start-Up Project of Guangzhou Railway Polytechnic","award":["GTXYR2313"],"award-info":[{"award-number":["GTXYR2313"]}]},{"name":"Newly Introduced Talents Scientific Research Start-Up Project of Guangzhou Railway Polytechnic","award":["2023ZDZX1077"],"award-info":[{"award-number":["2023ZDZX1077"]}]},{"name":"Special Projects in Key Field of Guangdong Province General University (New Generation Information Technology)","award":["GTXYR2313"],"award-info":[{"award-number":["GTXYR2313"]}]},{"name":"Special Projects in Key Field of Guangdong Province General University (New Generation Information Technology)","award":["2023ZDZX1077"],"award-info":[{"award-number":["2023ZDZX1077"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Printed circuit board (PCB) surface defect detection is an essential part of the PCB manufacturing process. Currently, advanced CCD or CMOS sensors can capture high-resolution PCB images. However, the existing computer vision approaches for PCB surface defect detection require high computing effort, leading to insufficient efficiency. To this end, this article proposes a local and global context-enhanced lightweight CenterNet (LGCL-CenterNet) to detect PCB surface defects in real time. Specifically, we propose a two-branch lightweight vision transformer module with local and global attention, named LGT, as a complement to extract high-dimension features and leverage context-aware local enhancement after the backbone network. In the local branch, we utilize coordinate attention to aggregate more powerful features of PCB defects with different shapes. In the global branch, Bi-Level Routing Attention with pooling is used to capture long-distance pixel interactions with limited computational cost. Furthermore, a Path Aggregation Network (PANet) feature fusion structure is incorporated to mitigate the loss of shallow features caused by the increase in model depth. Then, we design a lightweight prediction head by using depthwise separable convolutions, which further compresses the computational complexity and parameters while maintaining the detection capability of the model. In the experiment, the LGCL-CenterNet increased the mAP@0.5 by 2% and 1.4%, respectively, in comparison to CenterNet-ResNet18 and YOLOv8s. Meanwhile, our approach requires fewer model parameters (0.542M) than existing techniques. The results show that the proposed method improves both detection accuracy and inference speed and indicate that the LGCL-CenterNet has better real-time performance and robustness.<\/jats:p>","DOI":"10.3390\/s24144729","type":"journal-article","created":{"date-parts":[[2024,7,22]],"date-time":"2024-07-22T14:45:53Z","timestamp":1721659553000},"page":"4729","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":23,"title":["Local and Global Context-Enhanced Lightweight CenterNet for PCB Surface Defect Detection"],"prefix":"10.3390","volume":"24","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9134-6634","authenticated-orcid":false,"given":"Weixun","family":"Chen","sequence":"first","affiliation":[{"name":"The Information Engineering Institute, Guangzhou Railway Polytechnic, Guangzhou 510430, China"},{"name":"Key Laboratory of Equipment Safety and Intelligent Technology of Guangzhou Rail Transit System, Guangzhou 510430, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Siming","family":"Meng","sequence":"additional","affiliation":[{"name":"The Information Engineering Institute, Guangzhou Railway Polytechnic, Guangzhou 510430, China"},{"name":"Key Laboratory of Equipment Safety and Intelligent Technology of Guangzhou Rail Transit System, Guangzhou 510430, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xueping","family":"Wang","sequence":"additional","affiliation":[{"name":"The Science and Engineering College of Information, Hunan Normal University, Changsha 410081, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2024,7,21]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"12559","DOI":"10.1038\/s41598-022-16302-3","article-title":"End-to-end deep learning framework for printed circuit board manufacturing defect classifi-cation","volume":"12","author":"Bhattacharya","year":"2022","journal-title":"Sci. Rep."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Pham, T.T.A., Thoi, D.K.T., Choi, H., and Park, S. (2023). Defect detection in printed circuit boards using semi-supervised learning. Sensors, 23.","DOI":"10.3390\/s23063246"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"112","DOI":"10.1016\/j.neucom.2019.09.107","article-title":"A learning-based approach for surface defect detection using small image datasets","volume":"408","author":"Le","year":"2020","journal-title":"Neurocomputing"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"9805","DOI":"10.1038\/s41598-023-36854-2","article-title":"Global contextual attention augmented YOLO with ConvMixer prediction heads for PCB surface defect detection","volume":"13","author":"Xia","year":"2023","journal-title":"Sci. Rep."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Kim, J., Ko, J., Choi, H., and Kim, H. (2021). Printed circuit board defect detection using deep learning via a skip-connected convolutional autoencoder. Sensors, 21.","DOI":"10.3390\/s21154968"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Wan, Y., Gao, L., Li, X., and Gao, Y. (2022). Semi-supervised defect detection method with data-expanding strategy for pcb quality inspection. Sensors, 22.","DOI":"10.3390\/s22207971"},{"key":"ref_7","first-page":"1415","article-title":"Improved bare PCB defect detection approach based on deep feature learning","volume":"2018","author":"Zhang","year":"2018","journal-title":"J. Eng."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"277","DOI":"10.1007\/s10044-017-0640-9","article-title":"An efficient similarity measure approach for PCB surface defect detection","volume":"21","author":"Gaidhane","year":"2017","journal-title":"Pattern Anal. Appl."},{"key":"ref_9","first-page":"3197","article-title":"A robust approach for surface defect detection based on one dimensional local binary patterns","volume":"5","author":"Tajeripour","year":"2012","journal-title":"Indian J. Sci. Technol."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Ran, G., Lei, X., Li, D., and Guo, Z. (2020, January 25\u201327). Research on PCB defect detection using deep convolutional nerual network. Proceedings of the 2020 5th International Conference on Mechanical, Control and Computer Engineering (ICMCCE), Harbin, China.","DOI":"10.1109\/ICMCCE51767.2020.00287"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"1565","DOI":"10.1038\/nbt1206-1565","article-title":"What is a support vector machine","volume":"24","author":"Noble","year":"2006","journal-title":"Nat. Biotechnol."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"261","DOI":"10.1007\/s10462-011-9272-4","article-title":"Decision trees: A recent overview","volume":"39","author":"Kotsiantis","year":"2011","journal-title":"Artif. Intell. Rev."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"De Oliveira, M., Monteiro, A., and Vieira Filho, J. (2018). A new structural health monitoring strategy based on PZT sensors and convolu-tional neural network. Sensors, 18.","DOI":"10.20944\/preprints201808.0130.v1"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"5012311","DOI":"10.1109\/TIM.2021.3092510","article-title":"FPCB surface defect detection: A decoupled two-stage object detection framework","volume":"70","author":"Luo","year":"2021","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Qiao, S., Chen, L.-C., and Yuille, A. (2021, January 20\u201325). DetectoRS: Detecting objects with recursive feature pyramid and switchable Atrous convolution. Proceedings of the 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, TN, USA.","DOI":"10.1109\/CVPR46437.2021.01008"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"34","DOI":"10.1016\/j.neucom.2020.09.046","article-title":"Automatic zipper tape defect detection using two-stage multi-scale convolutional networks","volume":"422","author":"Fang","year":"2021","journal-title":"Neurocomputing"},{"key":"ref_17","first-page":"5024712","article-title":"Global Context-Based Self-Similarity Feature Augmentation and Bidirectional Feature Fusion for Surface Defect Detection","volume":"72","author":"Wang","year":"2023","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"5017712","DOI":"10.1109\/TIM.2021.3117357","article-title":"Real-time defect detection of track components: Considering class imbalance and subtle difference between classes","volume":"70","author":"Tu","year":"2021","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Duan, K., Bai, S., Xie, L., Qi, H., Huang, Q., and Tian, Q. (2019, January 27\u201328). CenterNet: Keypoint triplets for object detection. Proceedings of the 2019 IEEE\/CVF International Conference on Computer Vision (ICCV), Seoul, Republic of Korea.","DOI":"10.1109\/ICCV.2019.00667"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"115673","DOI":"10.1016\/j.eswa.2021.115673","article-title":"CS-ResNet: Cost-sensitive residual convolutional neural network for PCB cosmetic defect detection","volume":"185","author":"Zhang","year":"2021","journal-title":"Expert Syst. Appl."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Kang, L., Ge, Y., Huang, H., and Zhao, M. (2022, January 12\u201314). Research on PCB defect detection based on SSD. Proceedings of the 2022 IEEE 4th International Conference on Civil Aviation Safety and Information Technology (ICCASIT), Dali, China.","DOI":"10.1109\/ICCASIT55263.2022.9986754"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"105007","DOI":"10.1088\/1361-6501\/ac793d","article-title":"ESDDNet: Efficient small defect detection network of workpiece surface","volume":"33","author":"Chen","year":"2022","journal-title":"Meas. Sci. Technol."},{"key":"ref_23","first-page":"3505008","article-title":"Collaborative Learning Classification Model for PCBs Defect Detection against Image and Label Uncertainty","volume":"72","author":"Yu","year":"2023","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Haase, D., and Amthor, M. (2020, January 13\u201319). Rethinking depthwise separable convolutions: How intra-kernel correlations lead to improved mobilenets. Proceedings of the 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.01461"},{"key":"ref_25","first-page":"127061","article-title":"Scarcity-GAN: Scarce data augmentation for defect detection via generative adversarial nets","volume":"566","author":"Xu","year":"2024","journal-title":"Neuro-Computing"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"163","DOI":"10.1109\/TCPMT.2018.2873744","article-title":"Defect detection in electronic surfaces using template-based fourier image reconstruction","volume":"9","author":"Tsai","year":"2018","journal-title":"IEEE Trans. Compon. Packag. Manuf. Technol."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"34437","DOI":"10.1007\/s11042-019-08097-9","article-title":"A real-time approach for automatic defect detection from PCBs based on SURF features and morphological operations","volume":"78","author":"Hassanin","year":"2019","journal-title":"Multimed. Tools Appl."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Kaur, B., Kaur, G., and Kaur, A. (2014, January 6\u20138). Detection and classification of Printed circuit board defects using image subtraction method. Proceedings of the 2014 Recent Advances in Engineering and Computational Sciences (RAECS), Chandigarh, India.","DOI":"10.1109\/RAECS.2014.6799537"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"406","DOI":"10.1016\/j.neucom.2013.07.038","article-title":"A sparse representation based fast detection method for surface defect detection of bottle caps","volume":"123","author":"Zhou","year":"2014","journal-title":"Neurocomputing"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"420","DOI":"10.1007\/s001700200172","article-title":"Defect detection of gold-plated surfaces on PCBs using entropy measures","volume":"20","author":"Tsai","year":"2002","journal-title":"Int. J. Adv. Manuf. Technol."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Xie, L., Huang, R., and Cao, Z. (2013). Detection and classification of defect patterns in optical inspection using support vector machines. Intelligent Computing Theories, Springer.","DOI":"10.1007\/978-3-642-39479-9_45"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"690","DOI":"10.1109\/TIM.2017.2783098","article-title":"An optical surface inspection and automatic classification technique using the rotated wavelet transform","volume":"67","author":"Borwankar","year":"2018","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_33","first-page":"1741","article-title":"Defect detection of PCB based on Bayes feature fusion","volume":"2018","author":"Lu","year":"2018","journal-title":"J. Eng."},{"key":"ref_34","first-page":"81","article-title":"A framework for inspection of dies attachment on PCB utilizing machine learning techniques","volume":"5","author":"Vafeiadis","year":"2018","journal-title":"J. Manag. Anal."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"351","DOI":"10.1007\/s10845-016-1254-6","article-title":"Online inspection system based on machine learning techniques: Real case study of fabric textures classification for the automotive industry","volume":"30","author":"Malaca","year":"2016","journal-title":"J. Intell. Manuf."},{"key":"ref_36","first-page":"1616","article-title":"A novel deep convolutional neural network algorithm for surface defect detection","volume":"9","author":"Zhang","year":"2022","journal-title":"J. Comput. Des. Eng."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"106412","DOI":"10.1016\/j.engappai.2023.106412","article-title":"An EA-based pruning on improved YOLOv3 for rapid copper elbow surface defect detection","volume":"123","author":"Xian","year":"2023","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"108335","DOI":"10.1109\/ACCESS.2020.3001349","article-title":"Detection of PCB surface defects with improved faster-RCNN and feature pyramid network","volume":"8","author":"Hu","year":"2020","journal-title":"IEEE Access"},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"3507014","DOI":"10.1109\/TIM.2022.3153997","article-title":"A Small-Sized Object Detection Oriented Multi-Scale Feature Fusion Approach with Application to Defect Detection","volume":"71","author":"Zeng","year":"2022","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Xu, X., Zhao, M., Shi, P., Ren, R., He, X., Wei, X., and Yang, H. (2022). Crack Detection and Comparison Study Based on Faster R-CNN and Mask R-CNN. Sensors, 22.","DOI":"10.3390\/s22031215"},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Tang, J., Zhao, Y., Bai, D., and Liu, Q. (2023, January 24\u201326). Rev-RetinaNet: PCB defect detection algorithm based on improved RetinaNet. Proceedings of the 2023 IEEE 2nd International Conference on Electrical Engineering, Big Data and Algorithms (EEBDA), Changchun, China.","DOI":"10.1109\/EEBDA56825.2023.10090524"},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Li, C., Yu, C., and Lin, H. (2023, January 26\u201328). DesNet: PCB defect detection network based on deformable convolution. Proceedings of the 2023 IEEE 3rd International Conference on Electronic Technology, Communication and Information (ICETCI), Changchun, China.","DOI":"10.1109\/ICETCI57876.2023.10176845"},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., and Farhadi, A. (2016, January 27\u201330). You Only Look Once: Unified, Real-Time Object Detection. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"10651","DOI":"10.1007\/s10462-023-10438-y","article-title":"An efficient lightweight convolutional neural network for industrial surface defect detection","volume":"56","author":"Zhang","year":"2023","journal-title":"Artif. Intell. Rev."},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"101824","DOI":"10.1016\/j.aei.2022.101824","article-title":"Sim-YOLOv5s: A method for detecting defects on the end face of lithium battery steel shells","volume":"55","author":"Hu","year":"2023","journal-title":"Adv. Eng. Inform."},{"key":"ref_46","doi-asserted-by":"crossref","unstructured":"Yan, R., Zhang, R., Bai, J., Hao, H., Guo, W., Gu, X., and Liu, Q. (2023). STMS-YOLOv5: A Lightweight Algorithm for Gear Surface Defect Detection. Sensors, 23.","DOI":"10.3390\/s23135992"},{"key":"ref_47","doi-asserted-by":"crossref","unstructured":"Zhu, L., Wang, X., Ke, Z., Zhang, W., and Lau, R. (2023, January 17\u201324). BiFormer: Vision Transformer with Bi-Level Routing Attention. Proceedings of the 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Vancouver, BC, Canada.","DOI":"10.1109\/CVPR52729.2023.00995"},{"key":"ref_48","doi-asserted-by":"crossref","unstructured":"Hou, Q., Zhou, D., and Feng, J. (2021, January 20\u201325). Coordinate Attention for Efficient Mobile Network Design. Proceedings of the 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, TN, USA.","DOI":"10.1109\/CVPR46437.2021.01350"},{"key":"ref_49","first-page":"303","article-title":"HRIPCB: A challenging dataset for PCB defects detection and classification","volume":"2020","author":"Huang","year":"2020","journal-title":"J. Eng."},{"key":"ref_50","doi-asserted-by":"crossref","unstructured":"Wang, K., Liew, J.H., Zou, Y., Zhou, D., and Feng, J. (November, January 27). PANet: Few-Shot Image Semantic Segmentation with Prototype Alignment. Proceedings of the 2019 IEEE\/CVF International Conference on Computer Vision (ICCV), Seoul, Republic of Korea.","DOI":"10.1109\/ICCV.2019.00929"},{"key":"ref_51","doi-asserted-by":"crossref","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":"ref_52","doi-asserted-by":"crossref","unstructured":"Yang, R., Ma, H., Wu, J., Tang, Y., Xiao, X., Zheng, M., and Li, X. (2022, January 23\u201327). ScalableViT: Rethinking the context-oriented generalization of vision transformer. Proceedings of the 17th European Conference on Computer Vision, Tel Aviv, Isarel.","DOI":"10.1007\/978-3-031-20053-3_28"},{"key":"ref_53","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, \u0141., and Polosukhin, I. (2017, January 4\u20139). Attention is all you need. Proceedings of the Advances in Neural Information Processing Systems 30 (NIPS 2017), Long Beach, CA, USA."},{"key":"ref_54","doi-asserted-by":"crossref","unstructured":"He, K., Chen, X., Xie, S., Li, Y., Dollar, P., and Girshick, R. (2022, January 18\u201324). Masked Autoencoders Are Scalable Vision Learners. Proceedings of the 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA.","DOI":"10.1109\/CVPR52688.2022.01553"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/24\/14\/4729\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T15:20:37Z","timestamp":1760109637000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/24\/14\/4729"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,21]]},"references-count":54,"journal-issue":{"issue":"14","published-online":{"date-parts":[[2024,7]]}},"alternative-id":["s24144729"],"URL":"https:\/\/doi.org\/10.3390\/s24144729","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,7,21]]}}}