{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T14:14:26Z","timestamp":1779372866904,"version":"3.53.1"},"reference-count":46,"publisher":"MDPI AG","issue":"12","license":[{"start":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T00:00:00Z","timestamp":1765324800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61865012"],"award-info":[{"award-number":["61865012"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Natural Science Foundation Jiangxi Province","award":["20213AAG01012"],"award-info":[{"award-number":["20213AAG01012"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Computers"],"abstract":"<jats:p>The surface defect detection of printed circuit boards (PCBs) plays a crucial role in the field of industrial manufacturing. However, the existing PCB defect detection methods have great challenges in detecting the accuracy of tiny defects under the complex background due to its compact layout. To address this problem, we propose a novel YOLO-AMBA-EASPP-BiFPN (YOLO-AEB) network based on the YOLOv10 framework that achieves high precision and real-time detection of tiny defects through multi-level architecture optimization. In the backbone network, an adaptive multi-branch attention mechanism (AMBA) is first proposed, which employs an adaptive reweighting algorithm (ARA) to dynamically optimize fusion weights within the multi-branch attention mechanism (MBA), thereby optimizing the ability to represent tiny defects under complex background noise. Then, an efficient atrous spatial pyramid pooling (EASPP) is constructed, which fuses AMBA and atrous spatial pyramid pooling-fast (ASPF). This integration effectively mitigates feature degradation while preserving expansive receptive fields, and the extraction of defect detail features is strengthened. In the neck network, the bidirectional feature pyramid network (BiFPN) is used to replace the conventional path aggregation network (PAN), and the bidirectional cross-scale feature fusion mechanism is used to improve the transfer ability of shallow detail features to deep networks. Comprehensive experimental evaluations demonstrate that our proposed network achieves state-of-the-art performance, whose F1 score can reach 95.7% and mean average precision (mAP) can reach 97%, representing respective improvements of 7.1% and 5.8% over the baseline YOLOv10 model. Feature visualization analysis further verifies the effectiveness and feasibility of YOLO-AEB.<\/jats:p>","DOI":"10.3390\/computers14120543","type":"journal-article","created":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T15:32:17Z","timestamp":1765380737000},"page":"543","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["YOLO-AEB: PCB Surface Defect Detection Based on Adaptive Multi-Branch Attention and Efficient Atrous Spatial Pyramid Pooling"],"prefix":"10.3390","volume":"14","author":[{"given":"Chengzhi","family":"Deng","sequence":"first","affiliation":[{"name":"School of Information Engineering, Jiangxi University of Water Resources and Electric Power, Nanchang 330099, China"},{"name":"Jiangxi Province Key Laboratory of Water Information Cooperative Sensing, and Intelligent Processing, School of Information Engineering, Nanchang 330099, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-5509-2238","authenticated-orcid":false,"given":"Yingbo","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Information Engineering, Jiangxi University of Water Resources and Electric Power, Nanchang 330099, China"},{"name":"Jiangxi Province Key Laboratory of Water Information Cooperative Sensing, and Intelligent Processing, School of Information Engineering, Nanchang 330099, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhaoming","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Information Engineering, Jiangxi University of Water Resources and Electric Power, Nanchang 330099, China"},{"name":"Jiangxi Province Key Laboratory of Water Information Cooperative Sensing, and Intelligent Processing, School of Information Engineering, Nanchang 330099, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weiwei","family":"Zhou","sequence":"additional","affiliation":[{"name":"Jiangxi Province Key Laboratory of Water Information Cooperative Sensing, and Intelligent Processing, School of Information Engineering, Nanchang 330099, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"You","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Information Engineering, Jiangxi University of Water Resources and Electric Power, Nanchang 330099, China"},{"name":"Jiangxi Province Key Laboratory of Water Information Cooperative Sensing, and Intelligent Processing, School of Information Engineering, Nanchang 330099, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaowei","family":"Sun","sequence":"additional","affiliation":[{"name":"School of Information Engineering, Jiangxi University of Water Resources and Electric Power, Nanchang 330099, China"},{"name":"Jiangxi Province Key Laboratory of Water Information Cooperative Sensing, and Intelligent Processing, School of Information Engineering, Nanchang 330099, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shengqian","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Information Engineering, Jiangxi University of Water Resources and Electric Power, Nanchang 330099, China"},{"name":"Jiangxi Province Key Laboratory of Water Information Cooperative Sensing, and Intelligent Processing, School of Information Engineering, Nanchang 330099, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2025,12,10]]},"reference":[{"key":"ref_1","first-page":"1","article-title":"An Efficient Tiny Defect Detection Method for PCB With Improved YOLO Through a Compression Training Strategy","volume":"73","author":"Zhou","year":"2024","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_2","unstructured":"Ibrahim, Z., Al-Attas, S.A.R., Aspar, Z., and Mokji, M.M. (2002, January 11\u201314). Performance evaluation of wavelet-based PCB defect detection and localization algorithm. Proceedings of the 2002 IEEE International Conference on Industrial Technology, 2002, IEEE ICIT, Bankok, Thailand."},{"key":"ref_3","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":"2019","journal-title":"IEEE Trans. Compon. Packag. Manuf. Technol."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Wang, Y., Sun, Y., and Zhang, W. (2009, January 14\u201316). Automatic Inspection of Small Component on Loaded PCB Based on Mean-Shift and Support Vector Machine. Proceedings of the 2009 Fifth International Conference on Natural Computation, Tianjian, China.","DOI":"10.1109\/ICNC.2009.407"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Huang, Z., Xiao, H., Zhang, R., Wang, H., Zhang, C., and Shi, X. (2019, January 14\u201317). Multi-Scale Feature Pair Based R-CNN Method for Defect Detection. Proceedings of the 2019 International Conference on Internet of Things (iThings) and IEEE Green Computing and Communications (GreenCom) and IEEE Cyber, Physical and Social Computing (CPSCom) and IEEE Smart Data (SmartData), Atlanta, GA, USA.","DOI":"10.1109\/iThings\/GreenCom\/CPSCom\/SmartData.2019.00031"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Liu, Y. (2018, January 8\u20139). An Improved Faster R-CNN for Object Detection. Proceedings of the 2018 11th International Symposium on Computational Intelligence and Design (ISCID), Hangzhou, China.","DOI":"10.1109\/ISCID.2018.10128"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"29300","DOI":"10.1038\/s41598-024-78566-1","article-title":"Brain CT image classification based on mask RCNN and attention mechanism","volume":"14","author":"Yin","year":"2024","journal-title":"Sci. Rep."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"188577","DOI":"10.1109\/ACCESS.2020.3031990","article-title":"A Lightweight Feature Fusion Single Shot Multibox Detector for Garbage Detection","volume":"8","author":"Ma","year":"2020","journal-title":"IEEE Access"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Hussain, M. (2023). YOLO-v1 to YOLO-v8, the Rise of YOLO and Its Complementary Nature toward Digital Manufacturing and Industrial Defect Detection. Machines, 11.","DOI":"10.3390\/machines11070677"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Fan, F., Wang, B., Zhu, G., and Wu, J. (2021, January 13\u201315). Efficient Faster R-CNN: Used in PCB Solder Joint Defects and Components Detection. Proceedings of the 2021 IEEE 4th International Conference on Computer and Communication Engineering Technology (CCET), Beijing, China.","DOI":"10.1109\/CCET52649.2021.9544356"},{"key":"ref_11","first-page":"101032","article-title":"Automatic visual inspection for printed circuit board via novel Mask R-CNN in smart city applications","volume":"44","author":"Lian","year":"2021","journal-title":"Sustain. Energy Technol. Assess"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Chaudhari, A., Upganlawar, V., Barve, T., Vaidya, R., and Shelke, D. (2024, January 3\u20134). Analysis of YOLO V3 for Multiple Defects Detection in PCB. Proceedings of the 2024 Parul International Conference on Engineering and Technology (PICET), Vadodara, India.","DOI":"10.1109\/PICET60765.2024.10716153"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Ye, M., Wang, H., and Xiao, H. (2023, January 24\u201326). Light-YOLOv5: A Lightweight Algorithm for Improved YOLOv5 in PCB Defect Detection. Proceedings of the 2023 IEEE 2nd International Conference on Electrical Engineering, Big Data and Algorithms (EEBDA), Changchun, China.","DOI":"10.1109\/EEBDA56825.2023.10090731"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Wang, Q., Wu, B., Zhu, P., Li, P., Zuo, W., and Hu, Q. (2020, January 13\u201319). ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks. Proceedings of the 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.01155"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Wang, X., Zhang, X., and Zhou, N. (2021, January 5\u20137). Improved YOLOv5 with BiFPN on PCB Defect Detection. Proceedings of the 2021 2nd International Conference on Artificial Intelligence and Computer Engineering (ICAICE), Hangzhou, China.","DOI":"10.1109\/ICAICE54393.2021.00045"},{"key":"ref_16","unstructured":"Yang, B., and Qu, Z. (2023, January 11\u201313). A PCB Defect Detection Algorithm Based on Improved Yolov7-tiny. Proceedings of the 2023 IEEE 5th International Conference on Civil Aviation Safety and Information Technology (ICCASIT), Dali, China."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Liu, Y., Gao, C., Song, B., and Liang, S. (2023, January 17\u201319). A Surface Defect Detection Algorithm for PCB Based on MobileViT-YOLO. Proceedings of the 2023 China Automation Congress (CAC), Chongqing, China.","DOI":"10.1109\/CAC59555.2023.10450181"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Hua, L. (2024, January 28\u201330). Motor PCB Defect Detection Algorithm Based on Improved YOLOv7-tiny. Proceedings of the 2024 6th International Conference on Electronic Engineering and Informatics (EEI), Chongqing, China.","DOI":"10.1109\/EEI63073.2024.10695971"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Lan, H., Zhu, H., Luo, R., Ren, Q., and Chen, C. (2023, January 27\u201329). PCB Defect Detection Algorithm of Improved YOLOv8. Proceedings of the 2023 8th International Conference on Image, Vision and Computing (ICIVC), Dalian, China.","DOI":"10.1109\/ICIVC58118.2023.10270049"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Hu, Y., Wang, S., Hong, Y., and Li, R. (June, January 31). A YOLOv8s Model Integrating GELAN Module and HAT Attention for PCB Defect Detection. Proceedings of the 2024 5th International Conference on Electronic Communication and Artificial Intelligence (ICECAI), Shenzhen, China.","DOI":"10.1109\/ICECAI62591.2024.10675021"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"143085","DOI":"10.1109\/ACCESS.2025.3595048","article-title":"YOLO-DefXpert: An Advanced Defect Detection on PCB Surfaces Using Improved YOLOv11 Algorithm","volume":"13","author":"Selvam","year":"2025","journal-title":"IEEE Access"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Yin, X., Zhao, Z., and Weng, L. (2025). MAS-YOLO: A Lightweight Detection Algorithm for PCB Defect Detection Based on Improved YOLOv12. Appl. Sci., 15.","DOI":"10.3390\/app15116238"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"5042513","DOI":"10.1109\/TIM.2025.3602542","article-title":"A High-Performance and Enhanced Generalization Small Target Defect Detection Method for PCB Boards Based on YOLO-EMAC","volume":"74","author":"Wu","year":"2025","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_24","unstructured":"Wang, A., Chen, H., Liu, L., Chen, K., Lin, Z., Han, J., and Ding, G. (2024). YOLOv10: Real-Time End-to-End Object Detection. arXiv."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"70","DOI":"10.1109\/TPDS.2021.3084813","article-title":"Optimizing Depthwise Separable Convolution Operations on GPUs","volume":"33","author":"Lu","year":"2022","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"21547","DOI":"10.1109\/ACCESS.2025.3533653","article-title":"BMNet: Enhancing Deepfake Detection Through BiLSTM and Multi-Head Self-Attention Mechanism","volume":"13","author":"Xiong","year":"2025","journal-title":"IEEE Access"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"9011","DOI":"10.1109\/TPAMI.2021.3122970","article-title":"Learn to Predict Sets Using Feed-Forward Neural Networks","volume":"44","author":"Rezatofighi","year":"2022","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"166579","DOI":"10.1109\/ACCESS.2021.3134639","article-title":"Parallelization of Non-Maximum Suppression","volume":"9","author":"Lee","year":"2021","journal-title":"IEEE Access"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Mao, M., Lee, A., and Hong, M. (2024). Efficient Fabric Classification and Object Detection Using YOLOv10. Electronics, 13.","DOI":"10.3390\/electronics13193840"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"55382","DOI":"10.1109\/ACCESS.2025.3552683","article-title":"EAD-YOLOv10: Lightweight Steel Surface Defect Detection Algorithm Research Based on YOLOv10 Improvement","volume":"13","author":"Hu","year":"2025","journal-title":"IEEE Access"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Mayya, A.M., and Alkayem, N.F. (2024). Enhance the Concrete Crack Classification Based on a Novel Multi-Stage YOLOV10-ViT Framework. Sensors, 24.","DOI":"10.3390\/s24248095"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Mei, J., and Zhu, W. (2024). BGF-YOLOv10: Small Object Detection Algorithm from Unmanned Aerial Vehicle Perspective Based on Improved YOLOv10. Sensors, 24.","DOI":"10.3390\/s24216911"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Liao, L., Song, C., Wu, S., and Fu, J. (2025). A Novel YOLOv10-Based Algorithm for Accurate Steel Surface Defect Detection. Sensors, 25.","DOI":"10.3390\/s25030769"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"48","DOI":"10.1016\/j.neucom.2021.03.091","article-title":"A review on the attention mechanism of deep learning","volume":"452","author":"Niu","year":"2021","journal-title":"Neurocomputing"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"122","DOI":"10.1007\/s11554-024-01504-x","article-title":"YOLO-FGD: A fast lightweight PCB defect method based on FasterNet and the Gather-and-Distribute mechanism","volume":"21","author":"Qin","year":"2024","journal-title":"J. Real-Time Image Proc."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"2001611","DOI":"10.1109\/TIM.2024.3351241","article-title":"YOLO-HMC: An Improved Method for PCB Surface Defect Detection","volume":"73","author":"Yuan","year":"2024","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_37","first-page":"2506111","article-title":"Neighborhood Correlation Enhancement Network for PCB Defect Classification","volume":"72","author":"Huang","year":"2023","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"44","DOI":"10.1007\/s11554-024-01616-4","article-title":"Real-time recognition method for PCB chip targets based on YOLO-GSG","volume":"22","author":"Yue","year":"2025","journal-title":"J. Real-Time Image Proc."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"2389","DOI":"10.1038\/s41598-025-85245-2","article-title":"Improved printed circuit board defect detection scheme","volume":"15","author":"Bai","year":"2025","journal-title":"Sci. Rep."},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Li, G., Zhao, S., Zhou, M., Li, M., Shao, R., Zhang, Z., and Han, D. (2022). YOLO-RFF: An Industrial Defect Detection Method Based on Expanded Field of Feeling and Feature Fusion. Electronics, 11.","DOI":"10.3390\/electronics11244211"},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"138825","DOI":"10.1109\/ACCESS.2019.2942077","article-title":"Multi-Scale Receptive Field Detection Network","volume":"7","author":"Cui","year":"2019","journal-title":"IEEE Access"},{"key":"ref_42","first-page":"3386","article-title":"APANet: Auto-Path Aggregation for Future Instance Segmentation Prediction","volume":"44","author":"Hu","year":"2022","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"164","DOI":"10.1007\/s11554-024-01543-4","article-title":"YOLOv8s-CFB: A lightweight method for real-time detection of apple fruits in complex environments","volume":"21","author":"Zhao","year":"2024","journal-title":"J. Real-Time Image Proc."},{"key":"ref_44","doi-asserted-by":"crossref","unstructured":"Christlein, V., Spranger, L., Seuret, M., Nicolaou, A., Kr\u00e1l, P., and Maier, A. (2019, January 20\u201325). Deep Generalized Max Pooling. Proceedings of the 2019 International Conference on Document Analysis and Recognition (ICDAR), Sydney, NSW, Australia.","DOI":"10.1109\/ICDAR.2019.00177"},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"1904","DOI":"10.1109\/TPAMI.2015.2389824","article-title":"Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition","volume":"37","author":"He","year":"2015","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"303","DOI":"10.1049\/joe.2019.1183","article-title":"HRIPCB: A challenging dataset for PCB defects detection and classification","volume":"2020","author":"Huang","year":"2020","journal-title":"J. Eng."}],"container-title":["Computers"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2073-431X\/14\/12\/543\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T15:43:37Z","timestamp":1765381417000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2073-431X\/14\/12\/543"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,10]]},"references-count":46,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["computers14120543"],"URL":"https:\/\/doi.org\/10.3390\/computers14120543","relation":{},"ISSN":["2073-431X"],"issn-type":[{"value":"2073-431X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,10]]}}}