Multi-Generation YOLO Comparison for Indonesian Banknote Detection Under Challenging Conditions
DOI:
https://doi.org/10.32492/nucleus.v5i2.5220%20Keywords:
YOLO, Object Detection, Rupiah Banknotes, Real-World Evaluation, Computer VisiomAbstract
This study presents a comparative analysis of multiple YOLO model generations, namely YOLOv5, YOLOv8, YOLOv11, and YOLO26, for Indonesian banknote detection under real-world conditions. The evaluation focuses on challenging scenarios, including brightness variation, background clutter, and occlusion. A dataset of 1,400 images is used for training, while 200 real-world images are manually annotated and utilized for evaluation. All models are trained from scratch under identical configurations to ensure fair comparison. Performance is assessed using accuracy, precision, recall, and F1-score, with evaluation based on an Intersection over Union (IoU) threshold of 0.5. In addition, inference time is analyzed to examine computational efficiency. The results show that YOLOv11 achieves the most balanced performance, with the highest recall (0.700) and F1-score (0.775), indicating strong robustness under challenging conditions. YOLO26 attains the highest precision (0.893), demonstrating its ability to reduce false positives, while YOLOv5 provides the fastest inference time (92.463 ms) but with significantly lower detection performance. The findings highlight a clear trade-off between detection accuracy and computational efficiency across different YOLO models. Overall, YOLOv11 is identified as the most suitable model for real-world deployment due to its balanced performance and robustness. This study contributes to object detection research by providing a comprehensive evaluation of multiple YOLO generations under realistic conditions and offers practical insights for model selection in real-time applications.
References
M. Shahin, F. F. Chen, A. Hosseinzadeh, H. Khodadadi Koodiani, H. Bouzary, and A. Shahin, “Enhanced safety implementation in 5S + 1 via object detection algorithms,” International Journal of Advanced Manufacturing Technology, vol. 125, no. 7–8, pp. 3701–3721, 2023, doi: 10.1007/s00170-023-10970-9.
G. Duran, “Manufacturing-Induced Defect Taxonomy and Visual Detection in UD Tapes with Carbon and Glass Fiber Reinforcements,” Polymers (Basel)., vol. 18, no. 7, 2026, doi: 10.3390/polym18070807.
V. R. S. Mani, A. Saravanaselvan, and N. Arumugam, “Performance comparison of CNN, QNN and BNN deep neural networks for real-time object detection using ZYNQ FPGA node,” Microelectronics J., vol. 119, 2022, doi: 10.1016/j.mejo.2021.105319.
S. Bak et al., “Applicability Evaluation of Deep Learning-Based Object Detection for Coastal Debris Monitoring: A Comparative Study of YOLOv8 and RT-DETR,” Korean Journal of Remote Sensing, vol. 39, no. 6–1, pp. 1195–1210, 2023, doi: 10.7780/kjrs.2023.39.6.1.2.
D.-C. Rodríguez-Lira, D.-M. Córdova-Esparza, J. M. Álvarez-Alvarado, J.-A. Romero-González, J. Terven, and J. Rodríguez-Reséndiz, “Comparative Analysis of YOLO Models for Bean Leaf Disease Detection in Natural Environments,” AgriEngineering, vol. 6, no. 4, pp. 4585–4603, 2024, doi: 10.3390/agriengineering6040262.
B. Çarklı Yavuz, “Scale-Dependent Performance Analysis of YOLO26 and YOLOv11 for PPE Detection,” Electronics (Switzerland), vol. 15, no. 6, 2026, doi: 10.3390/electronics15061146.
I. P. Huaman-Pacco et al., “Proposal for Computationally Efficient Fog Computing System for Coffee Berry Borer Detection via Optimized YOLOv26,” Sensors, vol. 26, no. 7, 2026, doi: 10.3390/s26072212.
E. Macias-Garcia, D. Galeana-Pérez, V. Farias-Moreno, and E. Bayro-Corrochano, “Banknote and obstacle detection system for visually impaired people,” Comput. Methods Biomech. Biomed. Eng. Imaging Vis., vol. 11, no. 1, pp. 121–133, 2023, doi: 10.1080/21681163.2022.2058417.
T. Harminto, D. F. Najib, P. Wicaksono, and Z. N. Izdihar, “Performance Comparison of YOLOv8, YOLOv5 and YOLOv11 in Nature Image Segmentation,” Journal of Image and Graphics (United Kingdom), vol. 13, no. 5, pp. 515–520, 2025, doi: 10.18178/joig.13.5.515-520.
Y. Luo et al., “YOLOv11n-GrapeLite: A Lightweight Multi-Variety Grape Recognition Model,” Agriculture (Switzerland), vol. 16, no. 7, 2026, doi: 10.3390/agriculture16070794.
A. Safonova et al., “Deep learning for UAV thermal bird detection: Benchmarking YOLOv8–YOLOv26,” Remote Sens. Appl., vol. 42, 2026, doi: 10.1016/j.rsase.2026.101981.
A. M. Ghanem, H. A. Youness, M. Wahba, and H. M. Abdelaal, “Egyptian currency recognition for the visually impaired using deep learning models,” Neural Comput. Appl., vol. 38, no. 8, 2026, doi: 10.1007/s00521-026-11977-5.
M. Songthai and S. Kaitwanidvilai, “Enhancing deep learning–based railway inspection via PSO-guided brightness–contrast optimization,” Results in Engineering, vol. 29, 2026, doi: 10.1016/j.rineng.2026.109230.
X. Li, S. Xiao, P. Kumar, and B. Demir, “Data-driven few-shot crop pest detection based on object pyramid for smart agriculture,” J. Electron. Imaging, vol. 32, no. 5, 2023, doi: 10.1117/1.JEI.32.5.052403.
C. Li, M. Wang, L. Lei, H. Liu, K. Gao, and Z. Wang, “Research on Enhancing Fire Detection Performance in Ancient Architecture Under Occlusion Scenarios Based on YOLO-AR,” Sensors, vol. 26, no. 4, 2026, doi: 10.3390/s26041357.
M. Shamisavi, I. Segovia Ramirez, and C. Q. Gómez Muñoz, “Comparative Evaluation of YOLO- and Transformer-Based Models for Photovoltaic Fault Detection Using Thermal Imagery,” Energies (Basel)., vol. 19, no. 3, 2026, doi: 10.3390/en19030845.
P. Chhabra and S. Goyal, “A Two-Stage Deep Learning-Based Framework for Counterfeit Detection of Indian Currency Using YOLO-NAS and UV Imaging for Visually Impaired People,” Evergreen, vol. 12, no. 3, pp. 1633–1653, 2025, doi: 10.5109/7388855.
C. Charleen and G. P. Kusuma, “Evaluation of Deep Learning Models for Detection of Indonesian Rupiah,” International Journal of Computing and Digital Systems, vol. 16, no. 1, pp. 315–327, 2024, doi: 10.12785/ijcds/160125.
R. K. Hapsari, M. I. Khoiri, B. D. Satoto, A. H. Salim, and T. Kristanto, “Identification of Indonesian Rupiah Paper Currency Denominations Using First Order Statistical Feature Extraction and k-Nearest Neighbor,” International Journal on Informatics Visualization, vol. 9, no. 3, pp. 1244–1251, 2025, doi: 10.62527/joiv.9.3.3037.
M. Sofiyati, F. A. Wiranata, W. Shalanannda, E. Mulyana, I. Anshori, and A. Satriawan, “LoVi App: Android Application-based Image Classification for Low Vision,” Journal of ICT Research and Applications, vol. 18, no. 2, pp. 108–129, 2024, doi: 10.5614/itbj.ict.res.appl.2023.18.2.3.
A. Sharma, V. Kumar, and L. Longchamps, “Comparative performance of YOLOv8, YOLOv9, YOLOv10, YOLOv11 and Faster R-CNN models for detection of multiple weed species,” Smart Agricultural Technology, vol. 9, 2024, doi: 10.1016/j.atech.2024.100648.
H. A. Setiyo and L. Anifah, “Mango Leaf Detection: Comparison of YOLOv12n and YOLOv26n for Mangifera indica Disease,” Nucleus Journal, vol. 5, no. 1, pp. 27–45, May 2026, doi: 10.32492/nucleus.v5i1.5103.
M. Hussain, “YOLOv1 to v8: Unveiling Each Variant-A Comprehensive Review of YOLO,” IEEE Access, vol. 12, pp. 42816–42833, 2024, doi: 10.1109/ACCESS.2024.3378568.
T. G. Vibha, S. T. Chandra, and S. Sivaramakrishnan, “Benchmarking YOLO Variants on an Unseen Video: A Comparison of Inference Speed, GFLOPs, and Recall,” International Research Journal of Multidisciplinary Technovation, vol. 8, no. 2, pp. 203–211, 2026, doi: 10.54392/irjmt26212.
R. Khanam, T. Asghar, and M. Hussain, “Comparative Performance Evaluation of YOLOv5, YOLOv8, and YOLOv11 for Solar Panel Defect Detection,” Solar, vol. 5, no. 1, 2025, doi: 10.3390/solar5010006.
Z. Yang, X. Lan, and H. Wang, “Comparative Analysis of YOLO Series Algorithms for UAV-Based Highway Distress Inspection: Performance and Application Insights,” Sensors, vol. 25, no. 5, 2025, doi: 10.3390/s25051475.
N. Fanzury and M. Hwang, “Real-Time Identification of Mixed and Partly Covered Foreign Currency Using YOLOv11 Object Detection,” AI (Switzerland), vol. 6, no. 10, 2025, doi: 10.3390/ai6100241.
N. Fanzury and M. Hwang, “Identification of Mixed Foreign Banknotes Using YOLOv8 Object Detection,” Journal of Information and Communication Convergence Engineering, vol. 23, no. 2, pp. 101–112, 2025, doi: 10.56977/jicce.2025.23.2.101.
Y. Pan et al., “YOLO-CSB: A Model for Real-Time and Accurate Detection and Localization of Occluded Apples in Complex Orchard Environments,” Agronomy, vol. 16, no. 3, 2026, doi: 10.3390/agronomy16030390.
Z. Zheng et al., “Enhancing Geometric Factors in Model Learning and Inference for Object Detection and Instance Segmentation,” IEEE Trans. Cybern., vol. 52, no. 8, pp. 8574–8586, 2022, doi: 10.1109/TCYB.2021.3095305.
K. Alkandary, A. S. Yildiz, and H. Meng, “A Comparative Study of YOLO Series (v3–v10) with DeepSORT and StrongSORT: A Real-Time Tracking Performance Study,” Electronics (Switzerland), vol. 14, no. 5, 2025, doi: 10.3390/electronics14050876.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Rafli Firdaus Guzuntoro, Lilik Anifah
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
