.png)
Image-Based Detection of Reduced Security Features in Indonesian Banknotes Using U-Net Architecture
Abstract
The circulation of fake currency banknotes in Indonesia continues to rise alongside rapid technological advancements, while conventional verification systems remain limited and often ineffective in detecting subtle authenticity cues. The main objective of this study is to develop an image-based fake currency detection system using the U-Net deep learning architecture and its modified version, T-Net, to enhance feature extraction and classification accuracy. The key contribution of this research lies in combining convolutional architectures with a practical, web-based interface that enables real-time image analysis, thus bridging the gap between model performance and user accessibility. A quantitative experimental method was employed, involving model development in Python using TensorFlow and Keras, and implementation of a Flask-based web application for real-time classification. The research utilized a dataset of 2,141 Indonesian rupiah banknote images, consisting of 1,015 genuine and 1,126 fake currency samples synthetically generated through digital modification of security features such as watermarks and color-shifting ink. Image preprocessing included resizing, normalization, and augmentation techniques such as random flipping and brightness adjustment to enhance data quality. Three convolutional architectures U-Net, ResNet-50, and the modified T-Net were trained and compared using identical hyperparameters. The T-Net model achieved the best performance, with 97.8% training accuracy, 82.6% validation accuracy, precision of 0.83, recall of 0.80, and an F1-score of 0.81. Despite the performance gap indicating overfitting, the model effectively distinguishes genuine from fake currency notes. The Flask-based interface allows users to upload images and receive classification results from all three models within 0.3–1.8 seconds per image. The findings demonstrate the feasibility and efficiency of U-Net based architectures for image-driven fake currency detection and provide a foundation for developing advanced, reliable, and real-time financial authentication systems that can strengthen digital security infrastructures in future applications.
Keywords
Full Text:
PDFReferences
A. J. Andika, Y. Kristian, and E. I. Setiawan, “Detecting Cyberbullying Comments on YouTube Using the Convolutional Neural Network - Long Short-Term Memory Network (CNN-LSTM) Method,” TECHNIQUE: J. Technol. Inf. Commun., vol. 12, no. 3, 2023, doi: 10.34148/teknika.v12i3.677.
. D. Aprillia, T. Rohana, T. A. Mudzakir, and D. Wahiddin, “Detecting Rupiah Currency Nominal Using Convolutional Neural Network and Feedforward Neural Network Methods,” KLIK: Informatics and Computer Science Study, vol. 4, no. 4, 2024, doi: 10.30865/klik.v4i4.1711.
. I. R. W. Atmojo, “Implementation of Science, Technology, Engineering, Art, and Mathematics (STEAM)-Based Learning to Improve Elementary School Teachers' Pedagogical and Professional Competencies Through Method Lesson Study,” J. Educ. Base, vol. 8, no. 2, 2020, doi: 10.20961/jpd.v8i2.44214.
. V. Balakrishnan, H. L. Zing, and E. Laporte, “Covid-19 Infodemic–Understanding Content Features in Detecting Fake News using a Machine Learning Approach,” Malaysian J. Comput. Sci., vol. 36, no. 1, pp. 1–13, 2023, doi: 10.22452/mjcs.vol36no1.1.
. X. Chen, B. Zhang, and D. Gao, “Bearing Fault Diagnosis Base on Multi-Scale CNN and LSTM Model,” J. Intell. Manuf., vol. 32, pp. 971–987, 2021, doi: 10.1007/s10845-020-01600-2.
. H. S. Dimas, “Socialization of CIKUR (Characteristics of Authentic Rupiah) 2016 Emission Year to Prevent the Circulation of Counterfeit Money in Receiving Donations at the Al Irsyad Kertonegoro Mosque, Jenggawah District, Jember Regency,” MUJTAMA: J. Community Serv., vol. 1, no. 1, 2021, doi: 10.32528/mujtama.v1i1.5132.
. J. Ferreira, M. Mendonca, P. Dinic, and S. R., “Data Selection in Neural Networks,” IEEE Open J. Signal Process., vol. 1, no. 2, pp. 533–534, 2021, doi: 10.1109/OJSP.2021.3106197.
. H. Firat, M. E. Asker, M. I. Bayindir, and D. Hanbay, “MHybrid 3D/2D Complete Inception Module and Convolutional Neural Network for Hyperspectral Remote Sensing Image Classification,” Neural Process. Lett., vol. 55, 2023, doi: 10.1007/s11063-022-10929-z.
. I. Haider, H. J. Yang, G. S. Lee, and S. H. Kim, “Robust Human Face Emotion Classification using Triplet-Loss-Based Deep CNN Features and SVM,” Sensors, vol. 23, no. 10, pp. 1–19, 2023, doi: 10.3390/s23104770.
. W. Hamidah, N. A. P. Hasbullah, T. S. B. Irawan, and A. B. Kaswar, “Banknote Nominal Detection Using OCR (Optical Character Recognition),” J. Comput. Sci. Inf. Technol., vol. 7, no. 2, pp. 72–76, 2022, doi: 10.36805/technoxplore.v7i2.2123.
. D. Han, Q. Liu, and W. Fan, “A new image classification method using CNN transfer learning and web data augmentation,” Expert Syst. Appl., vol. 95, pp. 43–56, 2018, doi: 10.1016/j.eswa.2017.11.028.
. N. Hassan, T. Ahmad, N. A. Mahat, H. Maarof, and H. F. K., “Counterfeit Fifty Ringgit Malaysian Banknotes Authentication using Novel Graph-Based Chemometrics Method,” Sci. Rep., vol. 5, no. 4826, pp. 1–14, 2022, doi: 10.1038/s41598-022-08821-w.
. F. V. D. Horst, J. Snell, and J. Theeuwes, “Enhancing Banknote Authentication by Guiding Attention to Security Features and Manipulating Prevalence Expectancy,” Cogn. Res.: Princ. Implic., vol. 6, no. 73, pp. 1–10, 2021, doi: 10.1186/s41235-021-00341-x.
. M. M. Ibrahim, R. Rahmadewi, and L. Nurpulaela, “Detecting Currency Values in Images Using Convolutional Neural Networks: Integration of Image Pre-Processing and CNN-Based Classification Methods,” J. Inform. Eng., vol. 7, no. 2, 2023, doi: 10.36040/jati.v7i2.6863.
. D. Irfansyah, M. Mustikasari, and A. Suroso, “Alexnet U-Net Architecture for Pest Classification in Coffee Plant Leaf Images,” Informatics J.: Dev. J. IT, vol. 6, no. 2, pp. 87–92, 2021, doi: 10.30591/jpit.v6i2.2802.
. E. Jeczmionek and P. A. Kowalski, “Flattening Layer Pruning in Convolutional Neural Networks,” Symmetry, vol. 13, no. 7, pp. 1–13, 2021, doi: 10.3390/sym13071147.
. E. Kaya, A. Yasar, and I. Saritas, “Banknote Classification using Artificial Neural Network Approach,” Int. J. Intell. Syst. Appl. Eng., vol. 4, no. 1, pp. 16–19, 2016. [Online]. Available: https://ijisae.org/index.php/IJISAE/article/view/421
. A. Makundan, Y. M. Tsao, W. M. Cheng, F. C. Lin, and H. C. Wang, “Automatic Counterfeit Currency Detection using a Novel Snapshot Hyperspectral Imaging Algorithm,” Sensors, vol. 23, no. 4, pp. 1–14, 2023, doi: 10.3390/s23042026.
. Miladiah, R. Umar, and I. Riadi, “Local Implementation Binary Pattern for Currency Authenticity Detection Rupiah,” J. Inform. Educ. Res., vol. 5, no. 2, pp. 197–201, 2019, doi: 10.26418/jp.v5i2.32721.
. A. L. Zubaidi et al., “Review of Deep Learning: Concepts, CNN Architectures, Challenges, Applications, Future Directions,” J. Big Data, vol. 8, no. 53, pp. 1–74, 2021, doi: 10.1186/s40537-021-00444-8.
. A. R. Pratama and A. F. Cobantoro, “Pneumonia Image Classification Using U-Net Architecture,” NERO Sci. J., vol. 8, no. 2, pp. 133–144, 2023, doi: 10.21107/nero.v8i2.18992.
. A. R. Pratama, M. Mustajib, and A. Nugroho, “Banknote Image Detection with RGB Features Using K-Nearest Neighbor,” J. Eksplora Inform., vol. 9, no. 2, pp. 163–172, 2020, doi: 10.30864/eksplora.v9i2.336.
. B. A. Sadewa and Y. Yamasari, “Implementation of Deep Transfer Learning for Classification of Rupiah Banknotes,” JINACS: J. Inform. Comput. Sci., vol. 5, no. 4, pp. 543–551, 2024, doi: 10.26740/jinacs.v5n04.p543-551.
. R. A. Saputra, J. Nangi, I. P. Ningrum, M. F. Almaliki, and L. R. A. Pratama, “Detection of Counterfeit Rupiah Money Using the Laplacian of Gaussian (LoG) Edge Detection Method and the K-Means Clustering Algorithm,” J. Buana Inform., vol. 13, no. 2, pp. 85–92, 2022, doi: 10.24002/jbi.v13i02.5448.
. I. Singh, G. Goyal, and A. Chandel, “AlexNet Architecture Based Convolutional Neural Network for Toxic Comments Classification,” J. King Saud Univ. Comput. Inf. Sci., vol. 34, no. 9, pp. 7547–7558, 2022, doi: 10.1016/j.jksuci.2022.06.007.
. A. S. Siregar and Ishaq, “Analysis of Positive Law and Islamic Criminal Law on Criminal Acts in Spending Money,” JRTI: J. Hum. Action Res., vol. 8, no. 3, 2023, doi: 10.29210/30033377000.
. M. Soeharto, M. J. Hasan, A. R. Susanto, and D. A. Fahrezi, “Classifying Five Thousand Rupiah and Two Thousand Rupiah Currency Using the CNN Algorithm,” J. Inform. Eng., Sci. Commun. Stud., vol. 2, no. 3, 2024, doi: 10.59841/saber.v2i3.1407.
. M. M. Taye, “Theoretical Understanding of Convolutional Neural Networks: Concepts, Architectures, Applications, Future Directions,” Computation, vol. 11, no. 3, pp. 1–23, 2023, doi: 10.3390/computation11030052.
. K. D. K. A. Wardani, K. I. D. Jayanti, A. A. Gorda, and N. E. Supriyadinata, “Efforts to Combat Counterfeit Money Circulation in Denpasar City Through Cikur Education (Characteristics of Authentic Rupiah Banknotes),” Dissemination: J. Devotion Public, vol. 6, no. 2, 2024, doi: 10.33830/diseminasiabdimas.v6i2.6286.
. Y. J. Wong, “Comparative study of artificial neural network (ANN), adaptive neuro-fuzzy inference system (ANFIS) and multiple linear regression (MLR) for modeling of Cu (II) adsorption from aqueous solution using biochar derived from rambutan (Nephelium lappaceum) peel,” Environ. Monit. Assess., vol. 192, no. 7, 2020, doi: 10.1007/s10661-020-08268-4.
. R. Yamashita, M. Nishio, D. R. K. G., and K. Togashi, “Convolutional Neural Networks: An Overview and Application in Radiology,” Insights Imaging, vol. 9, pp. 611–629, 2018, doi: 10.1007/s13244-018-0639-9.
. A. Zafar et al., “Comparison of Pooling Methods for Convolutional Neural Networks,” Appl. Sci., vol. 12, no. 17, pp. 1–21, 2022, doi: 10.3390/app12178643.
DOI: https://doi.org/10.47738/jads.v7i1.1087
Refbacks
- There are currently no refbacks.
Journal of Applied Data Sciences
| ISSN | : | 2723-6471 (Online) |
| Publisher | : | Bright Publisher |
| Website | : | http://bright-journal.org/JADS |
| : | taqwa@amikompurwokerto.ac.id (principal contact) | |
| support@bright-journal.org (technical issues) |
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0