Developing and Evaluating an Explainable Deep Learning–Based User Interface for Libyan Currency Authentication.
DOI:
https://doi.org/10.37376/sjuob.v38i2.7470Keywords:
User Interface., Libyan Currency, Counterfeit Detection, Image Classification, Deep Learning, Efficientnet-B4,, Heatmap Visualization,, Grad-CAM,Abstract
The problem of counterfeit currency production and distribution is increasing, driven by technological advancements, particularly the development of advanced printing machines. The ongoing issue of counterfeit currency poses a significant threat to the national economy, necessitating the creation of an effective detection system. In light of this problem, this study proposes an intelligent system for identifying and detecting counterfeit Libyan currency. This system relies on deep learning techniques. Our proposed model is based on the EfficientNet-B4 controlled architecture, which seeks to optimize computing power and accuracy. In this study, the dataset was prepared and preprocessed using Gaussian filtering to reduce noise and normalize. The general framework developed here consists of two stages: The first stage is an intelligent filter that attempts to exclude any banknotes or images that are not Libyan currency, ensuring that only data related to Libyan banknotes is transmitted to the second stage of the model. The second stage is the core of the study, as it will determine whether Libyan currency is authentic or counterfeit. To improve the transparency of the model and enhance the understanding of its results, Grad-CAM software was used to generate heat maps that clearly show the banknote regions that contributed most to the model’s decision-making. To demonstrate the system’s usability, a mock-up user interface was designed to illustrate the system’s analysis and provide a practical environment. The results demonstrated good classification performance, consistently exceeding 90%, demonstrating how the proposed approach can be effectively applied to these models in practical situations. The findings of this research provide a practical framework to help financial institutions mitigate counterfeiting as part of the relevant compliance objectives that will determine the security of the monetary system. KEYWORDS: , , , ,Downloads
References
Barbosa J, Martins H S R, da Silva A J S, NoratoH M G, Duarte, A R. Counterfeit banknote identification based on outlier detection methods. International Journal of Scientific Management and Tourism, 2024;10(2), 45–59. ISSN: 2386-8570.
Antonius F, Ramu J, Sasikala P, Sekhar JC, Mary S C. Deep Cyber Detect: Hybrid AI for Counterfeit Currency Detection with GAN-CNN-RNN using African Buffalo Optimization. International Journal of Advanced Computer Science and Applications, 2023;14(7).
Alshorman O, Omar K, Ahmad T. Banknotes counterfeit detection using convolutional neural networks with attention mechanisms: A case study on Jordanian currency. Journal of Imaging, 2024 ;10(2).
Pham T D, Lee Y W, Park C, Park K R. Deep Learning-Based Detection of Fake Multinational Banknotes in a Cross-Dataset Environment Utilizing Smartphone Cameras for Assisting Visually Impaired Individuals. Mathematics, 2022;10(9), 1616.
Van der Horst F, Snell J, Theeuwes J. Finding counterfeited banknotes: the roles of vision and touch. Cognitive Research: Principles and Implications,2020; 5, Article 40.
Alzubaidi L, Zhang J, Humaidi A J.. Review of deep learning: concepts, CNN architectures, challenges, applications, future directions. J Big Data, 2021; 8, 53.
LeCun Y, Bengio Y. Hinton G. Deep learning. Nature, 2015; 521, 436–444 .
Waseem R, Zenghui W. Deep Convolutional Neural Networks for Image Classification: A Comprehensive Review. Neural Comput 2017; 29 (9): 2352–2449.
Krizhevsky A, Sutskever I, Hinton G. ImageNet classification with deep convolutional neural networks. In Proc. Advances in Neural Information Processing Systems, 2012; 25 1090–1098.
Gupta R., Singh S. Revolutionizing convolutional neural networks for enhanced currency security and fraud prevention. BPAS Journals. 2024; Vol.44 No. 3. P. 24900-24908.
Rangel C. A. survey on convolutional neural networks and their performance limitations in image recognition tasks. Journal of Sensors, 2024; 2797320.
O’Shea K, Nash R. An Introduction to Convolutional Neural Networks.2015; ArXiv, abs/1511.08458.
Albawi S, Mohammed T A,Al-Zawi S. “Understanding of a convolutional neural network,” 2017 International Conference on Engineering and Technology (ICET), Antalya, Turkey, 2017, pp. 1-6, doi: 10.1109/ICEngTechnol.2017.8308186.
Ali T, Jan S, Alkhodre A, Nauman M, Amin M, Siddiqui MS. DeepMoney: counterfeit money detection using generative adversarial networks. PeerJ Comput Sci. 2019;5:e216.
Wang J, Perez L,Hays J. The effectiveness of data augmentation in image classification using deep learning. Convolutional Neural Networks in Image Processing,2020; 10(4), 450–460.
Zhang B, Chen L, Liu X, Zhao L. Practices and challenges of using GitHub Copilot: An empirical study. arXiv preprint arXiv, 2023; 2303.08733.
Tan M, Le Q. EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks. In Proceedings of the 36th International Conference on Machine Learning 2019 ;(Vol. 97, pp. 6105–6114). PMLR.
Longo L, Lapuschkin S, Seifert C. (Eds.).. Explainable Artificial Intelligence: Second World Conference, xAI 2024, Valletta, Malta, July, Proceedings, Part IV (Communications in Computer and Information Science, 2024;Vol. 2156).
Cheng Z, Wu Y, Li Y, Cai L, Ihnaini B . A Comprehensive Review of Explainable Artificial Intelligence (XAI) in Computer Vision. Sensors, 2025; 25(13), 4166.
Zhang H, Ogasawara K. Grad-CAM-Based Explainable Artificial Intelligence Related to Medical Text Processing. Bioengineering (Basel). 2023; 10(9):1070. Published 2023 Sep 10.
Chattopadhay A, Sarkar A, Howlader P, BalasubramanianV N. Grad-CAM++: Generalized gradient-based visual explanations for deep convolutional networks. IEEE Winter Conference on Applications of Computer Vision (WACV), 2018;839–847.
Chefer H, Gur S, Wolf L. Transformer interpretability beyond attention visualization. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR),2021; 782–791.
Samek W.Wiegand T.Müller K. “Explainable Artificial Intelligence: Understanding, Visualizing and Interpreting Deep Learning Models.” ArXiv abs/1708.08296 2017: n. pag.
Selvaraju R. Cogswell M A, Das R. Vedantam D. BatraD. “Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization,; IEEE International Conference on Computer Vision (ICCV), Venice, Italy, 2017; pp. 618-626, doi: 10.1109/ICCV.2017.74.
Pachón, C G, Ballesteros, D M, Renza, D.. Fake banknote recognition using deep learning. Applied Sciences, 2021; 11(3), 1281.
Nasayreh A, Jaradat A S, Gharaibeh H, Dawaghreh W, Al Mamlook R M, Al-Na’amneh Q, Daoud M, Migdady H, Abualigah L. Jordanian banknote data recognition: A CNN-based approach with attention mechanism. Journal of King Saud University – Computer and Information Sciences, 2024; 36(4), 102038.
Rafiei A, Karimi A, Bodaghi M. Polymer banknotes: A review of materials, design, and printing. Sustainability, 2023; 15(4), 3736.
Lee J W. A survey on banknote recognition methods by various sensors. Sensors, 2017;17(11), 2627.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Scientific Journal of University of Benghazi
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
