Detecting Fake Banknotes: Performance Evaluation of ML and DL Algorithm

Gujarathi Kalyani, Basinepalli Keerthi, G. Shaheen Firdous, Boya Vasavi, Malipeddi Likhitha

2025

Abstract

For financial security, making sure counterfeit banknotes are detected is important. We evaluate the performance of many Machine Learning (ML) and Deep Learning (DL) algorithms to deceive fake currency accurately. It proposes extracting the numerical and visual features variance, skewness, entropy, of the wavelet transformed images which are fed to train and test the classification models. Important algorithms, such as Support Vector Machines (SVM), Decision Trees, Random Forests and Neural Networks are implemented and compared with respect to performance metrics like accuracy, precision, recall and F1 – score. Also, the detection accuracy is improved by using deep learning models, i.e., Convolutional Neural Networks (CNNs), which are capable of automated feature extraction. For the analysis, the dataset is used which contains labeled instances of genuine and counterfeit banknotes. Strengths and limitations of each approach are discussed and the applicability to the real word is discussed. Accuracy and robustness in counterfeit note detection using dummy models of Random Forest and deep learning models, e.g. CNNs, are superior according to results. The potential of AI driven solutions in automating counterfeit detection has been established in this project as it is a scalable, efficient, and cost-effective solution for the banking industry. The advancement of secure and reliable financial systems is made by leveraging data driven technologies in this study.

Paper Citation

in Harvard Style

Kalyani G., Keerthi B., Firdous G., Vasavi B. and Likhitha M. (2025). Detecting Fake Banknotes: Performance Evaluation of ML and DL Algorithm. In Proceedings of the 1st International Conference on Research and Development in Information, Communication, and Computing Technologies - ICRDICCT`25; ISBN 978-989-758-777-1, SciTePress, pages 468-475. DOI: 10.5220/0013900100004919

in Bibtex Style

@conference{icrdicct`2525,
author={Gujarathi Kalyani and Basinepalli Keerthi and G. Firdous and Boya Vasavi and Malipeddi Likhitha},
title={Detecting Fake Banknotes: Performance Evaluation of ML and DL Algorithm},
booktitle={Proceedings of the 1st International Conference on Research and Development in Information, Communication, and Computing Technologies - ICRDICCT`25},
year={2025},
pages={468-475},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013900100004919},
isbn={978-989-758-777-1},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 1st International Conference on Research and Development in Information, Communication, and Computing Technologies - ICRDICCT`25
TI - Detecting Fake Banknotes: Performance Evaluation of ML and DL Algorithm
SN - 978-989-758-777-1
AU - Kalyani G.
AU - Keerthi B.
AU - Firdous G.
AU - Vasavi B.
AU - Likhitha M.
PY - 2025
SP - 468
EP - 475
DO - 10.5220/0013900100004919
PB - SciTePress