• Vighnesh Kutty
• Siddharth Chhatre
• Mithunkumar Ravichandran
• Nitesh Pandey
• Kirti Rana

Counterfeit banknotes pose significant economic and security challenges globally. Traditional detection methods, reliant on manual inspection and physical security features, are often inefficient and errorprone. This paper proposes a deep learning-based system leveraging Convolutional Neural Networks (CNNs) to automate fake banknote detection. The system processes high-resolution banknote images through preprocessing, feature extraction, and classification modules. Experimental results demonstrate an accuracy of 98.3% on a dataset of 4,000 images, outperforming traditional methods like UV analysis and KNN classifiers. The solution is scalable, integrable with existing financial infrastructure (e.g., ATMs, POS systems), and robust under diverse environmental conditions. Key contributions include a hybrid CNN architecture combining ResNet and edge detection, a portable edgecomputing implementation, and synthetic data augmentation using Generative Adversarial Networks (GANs). The system’s efficacy is validated through metrics such as precision (97.5%), recall (98.1%), and F1- score (97.8%), establishing its applicability in real-world scenarios.

Counterfeit detection, convolutional neural networks (CNNs), deep learning, image processing, financial security, edge detection, Generative Adversarial Networks (GANs), ResNet-50, synthetic data augmentation, model optimization, real-time systems, automated teller machines (ATMs), anti-counterfeiting technologies, pattern recognition, computational efficiency, adversarial robustness, security features authentication, financial fraud prevention, hybrid architectures, mobile deployment

"Deep Learning-Based Fake Banknote Detection System", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 4, page no.h323-h329, April-2025, Available :http://www.jetir.org/papers/JETIR2504761.pdf

"Deep Learning-Based Fake Banknote Detection System", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 4, page no. pph323-h329, April-2025, Available at : http://www.jetir.org/papers/JETIR2504761.pdf