• Durlav Kalita, Priyankush Gogoi
• Biswajit Das
• Sonali Mondal

As counterfeit currency techniques become more sophisticated, advanced detection methods that adapt accurately are necessary. This study investigates the application of three key machine learning algorithms—K-Nearest Neighbors (KNN), Support Vector Machines (SVM), and Convolutional Neural Networks (CNN)—to detect fake Indian currency notes using an image-based dataset. The SVM showed outstanding results with a perfect test accuracy of 1.00, while the KNN achieved a commendable accuracy of 0.92. The CNN, however, had lower accuracy at 0.76, underscoring challenges in feature learning and generalization. These findings suggest that traditional machine learning models like the SVM are highly effective for structured detection tasks. In contrast, CNNs might require additional adjustments and data enhancements to perform equally well. This study highlights the significant role of machine learning in combating economic crimes such as currency counterfeiting. It sets the stage for further development of more effective detection systems.

Classification Algorithms, Convolutional Neural Networks, Counterfeit Currency Detection, K-Nearest Neighbors, Machine Learning, Support Vector Machine

"A Comparative Analysis of Machine Learning Models to Identify Fake Currency", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 4, page no.o215-o219, April-2024, Available :http://www.jetir.org/papers/JETIR2404F30.pdf

"A Comparative Analysis of Machine Learning Models to Identify Fake Currency", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 4, page no. ppo215-o219, April-2024, Available at : http://www.jetir.org/papers/JETIR2404F30.pdf