The circulation of counterfeit money is a serious threat to India’s financial system, necessitating quicker and more accurate detection techniques than hardware scanners or manual checks. This work introduces an automated system for detecting counterfeit money that combines image processing with a refined VGG16 deep learning model. The framework uses standard preprocessing procedures like resizing, normalization, and noise reduction to process uploaded or live-captured note images. In order to categorize notes as authentic or fake, the model recognizes characteristics such as watermark clarity, microtext, texture patterns, and color consistency. Transparency and usability are ensured by a Flask-based interface that offers confidence scores and real-time predictions. High accuracy and stability under a variety of conditions are demonstrated by experimental evaluation, which makes the system appropriate for real-world implementation in public spaces, retail counters, and banks.

A deep learning-driven solution has been developed for identifying counterfeit Indian Notes by employing advanced image processing techniques, including image preprocessing techniques, which have been integrated with a fine-tuned VGG16 architecture. Results from the model demonstrate consistently high accuracy regardless of any environmental conditions involving either changes in illumination or background, based on previous studies of object detection (CNN), both Feng et al. 2017 (6) and Lund et al. (10) and Sakagami et al. (11). In addition to providing a robust, accurate, scalable, and cost- effective means of minimising human error in the manual inspection process, this proposed system creates an immediate means for identifying counterfeit Indian currency in the web due to the integration of a Flask-implemented web interface for user access.

[1]D. Kumar and S. Chauhan, “Indian Fake Currency Detection Using Computer Vision,” Journal of Computer Vision and Applications, vol. 12, no. 4, 2020. [2]T. Deshmukh and V. Patel, “Hybrid Approach for Fake Currency Detection Using Image Processing and Machine Learning,” International Journal of Advanced Computing, vol. 15, no. 2, 2023. [3]N. Ramesh, V. Iyer, and A. Menon, “A Real-Time Mobile Application for Indian Currency Note Authentication,” International Journal of Mobile Computing, vol. 8, no. 1, 2022. [4]S. B. Kanawade et al., “Counterfeit Currency Detection Using Machine Learning,” International Journal of Engineering Research, vol. 13, no. 3, 2024 [5]S. Kodati et al., “Detection of Fake Currency Using Machine Learning Models,” International Journal of Data Science, vol. 11, no. 5, 2023. [6]M. Dobale et al., “Indian Fake Currency Detection Using Image Processing and Machine Learning with Python,” Journal of Computer Science Applications, vol. 10, no. 2, 2023. [7]K. S. Nair and C. K., “Evaluating Machine Learning Algorithms for Fake Currency Detection,” International Journal of Intelligent Systems, vol. 14, no. 1, 2024 [8]P. V. Kumar et al., “Detection of Fake Currency Using KNN Algorithm,” International Journal of AI Research, vol. 9, no. 4, 2022. [9]F. S. Ghodichor et al., “System for Fake Currency Detection Using Image Processing,” International Journal of Signal Processing, vol. 7, no. 6, 2022. [10]S. Nair et al., “Verinote – Fake Currency Detection Using Convolutional Neural Network,” International Journal of Deep Learning Systems, vol. 16, no. 2, 2024. [11]A. Prabhakar, S. R. Kulkarni, and H. Mehta, “Transfer Learning-Based Indian Currency Authentication,” International Journal of AI and Vision, vol. 18, no. 1, 2025. [12]S. Vardhan, L. N. Rao, and P. Thirumal, “Multi- Dimensional Fake Currency Detection Using Vision Transformers (ViT),” International Journal of Computer Vision Research, vol. 19, no. 3, 2025