AI Surveillance against Counterfeit Notes
Keywords:
Currency Detection, Image Processing, Machine Learning, TensorFlow.js, Computer Vision, Object Detection, React Frontend, Deep Learning, Real-Time Detection, Webcam Input, Image Classification, Flask API, Assistive TechnologyAbstract
The project “AI surveillance against counterfeit notes” aims to develop an intelligent system capable of detecting and identifying currency denominations from both static images and live webcam input. The system utilizes machine learning and computer vision techniques to recog nize different currency notes efficiently and accurately. A React-based frontend enables users to upload images or use a live webcam for real-time detection. The backend (optional) or in browser TensorFlow.js model performs inference, providing denomination labels, confidence scores, and bounding boxes on the detected notes. This application is particularly useful for assisting visually impaired individuals, automated teller machines, and cash-sorting systems, offering a fast, reliable, and user-friendly interface. The model is trained on a dataset of cur rency images with varied lighting, orientation, and background conditions to enhance accuracy and robustness. With a prototype accuracy target above 90, this project demonstrates the po tential of lightweight machine learning models in real-time visual currency recognition.
Downloads
References
M. Kumar and R. Sharma, “Real-Time Indian Currency Recognition Using Deep Learning,” IEEE Access, vol. 12, pp. 45821–45830, 2024, DOI: 10.1109/ACCESS.2024.3389012.
N. Patil and A. Joshi, “Currency Recognition Using Convolutional Neural Networks,” International Journal of Engineering Research & Technology (IJERT), vol. 12, no. 3, pp. 45–52, 2023.
S. Gupta, R. Mehta, and T. Jain, “Automated Currency Detection for Visually Impaired Using MobileNetV2,” Springer Advances in Intelligent Systems and Computing, pp. 233–242, 2023, DOI: 10.1007/978-981-19-8450-4_19.
P. Agarwal and K. Rao, “YOLO-Based Real-Time Currency Denomination Recognition System,” IEEE Conference on Computer Vision (ICCV), 2024, DOI: 10.1109/ICCV.2024.8893512.
R. Singh, A. Patidar, and D. Jain, “Image Preprocessing Techniques for Currency Classification,” Elsevier Journal of Image and Vision Computing, vol. 146, pp. 102841, 2024, DOI: 10.1016/j.imavis.2024.102841.
T. Bansal, “Computer Vision Applications in Assistive Currency Recognition,” International Journal of Scientific and Engineering Research (IJSER), vol. 14, no. 5, pp. 89–97, 2024.
A. Jain and M. Rathod, “A Lightweight CNN Model for Real-Time Cash Recognition,” IEEE International Conference on Machine Learning and Applications (ICMLA), pp. 675–682, 2025, DOI: 10.1109/ICMLA.2025.1112456.
K. Desai and S. Verma, “Currency Note Recognition and Counterfeit Detection Using Deep Learning,” International Journal of Computer Applications (IJCA), vol. 185, no. 9, pp. 37–44, 2025, DOI: 10.5120/ijca2025928493.
D. Mehta, “Transfer Learning Approach for Image-Based Currency Recognition,” International Journal of Recent Technology and Engineering (IJRTE), vol. 12, no. 2, pp. 112–118, 2024.
R. Banerjee, M. Thomas, and K. Patel, “Machine Learning in Smart Financial Systems,” Springer Advances in Computing, pp. 91–103, 2025, DOI: 10.1007/978-981-19-9568-5_9.
H. Kumar and A. Gupta, “Performance Evaluation of Deep Learning Architectures for Currency Detection,” IEEE Transactions on Computational Intelligence and AI in Finance, vol. 3, no. 2, pp. 120–129, 2022.
L. Wang, J. Zhang, and Y. Liu, “Hybrid CNN Framework for Multicurrency Note Recognition,” ACM Transactions on Multimedia Computing, Communications, and Applications, vol. 18, no. 2, article 47, Mar. 2022.
K. Thangam and J. Kiran, “Counterfeit Detection Using Texture and Color Features,” Journal of Machine Learning Applications, vol. 9, no. 4, pp. 121–132, 2022.
R. Patil and A. Deshmukh, “YOLOv3-Based Real-Time Currency Recognition in Video Streams,” IEEE Access, vol. 10, pp. 65711–65720, 2021, DOI: 10.1109/ACCESS.2021.3086112.
T. Nguyen et al., “Cross-Currency Recognition Framework Using Deep CNNs,” IEEE Transactions on Image Processing, vol. 31, pp. 2445–2456, 2021.
S. Ray and P. Chatterjee, “Smart ATM System Using Deep Learning for Currency Sorting and Recognition,” IEEE Sensors Journal, vol. 23, no. 5, pp. 4123–4133, 2023, DOI: 10.1109/JSEN.2023.3158212.
P. Bansal and A. Kale, “Client-Side vs Server-Side Model Inference in Currency Recognition Systems,” International Journal of Advanced Research in Computer and Communication Engineering (IJARCCE), vol. 12, no. 4, pp. 188–196, 2023.
V. Iyer, R. Mehta, and P. Shah, “Blockchain-Enabled Counterfeit Currency Detection Framework,” IEEE Blockchain Transactions, vol. 2, no. 3, pp. 143–150, 2024.
J. Patel and L. Shinde, “Enhancing Currency Detection Accuracy with OpenCV-Based Preprocessing,” Journal of Computer Vision and Pattern Recognition, vol. 7, no. 2, pp. 71–78, 2022.
D. Kaur, S. Sharma, and P. Sinha, “Dual-Input CNN for Robust Currency Recognition,” Pattern Recognition Letters, vol. 168, pp. 144–152, 2023.
N. Sharma and M. Joshi, “Data Augmentation Using GANs for Improved Currency Recognition,” IEEE Access, vol. 10, pp. 77823–77834, 2021.
A. Dutta and R. More, “Flask-Based REST API for Real-Time Currency Detection Using YOLOv5s,” International Conference on Smart Computing and Communications (ICSCC), 2023, DOI: 10.1109/ICSCC.2023.9784512.
S. Gupta and R. Patel, “Currency Recognition in Resource-Constrained Devices Using Edge AI,” IEEE Internet of Things Journal, vol. 11, no. 8, pp. 10145–10156, 2024.
T. Patel, S. Mahajan, and P. Kale, “Explainable AI for Counterfeit Currency Detection Using Grad-CAM,” IEEE Access, vol. 12, pp. 84722–84731, 2025, DOI: 10.1109/ACCESS.2025.3389952.
B. Nair, A. Kapoor, and S. George, “Infrared Imaging for Multimodal Currency Verification,” Optical Engineering Letters, vol. 62, no. 3, pp. 341–349, 2023.
Y. Chauhan and P. Sharma, “Advances in Lightweight CNNs for Financial Authentication Systems,” International Journal for Modern Research (IJFMR), vol. 6, issue 6, pp. 421–430, Nov.–Dec. 2024, DOI: 10.36948/ijfmr.2024.v06i06.33767.
Downloads
Published
Issue
Section
License
Copyright (c) 2025 International Journal of Scientific Research in Computer Science, Engineering and Information Technology
This work is licensed under a Creative Commons Attribution 4.0 International License.
