International Research Journal of Innovations in Engineering and Technology - IRJIET International Open Access, Monthly, Peer Reviewed, Reputed Journal ISSN (online): 2581-3048

Impact Factor (2025): 6.9

DOI Prefix: 10.47001/IRJIET

Multi Task Learning Based Transformer Model for Real-Time Indian Fake Currency Detection & Conversion

Karthik. SDepartment of Artificial Intelligence, Madanapalle Institute of Technology & Science (MITS), Madanapalle, AP, IndiaManjunath. KDepartment of Artificial Intelligence, Madanapalle Institute of Technology & Science (MITS), Madanapalle, AP, IndiaNishal. P.HDepartment of Artificial Intelligence, Madanapalle Institute of Technology & Science (MITS), Madanapalle, AP, IndiaRizwan. SDepartment of Artificial Intelligence, Madanapalle Institute of Technology & Science (MITS), Madanapalle, AP, IndiaNirupa. VDepartment of Artificial Intelligence, Madanapalle Institute of Technology & Science (MITS), Madanapalle, AP, India

Vol 9 No 2025 (2025): Volume 9, Special Issue of ICCIS-2025 May 2025 | Pages: 1-7

International Research Journal of Innovations in Engineering and Technology

OPEN ACCESS | Research Article | Published Date: 11-06-2025

doi Logo doi.org/10.47001/IRJIET/2025.ICCIS-202501

pdf iconFull Text PDF
Abstract

Economic systems frequently face the problem of counterfeit money circulation, which compromises financial credibility and transaction integrity. Even while manual and UV-based inspection methods are widely utilized, they are time-consuming, prone to human mistake, and inefficient and subjective, hence automated replacements are required. In order to improve and automate the detection of counterfeit cash, this study proposes a hybrid deep learning model that makes use of Transformers, Convolutional Neural Networks (CNNs), and Recurrent Neural Networks (RNNs).

RNNs analyze sequential data, such money serial numbers, for anomalies, Transformers hone spatial correlations, and CNNs collect complex visual aspects. This multi-modal method facilitates real-time operation and increases detection robustness. Indian banknotes in values of 100, 200, and 500 Indian rupees are used to train the model.

Once a note is classified as genuine, the system integrates a real-time currency conversion module to convert its value into various foreign currencies, enhancing its practical applicability for financial and travel-related use cases. The model is implemented using TensorFlow and PyTorch, with optimization techniques including batch normalization, dropout, and transfer learning.

With little retraining, the system is made to be flexible and expandable across several money kinds. It may be implemented in settings including retail points of sale, ATMs, and banks. Additionally, the architecture is appropriate for mobile platforms and embedded devices because to its support for real-time processing. Its modular architecture also makes it possible to integrate OCR for serial number recognition in the future. All things considered, this approach offers a strong, effective, and expandable answer to the cash authentication issue.

Keywords

Fake Currency Detection, Indian Currency, CNN, Transformer, RNN, Multi-Task Learning, Currency Converter


Citation of this Article

Karthik. S, Manjunath. K, Nishal. P.H, Rizwan. S, & Nirupa. V. (2025). Multi Task Learning Based Transformer Model for Real-Time Indian Fake Currency Detection & Conversion. In proceeding of Second International Conference on Computing and Intelligent Systems (ICCIS-2025), published in IRJIET, Volume 9, Special Issue ICCIS-2025, pp 1-7. Article DOI https://doi.org/10.47001/IRJIET/2025.ICCIS-202501

Licence Copyright (c) 2026 International Research Journal of Innovations in Engineering and Technology creative common licence This work is licensed under Creative common Attribution Non Commercial 4.0 Internation Licence
References
  1. M. Sravani, "Detection of Fake Indian Currency Using Deep Learning," 2024. Proposes a deep learning-based approach for distinguishing counterfeit Indian currency using visual patterns and texture recognition
  2. M. R. K. Choudhary, "Identification of Fake Currency Found in India," S. B. Jain Institute of Technology, Maharashtra, India, 2024. Discusses the challenges of fake currency circulation and presents an image-based detection method tailored for Indian notes.
  3. N. A. Rakesh, "Detection of Fake Currency," CMR Engineering College,Hyderabad,2024. Explores image preprocessing and feature extraction methods for fake note classification using machine learning algorithms.
  4. O. T. I, "Fake Currency Detection using Modified Faster Region-Based Convolutional Neural Network," Afe Babalola University, Nigeria, 2024. Introduces a region-based deep learning model for detecting counterfeit features on currency using Faster R-CNN.
  5. C. G. H, "Fake Currency Detection Using Machine Learning," BGS Institute of Technology, Mandya, Karnataka, India, 2024. Implements machine learning techniques for analyzing security features in Indian banknotes using statistical and visual cues.
  6. S. Charan, "Indian Fake Currency Detection Using Image Processing and Machine Learning," 2024. Combines edge detection and color histogram analysis to classify Indian currency notes as real or fake.
  7. Rajesh, "AI-Based Currency Verification System," 2024. Proposes a practical AI-powered system suitable for kiosks and mobile apps to verify the authenticity of currency notes.
  8. Sharma, "Real-Time Fake Currency Detection Using Mobile AI," 2024. Focuses on a mobile application for real-time note classification using embedded deep learning models.
  9. K. S. Sagar, "Counterfeit Currency Detection Using Machine Learning," Chaitanya Bharathi Institute of Technology, Hyderabad, India, 2023. Applies traditional image processing and ML classifiers to detect Indian counterfeit notes under variable lighting.
  10. P. D. P. Patil, "Counterfeit Currency Detection Based on AI," K.C. College of Engineering and Management Studies and Research, Thane, India, 2022. .Explores AI techniques to identify watermark inconsistencies and embedded elements on notes.
  11. S. B, "Fake Currency Detection Using Deep Learning," ,” Canara Engineering College, Karnataka, India, 2023. Implements a CNN-based classification model to distinguish fake notes by learning from visual datasets.
  12. M. M. Kalaiselvi, "Identification of Fake Indian Currency Using CNN," Vivekanandha College of Technology for Women, Tamil Nadu, India, 2023. Focuses on the design of CNNs trained on image datasets of Indian currency for binary classification tasks.
  13. A. Antre, "Fake Currency Detection Using CNN," Pune Vidyarthi Griha’s College of Engineering & Technology, 2023. Utilizes a lightweight convolutional neural network trained with augmentation to detect note forgery.
  14. M. K. Bhushanm, "Fake Currency Detection Using Deep Learning," VVIT, Guntur, India, 2024. Explores serial number recognition and visual verification using deep learning tools for Indian notes.
  15. K. Abhiram, "Identification of Fake Indian Currency Using CNN,”," Guru Nanak Institutions Technical Campus, Hyderabad, India, 2024. Implements a CNN model for identifying forged patterns on Indian currency notes with a focus on ease of deployment.

Copyright @ 2026 IRJIET. All Right Reserved.

Licensed underCreative Commons Attribution 4.0 International License.