Fake Currency Detector Using Image Processing and Computer Vision Techniques

Abstract

Counterfeiting of currency has become a real threat to the livelihood of people as well as the economy of our country. Though fake currency detectors are available, they are restricted to banks and corporate offices leaving common people and small businesses vulnerable. This project investigates the various secu- rity features of Indian currency and prepares a software-based system to detect and invalidate fake Indian currency by using advanced image processing and computer vision techniques. The proposed authentication system is implemented completely in Python, within a Jupyter Notebook environment, and achieves an accuracy of up to 83% in counterfeit detection

Introduction

The paper addresses the global problem of counterfeit currency, which devalues real money and contributes to inflation. Manual verification methods are slow and error-prone, so an automated system for detecting counterfeit Indian Rs. 500 and Rs. 2000 notes using computer vision is proposed. The system identifies key security features—watermarks, bleed lines, number panels, logos, and text inscriptions—through three algorithms and presents results via an intuitive Tkinter GUI.

Literature Survey: Various existing methods were reviewed, including image processing, MATLAB-based recognition, OCR with hybrid approaches, hyperspectral imaging, and voice-assisted verification for visually impaired users.

Problem Statement & Objectives: The goal is to automatically verify currency authenticity with speed, accuracy, and a user-friendly interface.

Methodology:

• Dataset Preparation: Images of real and counterfeit notes with feature templates.

• Image Acquisition & Preprocessing: Scanning/capturing images, converting to grayscale, and applying Gaussian blur.

• Algorithms:

  1. Feature matching using ORB detector and Structural Similarity Index (SSIM).

  2. Bleed line verification through contour detection.

  3. Number panel detection via segmentation and spatial arrangement checks.

• GUI: Displays results with Pass/Fail for each feature.

Implementation: Iterative development covering requirement analysis, system design, development, integration, and testing.

Results: Accuracy of 83% for fake notes and 79% for real notes, with processing time of ~5 seconds per note.

Functionalities:

• Preprocessing ensures consistent, noise-reduced input.

• CNN-based model learns to detect distinguishing features for real vs. fake notes.

• Prediction module provides classification results with confidence scores and error analysis.

• User-friendly GUI allows easy image upload, real-time feedback, and historical checks.

Conclusion

This paper describes the design and development of a system for counterfeit currency detection developed in Python. The proposed model achieves up to 83generate results in a matter of a few seconds. Current system may correctly identify specific denominations while future improvements could integrate greater deep learning capabilities for feature extraction and more currencies and note values to make a more holistic solution.

References

[1] S. R. Darade, “Automatic System for Identification of Fake Currency Notes,” 2018. [2] B. P. Yadav, P. H. Patil, “Recognition of Fake Indian Paper Currency Note using MATLAB,” 2019. [3] A. Zarin, J. Uddin, “Hybrid Fake Currency Detection Model for Bangladeshi Notes,” 2019. [4] S. Veling, “Fake Note Detection using Hyperspectral Imaging,” 2020. [5] P. Mangayarkarasi, A. S. Anakha, M. K. Meghashree, “Currency Recog- nition and Verification for Visually Impaired,” 2021. [6] Authentication of Indian paper currency using digital image processing [7] Sarkar, S., Pal, A. K. 2022. [8] Detection of Counterfeit Currency Using Supervised Machine Learning Algorithms — Yadav, R. K., Valecha, P., Paliwal, S. 2020. [9] Evaluating Machine Learning Algorithms for Fake Currency Detection [10] Keerthana S.N., Chitra K., Journal of Data Science, 2024. [11] Fake Indian Currency Detection System — P. S. Purohit, Sanika Datta- traya Bhosle, Ashish Hemant Ghatule, Tejaswini Vijay Kolekar, Ritesh Arvind Kataktalware, Vishal Ramkrishna Patil, IJRASET, 2025. [12] Identification of Fake Indian Currency Using Convolutional Neural Network — Raja Sekhar, P., et al. 2023 [13] Image Based Fake Currency Detection Using Explainable AI — Sakinala Jhosna, Geethanjali, Manoj Kumar et al. 2022. [14] Banknote Verification using Image Processing Techniques — Barrera Nazir, Muhammad Imran Babar Jehangir. 2019. [15] Fake Currency Note Detection using Image Processing and Convolution Neural Network — Dr. S. Sahaya Tamil Selvi et al. 2023 [16] Authentication of Indian Currency using Image Processing Techniques “Image Processing Technique for Authentication of Indian Paper Currency” — Rencita Maria Colaco et al. 2023 [17] Fake Currency Detection using Deep Learning Technique — Ruheena, Bibi Fathima, Harshitha B M, etc. 2022

Copyright

Copyright © 2025 Drashti Mehta, Nisha Modi, Karman Rao, Kartik Patel, Rahul Kumar. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.