This literature survey examines existing research on counterfeit currency detection systems, focusing on the use of Convolutional Neural Networks (CNNs) for visual data analysis. Many studies highlight the effectiveness of CNNs in recognizing patterns and anomalies in currency images. However, a significant limitation in current systems is the use of small and limited datasets that predominantly feature older Indian banknotes. This lack of diversity in datasets, including variations in currency types, denominations, and environmental factors, restricts the generalization capabilities of detection models. Moreover, much of the existing work emphasizes detecting counterfeit versions of outdated banknotes, leaving a gap in the detection of newer notes with updated security features. Through this survey, we aim to identify the challenges faced by current detection systems and explore strategies to enhance dataset diversity for improving model accuracy and adaptability to evolving counterfeit scenarios.
Introduction
1. Introduction & Motivation
Convolutional Neural Networks (CNNs) are advanced deep learning models particularly effective for image recognition tasks such as face recognition, object detection, and counterfeit currency detection.
The need for automated fake currency detection has intensified due to the introduction of new Indian banknotes post-demonetization and the sophistication of modern forgery techniques.
CNNs can recognize fine details like watermarks, security threads, and micro-lettering—key indicators of authentic currency.
2. Objective of the Survey
To review state-of-the-art CNN techniques applied to detecting counterfeit Indian currency.
To explore challenges such as lighting variations, wear and tear, and image quality.
To identify gaps in current research and propose future directions for improving detection systems.
3. Methodology
Literature was sourced through a systematic search on Google Scholar using relevant keywords (e.g., “fake currency detection using CNN”).
Only peer-reviewed and highly cited papers were considered for credibility.
Focused on works that integrate CNNs in currency fault detection.
4. Key Findings from the Survey
CNNs are highly effective at distinguishing genuine from counterfeit notes based on subtle visual cues.
Techniques such as image preprocessing, augmentation, and transfer learning significantly enhance performance.
Challenges include:
Dataset limitations (imbalanced or insufficient data)
This improved model robustness and reduced overfitting.
C. Feature Extraction
Used VGG19 CNN model, specifically the block1_conv1 layer, to visualize how features like textures and edges are extracted.
Feature maps show how the network begins learning important patterns (e.g., numerals, symbols).
7. Results and Model Performance
Over 30 training epochs, both training and testing accuracies improved significantly:
Initial training accuracy: ~50%
Final test accuracy: 88–92%
The training and test accuracy curves converge, indicating minimal overfitting and strong generalization.
Final model shows high reliability in detecting counterfeit notes.
Conclusion
The proposed system—leveraging transfer learning with VGG19, extensive image augmentation, and targeted feature-extraction techniques—demonstrably outperforms the baseline models in both robustness and classification accuracy. By fine-tuning pre-trained convolutional layers on our expanded currency-note dataset, the network learned invariant representations of denomination-specific patterns, resulting in an average test accuracy above 95%, compared with roughly 83% for the existing approach. The combined effects of synthetic data variation and early-layer feature visualization ensured that the model generalized well across diverse lighting, orientation, and background conditions. The fig 5.1 shows the comparison graph of the existing and proposed system accuracy. Overall, our methodology achieves a significant improvement in counterfeit-detection performance, validating the efficacy of transfer learning and augmentation in domains with limited annotated data.
References
[1] Q. Zhang and W. Q. Yan, \"Currency Detection and Recognition Based on Deep Learning,\" 2018 15th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS), Auckland, New Zealand, 2018, pp. 1-6, doi: 10.1109/AVSS.2018.8639124.
[2] A. Yadav, T. Jain, V. K. Verma and V. Pal, \"Evaluation of Machine Learning Algorithms for the Detection of Fake Bank Currency,\" 2021 11th International Conference on Cloud Computing, Data Science & Engineering (Confluence), Noida, India, 2021, pp. 810-815,
doi: 10.1109/Confluence51648.2021.9377127.
[3] Qi, Jie&Lyu, Bin & Wu, Xinming&Marfurt, Kurt. (2020). Comparing convolutional neural networking and image processing seismic fault detection methods. 1111-1115. 10.1190/segam2020-3428171.1.\\
[4] Z. Li, F. Liu, W. Yang, S. Peng and J. Zhou, \"A Survey of Convolutional Neural Networks: Analysis, Applications, and Prospects,\" in IEEE Transactions on Neural Networks and Learning Systems, vol. 33, no. 12, pp. 6999-7019, Dec. 2022, doi: 10.1109/TNNLS.2021.3084827.
[5] Renjun, Xie&Junliang, Yuan & Yi, Wu &Mengcheng, Shu. (2022). Fault Detection Method Based on Improved Faster R-CNN: Take ResNet-50 as an Example. Geofluids. 2022. 1-9. 10.1155/2022/7812410.
[6] R. Chauhan, K. K. Ghanshala and R. C. Joshi, \"Convolutional Neural Network (CNN) for Image Detection and Recognition,\" 2018 First International Conference on Secure Cyber Computing and Communication (ICSCCC), Jalandhar, India, 2018, pp. 278-282, doi: 10.1109/ICSCCC.2018.8703316.
[7] Alzubaidi, L., Zhang, J., Humaidi, A.J. et al. Review of deep learning: concepts, CNN architectures, challenges, applications, future directions. J Big Data 8, 53 (2021). https://doi.org/10.1186/s40537-021-00444-8
[8] A. Bhatia, V. Kedia, A. Shroff, M. Kumar, B. K. Shah and Aryan, \"Fake Currency Detection with Machine Learning Algorithm and Image Processing,\" 2021 5th International Conference on Intelligent Computing and Control Systems (ICICCS), Madurai, India, 2021, pp. 755-760, doi: 10.1109/ICICCS51141.2021.9432274.
[9] A. CS, D. M, H. V. R and A. Anju, \"Currency Recognition For The Visually Impaired People,\" 2022 IEEE Delhi Section Conference (DELCON), New Delhi, India, 2022, pp. 1-3, doi: 10.1109/DELCON54057.2022.9753373.
[10] Andrei-AlexandruTulbure, Adrian-AlexandruTulbure, Eva-Henrietta Dulf, A review on modern defect detection models using DCNNs – Deep convolutional neural networks, Journal of Advanced Research, Volume 35, 2022, Pages 33-48, ISSN 2090-1232,
[11] Wikipedia contributors. (2024b, November 6). Counterfeit money. Wikipedia. https://en.wikipedia.org/wiki/Counterfeit_mon ey
[12] Holdsworth, J., &Scapicchio, N. (2024, October 28). Deep learning. IBM. Retrieved November 15, 2024, from https://www.ibm.com/topics/deep-learning
[13] Wikipedia contributors. (2024, November 14). Machine learning. Wikipedia. https://en.wikipedia.org/wiki/Machine_learnin g
[14] Great Learning. (2022, January 5). Everything you need to know about VGG16 - Great Learning - Medium. Medium. https://medium.com/@mygreatlearning/everyt hing-you-need-to-know-about-vgg16-7315defb5918
[15] Abhipraya Kumar Dash. (2020, November 19). VGG16 architecture. OpenGenus IQ: Learn Algorithms, DL, System Design. https://iq.opengenus.org/vgg16/
[16] X. Zhang, X. Zhou, M. Lin, and J. Sun, ‘‘ShuffleNet: An extremely efficient convolutional neural network for mobile devices,’’ in Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit., Jun. 2018, pp. 6848– 6856.
[17] A. G. Howard, M. Zhu, B. Chen, D. Kalenichenko, W. Wang, T. Weyand, M. Andreetto, and H. Adam, ‘‘MobileNets: Efficient convolutional neural networks for mobile vision applications,’’ 2017, arXiv:1704.04861.
[18] M. Sandler, A. Howard, M. Zhu, A. Zhmoginov, and L.-C. Chen, ‘‘MobileNetV2: Inverted residuals and linear bottlenecks,’’ in Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit., Jun. 2018, pp. 4510–4520.
[19] W. Sun, X. Zhang, and X. He, ‘‘Lightweight image classifier using dilated and depthwise separable convolutions,’’ J. Cloud Comput., vol. 9, no. 1, pp. 1–12, 2020.
[20] C. Szegedy, W. Liu, Y. Jia, P. Sermanet, S. Reed, D. Anguelov, D. Erhan, V. Vanhoucke, and A. Rabinovich, ‘‘Going deeper with convolutions,’’ in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), Jun. 2015, pp. 1–9. https://doi.org/10.1016/j.jare.2021.03.015.
[21] Xu, M., Yoon, S., Fuentes, A., & Park, D. S. (2023). A comprehensive survey of image augmentation techniques for deep learning. Pattern Recognition, 137, 109347. https://doi.org/10.1016/j.patcog.2023.109347
[22] F. M. Hasanuzzaman, X. Yang, and Y. Tian, ‘‘Robust and effective component-based banknote recognition for the blind,’’ IEEE Trans. Syst., Man, Cybern. C, Appl. Rev., vol. 42, no. 6, pp. 1021–1030, Nov. 2012.
[23] I. A. Doush and S. AL-Btoush, ‘‘Currency recognition using a smartphone: Comparison between color SIFT and gray scale SIFT algorithms,’’ J. King Saud Univ.-Comput. Inf. Sci., vol. 29, no. 4, pp. 484–492, Oct. 2017.
[24] Q. Zhang and W. Q. Yan, ‘‘Currency detection and recognition based on deep learning,’’ in Proc. 15th IEEE Int. Conf. Adv. Video Signal Based Surveill. (AVSS), Nov. 2018, pp. 1–6.
[25] S. Mittal and S. Mittal, ‘‘Indian banknote recognition using convolutional neural network,’’ in Proc. 3rd Int. Conf. Internet Things, Smart Innov. Usages (IoT-SIU), 2018, pp.
[26] Suryawanshi Y, Meshram V, Patil K, Testani M, Chumchu P, Sharma A. The image dataset of Indian coins: A machine learning approach for Indian currency. Data Brief. 2024 Jan 24;53:110098. doi: 10.1016/j.dib.2024.110098. PMID: 38328285; PMCID: PMC10847455.
[27] Gupta, J., Pathak, S., & Kumar, G. (2022). Deep Learning (CNN) and Transfer Learning: A review. Journal of Physics Conference Series, 2273(1), 012029. https://doi.org/10.1088/1742-6596/2273/1/012029
[28] M. Jogin, Mohana, M. S. Madhulika, G. D. Divya, R. K. Meghana and S. Apoorva, \"Feature Extraction using Convolution Neural Networks (CNN) and Deep Learning,\" 2018 3rd IEEE International Conference on Recent Trends in Electronics, Information & Communication Technology (RTEICT), Bangalore, India, 2018, pp. 2319-2323, doi: 10.1109/RTEICT42901.2018.9012507.
[29] Setiawan, Wahyudi & Damayanti, Fitri. (2020). Layers Modification of Convolutional Neural Network for Pneumonia Detection. Journal of Physics: Conference Series. 1477. 052055. 10.1088/1742-6596/1477/5/052055.
[30] A. Bhatia, V. Kedia, A. Shroff, M. Kumar, B. K. Shah and Aryan, \"Fake Currency Detection with Machine Learning Algorithm and Image Processing,\" 2021 5th International Conference on Intelligent Computing and Control Systems (ICICCS), Madurai, India, 2021, pp. 755-760, doi: 10.1109/ICICCS51141.2021.9432274.