Artificial Intelligence Model of Iraqi Paper Currency Detection in Vending Machines

Shymaa Akram Hantoush

doi:10.30526/39.2.4330

Authors

Shymaa Akram Hantoush Middle Technical University, Continuous Education Center, Baghdad, Iraq https://orcid.org/0000-0003-4200-7748

DOI:

https://doi.org/10.30526/39.2.4330

Keywords:

Artificial intelligence (AI); Convolutional Neural Network (CNN); Vending machines (VM); Mahalanobis-distance (Mah-dis)

Abstract

The development of technology is becoming necessary in multiple fields that specialize in human interaction life. This has contributed to increasing awareness of electronic financial transactions by enhancing the ease of handling currencies, especially by employing vending machines in commercial markets and airports. Vending machines have become widespread nowadays, and due to their ease of use for customers, it has become necessary to pay attention to this type of device. Due to the different currencies adopted in countries around the world, there has emerged a need to increase the flexibility of programming these machines to be suitable for the countries using the devices. In this research, an intelligent convolutional neural network model CNN was built based on artificial intelligence techniques integrated with the Mahalanob distance method to embed the suggested “CNN-ThrMah” model. The dataset, which contains types of banknotes issued by the Central Bank of Iraq, was collected using digital scanning supplied by a high-resolution camera to achieve high accuracy. Then, the “CNN-ThrMah” model was built and trained on this data, using the optimizer “AdamW” to achieve a high level of accuracy in detecting the types of currencies for the tested data that the model had not seen. While a Mahalanobis-distance method is used to prevent the model from overfitting when generalizing in the real world. This model achieves high accuracy for all detections of all positive samples of Iraqi currencies and negative samples of non-currency items that contain currency from other countries

Author Biography

Shymaa Akram Hantoush, Middle Technical University, Continuous Education Center, Baghdad, Iraq

I have been teaching at the Continuing Education Center of the Middle Technical University, specializing in Computer Science, since 2016.

References

1. Rajesh KS, Kalaiselvi S, Sathyanathan P, Sudha K, Kavitha G, Murugan S, editors. Smart Vending Machines: Improving Service Quality with Integrated Controllers and SVM Algorithm. 2024 6th ICEPE; 2024 20-22 June 2024. https://doi.org/10.1109/ICEPE63236.2024.10668878 .

2. Liu L, Cui J, Huan Y, Zou Z, Hu X, Zheng L. A Design of Smart Unmanned Vending Machine for New Retail Based on Binocular Camera and Machine Vision. IEEE Cons Electron Magaz. 2022;11(4):21-31. https://doi.org/10.1109/MCE.2021.3060722 .

3. Hasan MN. Predictive Maintenance Optimization for Smart Vending Machines Using IoT and Machine Learning. arXiv: 250702934. 2025. https://doi.org/10.48550/arXiv.2507.02934 .

4. Karthiga M, Rahayu SB, Suganya E, Sankarananth S, Sountharrajan S, Venkatesan K. Multimodal Fusion and Cutting-Edge AI-Based Smart Vending Machines for Electronic Component Management. IEEE Access. 2025;13:6029-53. https://doi.org/10.1109/ACCESS.2024.3523774 .

5. Meera N, Pujitha R, Tulasi M, Eswar I, Kumars Rm. Classification And Detection Of Fake Bank Notes Using Artificial Intelligence. IJCNIS. 2025;17(3):214-9. https://ijcnis.org/index.php/ijcnis/article/view/8106 .

6. Aseffa DT, Kalla H, Mishra S. Ethiopian banknote recognition using convolutional neural network and its prototype development using embedded platform. J Sensors. 2022;2022(1):4505089. https://doi.org/10.1155/2022/4505089 .

7. Nasayreh A, Jaradat AS, Gharaibeh H, Dawaghreh W, Al Mamlook RM, Alqudah Y, et al. Jordanian banknote data recognition: A CNN-based approach with attention mechanism. J King Saud Univ-Comp Inform Sci. 2024;36(4):102038. https://doi.org/10.1016/j.jksuci.2024.102038 .

8. Omeiza I, Ogunbiyi O, Ogundepo O, Otuoze A, Egbune D, Osunsanya K. A Method of Colour-Histogram Matching for Nigerian Paper Currency Notes Classification. JJEE. 2023. https://kwasuspace.kwasu.edu.ng/handle/123456789/2375 .

9. Bhatia A, Kedia V, Shroff A, Kumar M, Shah BK, editors. Fake currency detection with machine learning algorithm and image processing. 2021 5th ICICCS; 2021: IEEE. https://doi.org/10.1109/ICICCS51141.2021.9432274 .

10. Tasnim R, Pritha ST, Das A, Dey A, editors. Bangladeshi banknote recognition in real-time using convolutional neural network for visually impaired people. 2021 2nd ICREST; 2021: IEEE. https://doi.org/10.1109/ICREST51555.2021.9331182 .

11. Awad SR, Sharef BT, Salih AM, Malallah FL. Deep learning-based iraqi banknotes classification system for blind people. Eastern-European Journal of Enterprise Technologies. 2022;1(2):115. https://doi.org/10.15587/1729-4061.2022.248642 .

12. Muttreja R, Patel H, Goyal M, Kumar S, Singh A. Indian currency classification and counterfeit detection using deep learning and image processing approach. Advanced machine intelligence and signal processing: Springer; 2022. p. 801-13. https://doi.org/10.1007/978-981-19-0840-8_62 .

13. Nowshin H, Sikder J, Das UK, editors. A deep learning approach for detecting bangladeshi counterfeit currency. 5th ICO2022; 2022: Springer. https://doi.org/10.1007/978-3-031-19958-5_51.

14. Pham TD, Lee YW, Park C, Park KR. Deep learning-based detection of fake multinational banknotes in a cross-dataset environment utilizing smartphone cameras for assisting visually impaired individuals. Mathematics. 2022;10(9):1616. https://doi.org/10.3390/math10091616 .

15. Chandrappa S, Chandra Shekar P, Chaya P, Dharmanna L, Guruprasad M. Machine learning algorithms for identifying fake currencies. SN Comp Sci. 2023;4(4):368. https://doi.org/10.1007/s42979-023-01812-2 .

16. Easa HK, Saber AA, Hamid NK, Saber HA. Machine learning based approach for detection of fake banknotes using support vector machine. IJEECS. 2023;31(2):1016. http://doi.org/10.11591/ijeecs.v31.i2.pp1016-1022 .

17. Kumar CP, Yadav MG, Praneetha K, Rushikesh M, Shreya R, editors. Classification and detection of banknotes using machine learning. 2023 5th ICIRCA; 2023: IEEE. https://doi.org/10.1109/ICIRCA57980.2023.10220876 .

18. Bandu SCD, Kakileti M, Jannu Soloman SS, Baydeti N. Indian fake currency detection using image processing and machine learning. Int J Inform Technol. 2024;16(8):4953-66. https://doi.org/10.1007/s41870-024-02170-9 .

19. Hamed NaM, Al Azzo F. Develop a Robust System for Detecting Counterfeit Iraq Currencies Based on Deep Learning Techniques. J Comp Anal Appl. 2024;33(2). https://eudoxuspress.com/index.php/pub/article/view/416 .

20. Hamed Na, Al Azzo F. Advanced Methods for Identifying Counterfeit Currency: Using Deep Learning and Machine Learning. NTU-JET. 2024;3(3). https://doi.org/10.56286/ntujet.v3i3.944 .

21. Mohammed BK, Jabbar BK. Detection of Forgery in Iraqi Banknotes of Denominations (25 and 10) Thousand Dinar and Matching Them with the Original Currencies by Microscopic Detection. IJRIAS. 2025;10(5):492-8. https://doi.org/10.51584/IJRIAS.2025.100500045 .

22. Averly R, Chao W-L, editors. Unified out-of-distribution detection: A model-specific perspective. Proceedings of the IEEE/CVF-ICCV; 2023. https://doi.org/10.1109/ICCV51070.2023.00140 .

23. Techapanurak E, Suganuma M, Okatani T, editors. Hyperparameter-free out-of-distribution detection using cosine similarity. 15th ACCV; 2020. https://doi.org/10.1007/978-3-030-69538-5_4

24. Anthony H, Kamnitsas K, editors. On the use of mahalanobis distance for out-of-distribution detection with neural networks for medical imaging. 5th International Workshop, UNSURE; 2023: Springer. https://doi.org/10.1007/978-3-031-44336-7_14

25. Szeliski R. Computer vision: algorithms and applications: Springer Nature; 2022. https://books.google.iq/books?id=QptXEAAAQBAJ&pg=PR15&lr=&source=gbs_selected_pages&cad=1#v=onepage&q&f=false .