A Visually Impaired Mobile Application for Currency Recognition using MobileNetV2 CNN Architecture

Authors

  • Abraham Eseoghene Evwiekpaefe Department of Computer Science, Faculty of Military Science and Interdisciplinary Studies, Nigerian Defence Academy, Kaduna
  • Habila Isacha Department of Computer Science, Faculty of Military Science and Interdisciplinary Studies, Nigerian Defence Academy, Kaduna

DOI:

https://doi.org/10.33736/jcsi.8562.2025

Keywords:

Currency, Naira, Transfer learning, Deep learning, MobileNetV2, Visually Impaired

Abstract

There are at least 2.2 billion people with visual impairment globally of which almost half of these cases could have been addressed or prevented. Visual impairment has both personal and economic impacts on individuals. It impacts negatively on the quality of life, especially among adults. Many visually impaired persons in our society today face a lot of challenges and one of these challenges is object recognition. The visually impaired persons need assistance so they can perform monetary transactions without being cheated. This work is aimed at developing a model for the recognition of Nigerian naira notes for visually impaired persons. The model was trained using the concept of transfer learning with a trainable layer built on the MobileNetV2 convolutional neural network architecture pre-trained model using python programming language on Spyder anaconda IDE. The model was saved and converted to TensorFlow lite format which was deployed into a mobile application coded in the java programming language in android studio. A total of 3615 image datasets were collected, including N5, N10, N20, N50, N100, N200, N500, and N1000 denominations and some random images of objects that constitute the non-currency class for the training of the model. The collected data was divided into 80% for training and 20% for testing. The model achieved an accuracy of 98%.

References

Agasti, T., Burand, G., Wade, P., & Chitra, P. (2017, November). Fake currency detection using image processing. In IOP conference Series: materials Science and Engineering VIT University, Vellore, Tamil Nadu, India, 263(5), 1-8. IOP Publishing.

Akano, O. F. (2017). Vision health disparities and visual impairment in Nigeria: A review of the Nigerian National Blindness and Visual Impairment Survey. African Vision and Eye Health (AVEH): 76(1), 1-5. DOI:https://doi.org/10.4102/aveh.v76i1.345

Almu, A., & Muhammad, A. B. (2017). Image-Based Processing of Naira Currency Recognition. Annals, Computer Science Series: 15(1), 169-173.

Beheshti, N. (2022). Guide to Confusion Matrices and Classification Performance Metrics. Retrieved on 21st July, 2022 from https://towardsdatascience.com/guide-to-confusion-matrices-classification- performance metrics-a0ebfc08408e

Bhatia, A., Kedia, V., Shroff, A., Kumar, M., Shah, B. K., & Aryan. (2021). Fake Currency Detection with Machine Learning Algorithm and Image Processing. IEEE Proceedings of the Fifth International Conference on Intelligent Computing and Control Systems Vaigai College Engineering (VCE), Madurai, India: 755-760. DOI: 10.1109/ICICCS51141.2021.9432274.

Bhutada, S., Reddy, V. K., Chevva, A., Kadapala, S. & Gella, M. (2020). Currency Recognition Using Image Processing. International Journal of Scientific Development and Research (IJSDR), 5(4), 275-278.

Chakraborty, K., Basumatary, J., Dasgupta, D., Chandra J. K., Mukherjee, S. (2020). Recent Developments in Paper Currency Recognition System. International Journal of Research in Engineering and Technology (IJRET), 2(11). Available @ http://www.ijret.org222 ISSN: 2319-1163.

Chandankhede, P. & Kumar, A. (2019). Deep Learning Technique for Serving Visually Impaired Person. IEEE 9th International Conference on Emerging Trends in Engineering and Technology - Signal and Information Processing (ICETET-SIP-19) Nagpur, India: doi: 978-1-7281-3506-9/19, 1-6.

Chaubey, N., Parikh, S., & Amin, K. (Eds.). (2020). Computing Science, Communication, and Security. Communications in Computer and Information Science. doi:10.1007/978-981- 15-66486

Daniel, U. (2020). Nigeria Association of the Blind (NAB). Retrieved on 25th October, 2021 from https://www.nigeriaassociationoftheblind.org/

Durgadevi, S., Thirupurasundari, K., Komathi, C. & Mithun, S. B. (2020). Smart Machine Learning System for Blind Assistance. IEEE International Conference on Power, Energy, Control and Transmission Systems (ICPECTS): 1-4 DOI: 10.1109/ICPECTS49113.2020.9337031

Gamage, C. Y., Bogahawatte, J. R. M., Prasadika, U. K. T., & Sumathipala, S. (2020). DNN Based Currency Recognition System for Visually Impaired in Sinhala. IEEE 2nd International Conference on Advancements in Computing (ICAC) Colombo, Sir Lanka: 1, 422-427. DOI: 10.1109/ICAC51239.2020.9357295

Geekforgeeks. (2019). Unified Modeling Language (UML) | An Introduction. Retrieved from https://www.geeksforgeeks.org/unified-modeling-language-uml-introduction/ on 21st July, 2022.

Howard, A. G., Zhu, M., Chen, B., Kalenichenko, D., Wand, W., Weyand, T., Andreetto, M. & Adam, H. (2017). MobileNets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv: 1704.04861

Islam, M. T., Ahmad, M., & Bappy, A. S. (2021). Real-Time Bangladeshi Currency Recognition Using Faster R-CNN Approach for Visually Impaired People. In Communication and Intelligent Systems:147-156. Springer, Singapore.

Jafri, R., Abid, S. A., Arabnia, H. R. & Fatima S. (2013). Computer Vision-based Object Recognition for the Visually Impaired in an Indoors Environment: A Survey. Vis Comput Springer: DOI: 10.1007/s00371-013 0886-11 26

Legess, M. M. & Seid, H. W. (2020). Real-Time Ethiopian Currency Recognition for Visually Disable Peoples Using Convolutional Neural Network. Research square: 1-24. DOI: https://doi.org/10.21203/rs.3.rs125061/v1.

Linkon, A. H. M., Labib, M. M., Bappy, F. H., Sarker, S., Jannat, M. E., & Islam, M. S. (2020). Deep Learning Approach Combining Lightweight CNN Architecture with Transfer Learning: An Automatic Approach for the Detection and Recognition of Bangladeshi Banknotes. 2020 IEEE 11th International Conference on Electrical and Computer Engineering (ICECE) Buet, Dhaka, Bangladesh: 214-217.

Mallikarjuna, G. C. P., Hajare, R., & Pavan, P. S. S. (2021). Cognitive IoT System for visually impaired: Machine Learning Approach. Materials Today Proceedings. 1-7. doi: 10.1016/j.matpr.2021.03.666

Mathworks (2021). Convolutional Neural Network. Retrieved on 11th November, 2021 from https://www.mathworks.com/discovery/convolutional-neural-network-matlab.html

Naing, M., Nwe, N. O., & Thwe, M. O. (2019). Smart Blind Walking Stick using Arduino. International Journal of Trend in Scientific Research and Development (IJTSRD):3(5) August 2019 Available Online: www.ijtsrd.com e-ISSN: 2456 – 6470, 1156-1159.

Ng, S. C., Kwok, C. P., Chung, S. H., Leung, Y. Y., & Pang, H. S. (2020). An Intelligent BanknoteRecognition System by using Machine Learning with Assistive Technology for Visually Impaired People. 10th IEEE International Conference on Information Science and Technology (ICIST) Bath, London, and Plymouth, United Kingdom: 185-193. doi:10.1109/icist49303.2020.9202087

Ogbuju, E., Usman, W. O., Obilikwu, P. & Yemi-Peters, V. (2020). Deep Learning for Genuine Banknotes FUOYE. Journal of Pure and Applied Sciences (FJPAS), 5(1), 56-67. ISSN: 2616-1419.

Pascolini, D., & Mariotti, S. P. (2012). Global estimates of visual impairment: 2010. British Journal of Ophthalmology, 96(5), 614-618.

Pathak, A., & Aurelia, S. (2019). Mobile Based Smart Currency Detection System for Visually Impaired. Journal of Image Processing and Artificial Intelligence, 5(3), 1–4. http://doi.org/10.5281/zenodo.3354669.

Rajebhosale, S., Gujarathi, D., Nikam, S., Gogte, P., & Bahiram, N. (2017). Currency Recognition System Using Image Processing. International Research Journal of Engineering and Technology (IRJET), 4(3), 2559-2561.

Samant, S., Sonawane, S., Thorat, R., Shah, P. B., & Kulkarni, N. P. (2020). Currency Recognition System for Visually Impaired People. International Journal of Advance Scientific Research and Engineering Trends, 5(3), 31-35.

Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., & Chen, L. C. (2018). Mobilenetv2: Inverted Residuals and Linear Bottlenecks. Proceedings Of the IEEE Conference On Computer Vision And Pattern Recognition (Iccvpr) Salt Lake City, Ut, Usa, 4510-4520: 10.1109/Cvpr.2018.00474.

Saranya, K. S., Badhan, A. K., Alekhya, A., Madhumitha, C., & Charmika, V. D. (2020). Currency Counting for Visually Impaired Through Voice using Image Processing. International Journal of Engineering Research & Technology (IJERT), 9(5), 195-199.

Sarfraz, M., Sargano, A.B., & UI Haq, N. (2019). An Intelligent System for Paper Currency Verification using Support Vector Machines. Scientia Iranica, 26(1) (Special Issue on: Socio-Cognitive Engineering), 59-71: doi: 10.24200/sci.2018.21194

Simske, S. (2019). Meta-analytics: consensus approaches and system patterns for data analysis. Morgan Kaufmann.

Sindhu, R. & Varma, P. (2020). Currency Recognition System Using Image Processing. International Journal of Scientific & Engineering Research, 11( 4), 1595-1601.

Tasnim, R., Pritha, S. T., Das, A., & Dey, A. (2021). Bangladeshi Banknote Recognition in Real-time using Convolutional Neural Network for Visually Impaired People. 2021 IEEE 2nd international Conference on Robotics, Electrical and Signal Processing Techniques (ICREST) American International University, Dhaka, Bangladesh: 388-393.

Veeramsetty, V., Singal, G., & Bidal, T. (2020). Coinnet: platform independent application to recognize Indian currency notes using deep learning techniques. Multimedia tools and applications, 79, 22569-22594

WHO. (14 October, 2021). Blindness and vision impairment. Retrieved on 25th October, 2021 from https://www.who.int/news-room/fact-sheets/detail/blindness-and-visual-impairment

Yadav, S., Ali, Z., & Gautam, K. S. (2020). Currency Detection for Visually Impaired. Journal of Emerging Technologies and Innovative Research (JETIR), 7(5), 999-1002. www.jetir.org (ISSN-2349-5162)

Zhang, Q. (2018). Currency Recognition Using Deep Learning. A thesis submitted to the Auckland University of Technology in partial fulfilment of the requirements for degree of Master of Computer and Information Sciences (MCIS): I-95.

Zhu, W., Braun, B., Chiang, L. H., & Romagnoli, J. A. (2021). Investigation of transfer learning for image classification and impact on training sample size. Chemometrics and Intelligent Laboratory Systems: An International Journal Sponsored by the Chemometrics Society, 211(104269), 104269. doi:10.1016/j.chemolab.2021.104269

Downloads

Published

2025-03-10

How to Cite

Evwiekpaefe, A. E., & Isacha, H. (2025). A Visually Impaired Mobile Application for Currency Recognition using MobileNetV2 CNN Architecture. Journal of Computing and Social Informatics, 4(1), 26–42. https://doi.org/10.33736/jcsi.8562.2025