CLASSIFICATION OF RUPIAH CURRENCY IN THE FORM OF PAPER USING THE MOBILENETV3 LARGE METHOD

Anggito Karta Wijaya; Ando Zamhariro Royan

doi:10.52436/1.jutif.2025.6.1.2040

Anggito Karta Wijaya Information Systems Department, Faculty of Computer Science, Universitas Jember, Indonesia
Ando Zamhariro Royan Information Systems Department, Faculty of Computer Science, Universitas Jember, Indonesia

DOI: https://doi.org/10.52436/1.jutif.2025.6.1.2040

Keywords: Currency Classification, Computational Efficiency, Data Augmentation, Deep Learning, Image Processing, Indonesian Banknote, MobileNetV3 Large

Abstract

Money plays an important role in everyday life as a legal tender and a symbol of a country's economic strength. The ability to accurately classify rupiah banknotes has many practical applications such as in automated payment systems, currency exchange, and cash management. However, conventional classification approaches based on digital image processing and image processing techniques are often limited in terms of accuracy and computational efficiency, especially when dealing with a variety of banknote conditions such as wrinkles, stains, or damage. This research aims to propose a new approach by utilising the MobileNetV3 Large architecture, an efficient and lightweight deep learning model, to address the challenges of paper currency classification. The main objective is to improve classification accuracy while minimising computational resources. The dataset used consists of 2873 images of paper rupiah currency of various denominations and conditions from seven classes. These images were processed and trained using the MobileNetV3 Large model that has been customised for this classification task by applying various data augmentation techniques. Experimental results show that the proposed approach is able to achieve 100% classification accuracy on a test dataset with a relatively small model size so that it can be run efficiently on mobile devices or embedded systems. This research makes an important contribution to the development of accurate and efficient rupiah banknote classification techniques for various practical applications in the future.

Downloads

Download data is not yet available.

References

U. Hasanah and N. Purwanti, "Klasifikasi nilai pecahan uang kertas rupiah menggunakan metode deteksi tepi canny dan transformasi hough," Jurnal Informatika, vol. 11, no. 2, pp. 73-84, 2017.

A. Ratnawati, A. A. Zainal, and D. H. Widyantoro, "Klasifikasi Mata Uang Rupiah Kertas Menggunakan Convolutional Neural Network," Jurnal Informatika, vol. 7, no. 1, pp. 112-120, 2020, doi: 10.25139/inf.v7i1.2716.

A. P. Wibawa, H. A. Nugroho, M. H. Fauzy, and S. Al Faraby, "Indonesian Banknotes Recognition Using Convolutional Neural Networks," International Journal of Advanced Computer Science and Applications, vol. 10, no. 11, pp. 593-599, 2019, doi: 10.14569/IJACSA.2019.0101176.

G. Oyedotun, O. K. B. O, B. Awwalu, and J. Sanni, "Efficient Deep Learning Approach for Currency Recognition," International Journal of Computer Science and Network Security, vol. 21, no. 9, pp. 128-133, 2021.

M. Salmam, B. Riyanto, and E. Sutanta, "Penerapan Metode Convolutional Neural Network untuk Klasifikasi Mata Uang Kertas Rupiah," Jurnal Teknologi Informasi dan Ilmu Komputer, vol. 6, no. 5, pp. 537-544, 2019.

H. Sugiarto, D. Permanasari, and W. Jatmiko, "Mobile Application for Indonesian Banknotes Recognition Using Convolutional Neural Network," in International Seminar on Application for Technology of Information and Communication, 2020, pp. 267-272, doi: 10.1109/isatic50879.2020.9366826.

H. Situmeang, H. S. Purba, and H. Saragih, "Klasifikasi Mata Uang Kertas Rupiah Dengan Metode Convolutional Neural Network," Jurnal Teknologi Informasi, vol. 3, no. 2, pp. 182-188, 2019..

A. G. Howard et al., "MobileNets: Efficient convolutional neural networks for mobile vision applications," arXiv preprint arXiv:1704.04861, 2019.

M. Shaikh, N. A. Siddiqui, and A. R. Hasan, "Currency Recognition Using Convolutional Neural Network," International Journal of Computer Science and Engineering, vol. 8, no. 6, pp. 269-274, 2020, doi: 10.26438/ijcse/v8i6.269274.

A. Pramerdorfer et al., "Real-time deep learning-based currency recognition for automated cash handling," in Proceedings of the IEEE International Conference on Industrial Technology, 2022, pp. 398-403, doi: 10.1109/ICIT54555.2022.9934852.

B. A. A. A. Ni'am, "Identifikasi Nilai Nominal dan Keaslian Uang Kertas Rupiah Menggunakan Support Vector Machine," Undergraduate thesis, Universitas Islam Negeri Maulana Malik Ibrahim, 2013.

S. P. Sari and R. K. Devi, "Indonesian Banknote Recognition Using Deep Learning Approach," International Journal of Engineering and Technology, vol. 7, no. 4.15, pp. 207-210, 2018, doi: 10.14419/ijet.v7i4.15.22426.

S. M. Mohammadi, D. P. Dogra, and S. K. Meher, "Low-complexity and real-time banknote recognition using deep learning," Journal of Real-Time Image Processing, vol. 19, no. 1, pp. 247-266, 2022, doi: 10.1007/s11554-021-01093-3.

R. T. Wibowo et al., "Classification of Indonesian banknote using Convolutional Neural Network with Data Augmentation," Proc. Int. Conf. Electr. Eng. Informatics, vol. 1, no. 2021, pp. 81–87, 2021, doi: 10.1109/ICon-EEI51454.2021.9526906.

SR. M. Abdelaal, R. M. Ebied, E. M. Saad, and M. A. Hamza, "An accurate model for currency recognition using convolutional neural networks," Alexandria Engineering Journal, vol. 61, no. 6, pp. 4757-4769, 2022, doi: 10.1016/j.aej.2022.01.020.