Thai Currency Classification Application for Visually Impaired Persons

Wiyada Yawai; Mongkol Saejia; Nuntiya Limsiroratana; Rujirawadee Thammasang

doi:10.59796/jcst.V14N3.2024.64

Authors

Wiyada Yawai Computer Science, Nakhon Ratchasima Rajabhat University, Nakhon Ratchasima 30000, Thailand
Mongkol Saejia Department of Electrical and Biomedical Engineering, Faculty of Engineering, Prince of Songkla University, Songkhla 90110, Thailand
Nuntiya Limsiroratana Computer Science, Nakhon Pathom Rajabhat University, Nakhon Pathom 73000, Thailand
Rujirawadee Thammasang Computer Science, Nakhon Pathom Rajabhat University, Nakhon Pathom 73000, Thailand

DOI:

https://doi.org/10.59796/jcst.V14N3.2024.64

Keywords:

Banknotes, coins, smart app, classification, currency, Thai banknote, Thai currency, mobile app

Abstract

This research presents an application designed to assist visually impaired individuals in identifying Thai banknotes and coins. The application utilizes image processing and machine learning techniques, specifically a Convolutional Neural Network with ResNet101 architecture, to accurately classify 11 types of Thai currency. It is designed for offline use on smartphones, providing real-time audio and text output to enhance accessibility and understanding for users with visual impairments. The dataset includes 2,593 images of Thai banknotes and coins, split into 80% for training and 20% for testing. The application employs the trained model to conduct real-world tests using a smartphone camera, testing with actual banknotes and coins, achieving an average accuracy of 92.73%.

References

Aseffa, D. T., Kalla, H., & Mishra, S. (2022). Ethiopian banknote recognition using convolutional neural network and its prototype development using embedded platform. Journal of Sensors, 2022(1), Article 4505089. https://doi.org/10.1155/2022/4505089

Bank of Thailand. (2023). Current Banknotes in Circulation. Retrieved April 19, 2024, from https://www.bot.or.th/en/our-roles/banknotes/History-and-Series-of-Banknote-And-Commemorative/current-series-of-banknotes.html

Huang, X., & Gai, S. (2020). Banknote classification based on convolutional neural network in quaternion wavelet domain. IEEE Access, 8, 162141-162148. https://doi.org/10.1109/ACCESS.2020.3021181

Jangir, H., Raghav, N., Kashyap, N., Tanwar, P., & Kumar, B. (2020, August 20 – 22). HOMER: Cryptography based Currency Detection System for Visually Impaired People [Conference presentation]. 2020 Third International Conference on Smart Systems and Inventive Technology (ICSSIT). Tirunelveli, India. https://doi.org/10.1109/ICSSIT48917.2020.9214204

Jayaswal, V. (2021). Performance Metrics: Confusion matrix, Precision, Recall, and F1 Score. Towards Data Science. Retrieved from https://towardsdatascience.com/performance-metrics-confusion-matrix-precision-recall-and-f1-score-a8fe076a2262

Joshi, R. C., Yadav, S., & Dutta, M. K. (2020, February 5-7). YOLO-v3 based currency detection and recognition system for visually impaired persons [Conference presentation]. 2020 International Conference on Contemporary Computing and Applications (IC3A). Lucknow, India. https://doi.org/10.1109/IC3A48958.2020.233314

Kalshetty, R., & Parveen, A. (2023). Abnormal event detection model using an improved ResNet101 in context aware surveillance system. Cognitive Computation and Systems, 5(2), 153-167. https://doi.org/10.1049/ccs2.12084

Kang, K., & Lee, C. (2016, July 13-15). Fake banknote detection using multispectral images [Conference presentation]. In 2016 7th International Conference on Information, Intelligence, Systems & Applications (IISA). Chalkidiki, Greece. https://doi.org/10.1109/IISA.2016.7785338

Kitagawa, R., Mochizuki, Y., Iizuka, S., Simo-Serra, E., Matsuki, H., Natori, N., & Ishikawa, H. (2017, May 8-12). Banknote Portrait Detection Using Convolutional Neural Network [Conference presentation]. 2017 Fifteenth IAPR International Conference on Machine Vision Applications (MVA). Nagoya University, Nagoya, Japan. https://doi.org/10.23919/MVA.2017.7986895

Kongprasert, T., & Chongstitvatana, P. (2019, October 30 – November 1). Parameters Learning of BPS M7 Banknote Processing Machine for Banknote Fitness Classification [Conference presentation]. 2019 23rd International Computer Science and Engineering Conference (ICSEC). Phuket, Thailand. https://doi.org/10.1109/ICSEC47112.2019.8974837

Lee, S., Choi, E., Baek, Y., & Lee, C. (2019). Morphology-Based Banknote Fitness Determination. IEEE Access, 7, 65460-65466. https://doi.org/10.1109/ACCESS.2019.2917514

Meshram, V., Thamkrongart, P., Patil, K., Chumchu, P., & Bhatlawande, S. (2020). Dataset of Indian and Thai Banknotes. IEEE Dataport. https://dx.doi.org/10.21227/cjb5-n039

Ng, S.-C., Kwok, C.-P., Chung, S.-H., Leung, Y.-Y., & Pang, H.-S. (2020, September 9-15). An Intelligent Banknote Recognition System by using Machine Learning with Assistive Technology for Visually Impaired People [Conference presentation]. 2020 10th International Conference on Information Science and Technology (ICIST). Bath, London, and Plymouth, UK. https://doi.org/10.1109/ICIST49303.2020.9202087

Padmanabhan, A., & Dubey, P. K. (2019). Confusion Matrix. Retrieved from https://devopedia.org/confusion-matrix

Park, C., Cho, S. W., Baek, N. R., Choi, J., & Park, K. R. (2020). Deep feature-based three-stage detection of banknotes and coins for assisting visually impaired people. IEEE Access, 8, 184598-184613. https://doi.org/10.1109/ACCESS.2020.3029526

Pham, T. D., Lee, D. E., & Park, K. R. (2017). Multi-national banknote classification based on visible-light line sensor and convolutional neural network. Sensors, 17(7), Article 1595. https://doi.org/10.3390/s17071595

Saha, S. (2018). A Comprehensive Guide to Convolutional Neural Networks — the ELI5 way. Retrieved April 15, 2024, from https://towardsdatascience.com/a-comprehensive-guide-to-convolutional-neural-networks-the-eli5-way-3bd2b1164a53

Sarker, M. F. R., Raju, M. I. M., Marouf, A. A., Hafiz, R., Hossain, S. A., & Khandker Protik, M. H. (2019, September 27-28). Real-time Bangladeshi Currency Detection System for Visually Impaired Person [Conference presentation]. 2019 International Conference on Bangla Speech and Language Processing (ICBSLP). https://doi.org/10.1109/ICBSLP47725.2019.201518

Sirikham, A., Chiracharit, W., & Chamnongthai, K. (2009, February 15-18). Banknote and coin speaker device for blind people [Conference presentation]. 11th International Conference on Advanced Communication Technology. Gangwon, Korea (South). https://ieeexplore.ieee.org/document/4809503

Sooruth, T., & Gwetu, M. V. (2018, August 6-7). Automatic South African Coin Recognition Through Visual Template Matching [Conference presentation]. 2018 International Conference on Advances in Big Data, Computing and Data Communication Systems (icABCD). Durban, South Africa. https://doi.org/10.1109/ICABCD.2018.8465460

Sun, W.-Z., Ma, Y., Yin, Z.-Y., Wang, J.-S., Gu, A., & Guo, F.-J. (2021, May 22-24). Banknote Dirty Degree Identification Method Based on Texture Features of Banknote Images and Multi-layer Support Vector Machines [Conference presentation]. 2021 33rd Chinese Control and Decision Conference (CCDC). Kunming, China. https://doi.org/10.1109/CCDC52312.2021.9601832

TensorFlow. (n.d.). TensorFlow Lite guide. Retrieved April 15, 2024, from https://www.tensorflow.org/lite/guide?hl=th

Thailand Circulation. Royal Thai Mint. (2024). Royal Thai Mint. Retrieved April 19, 2024, from https://www.royalthaimint.net/ewtadmin/ewt/mint_en/mobile_detail.php?cid=21&nid=302

Wang, C., Chen, Q., Shen, C., & Wang, X. (2021, December 17-19). Graph elements of banknotes of the Republic of China detection and recognition based on deep learning algorithm [Conference presentation]. 2021 IEEE 2nd International Conference on Information Technology, Big Data and Artificial Intelligence (ICIBA), Chongqing, China. https://doi.org/10.1109/ICIBA52610.2021.9688209

Zhou, S. (2018, July 6-8). A Kind of Automatic Banknote Sorting Device Based on Vision [Conference presentation]. 2018 International Conference on Information Systems and Computer Aided Education (ICISCAE). Changchun, China, July 6-8, 2018. https://doi.org/10.1109/ICISCAE.2018.8666909