Coin Identification for Coin Recognition Systems Based on Convolutional Neural Network and Transfer Learning
การระบุประเภทเหรียญกษาปณ์สำหรับระบบรู้จำเหรียญกษาปณ์โดยใช้เครือข่ายใยประสาทคอนโวลูชันและการเรียนรู้แบบถ่ายโอน
Keywords:
Coin Recognition, Deep Learning, Machine Learning, Transfer LearningAbstract
Coin collecting is a multifaceted hobby that appeals to individuals for various reasons, ranging from historical curiosity to investment opportunities to personal enjoyment and satisfaction. Moreover, information about different types of coins is important and necessary for the new generation of coin collectors. This research proposes the integration of deep learning technique incorporating with transfer learning for Thai coin recognition. By leveraging deep learning algorithms and transfer learning, this study can be applied to develop the coin information searching systems from coin images for Thai currency. The performance of the proposed method is evaluated and compared to other transfer learning models. The experimental results signify that the pre-trained MobileNet-v2 method can achieve the highest macro average f1-score of 100%, indicating that this approach is highly suitable for the Thai coin recognition system.
Downloads
References
Li Q, Ji L, Wu J. Coin image recognition based on K-nearest neighbor algorithm. In: ECITech 2022; The 2022 International Conference on Electrical, Control and Information Technology; 2022; Kunming, China.
He W, Wu H. Ancient and modern coin recognition using a novel rotation-invariant convolutional neural network. In: 2021 6th International Symposium on Computer and Information Processing Technology (ISCIPT); 2021; Changsha, China. p. 395-8.
Zainuddin NN, Azhari MSNBN, Hashim W, Alkahtani AA, Mustafa AS, Alkawsi G, et al. Malaysian coins recognition using machine learning methods. In: 2021 2nd International Conference on Artificial Intelligence and Data Sciences (AiDAS); 2021; Ipoh, Malaysia. p. 1-5.
Tajane AU, Patil JM, Shahane AS, Dhulekar PA, Gandhe ST, Phade GM. Deep learning based Indian currency coin recognition. In: 2018 International Conference on Advances in Communication and Computing Technology (ICACCT); 2018; Sangamner, India. p. 130-4.
Swain D, Rupapara V, Nour A, Satapathy S, Acharya B, Mishra S, et al. A deep learning framework for the classification of Brazilian coins. IEEE Access. 2023;11:109448-61.
Zhou J, Zhuang J, Li B, Zhou L. Research on underwater image recognition based on transfer learning. In: OCEANS 2022; 2022; Hampton Roads, VA, USA. p. 1-7.
Kondo K, Hasegawa T. Deep transfer learning using class augmentation for sensor-based human activity recognition. IEEE Sens Lett. 2022 Oct;6(10):1-4. Art no. 6003604.
Tai TT, Thanh DNH, Hung NQ. A dish recognition framework using transfer learning. IEEE Access. 2022;10:7793-9.
Goel P, Ganatra A. Handwritten Gujarati numerals classification based on deep convolution neural networks using transfer learning scenarios. IEEE Access. 2023;11:20202-15.
Li J, Luo X, Ma H, Zhao W. A hybrid deep transfer learning model with kernel metric for COVID-19 pneumonia classification using chest CT images. IEEE/ACM Trans Comput Biol Bioinform. 2023 Jul-Aug;20(4):2506-17.
Huang X. High resolution remote sensing image classification based on deep transfer learning and multi feature network. IEEE Access. 2023;11:110075-85.
Raza A, Munir K, Almutairi MS, Sehar R. Novel transfer learning based deep features for diagnosis of Down syndrome in children using facial images. IEEE Access. 2024;12:16386-96.
Capece N, Erra U, Ciliberto AV. Implementation of a coin recognition system for mobile devices with deep learning. In: 2016 12th International Conference on Signal-Image Technology & Internet-Based Systems (SITIS); 2016; Naples, Italy. p. 186-92.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2024 Advanced Science Journal
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
