การจำแนกชนิดอัญมณีเบื้องต้นผ่านโมบายแอปพลิเคชันด้วยกระบวนการเรียนรู้เชิงลึก (Preliminary Classification of Gemstone Types on Mobile Application using Deep Learning)
Main Article Content
บทคัดย่อ
A standard method for gemstone classification requires gemstone testing in the laboratory, which is a time-consuming and expensive process. Therefore, deep learning technologies are applied in image classification to facilitate the identification process. In this research work, the development of a gemstone classification model using deep learning and a mobile application for automatic gemstone classification is proposed so that untrained people can classify the gemstones. The process consisted of creating a convolutional neural network that can classify six gemstone types with similar characteristics (ruby, garnet, citrine, yellow sapphire, peridot, and green sapphire). Evaluation of the model showed that MobileNetV1 had the best performance, with accuracy of 95.00%, precision of 95.00%, and recall of 95.10%, making it suitable for use. Then use the model to develop a user interface in the form of a mobile application. Apply the application performance evaluation method with classification accuracy to the test dataset. The evaluation results showed that the application can classify images of gemstones efficiently and user-friendly, with an average accuracy of 82.50%. This demonstrated that the developed application can be used to examine and classify preliminary gemstone types.
Article Details
References
Abidalkareem, A. Abd, M. Ibrahim, A. Zhuang, H. Altaher, A. and Ali, A. (2020). Diabetic Retinopathy (DR) Severity Level Classification Using Multimodel Convolutional Neural Networks. The Proceedings of 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), July 2020 at Montreal, Canada, 1404-1407.
Abu-Jamie, T. and Abu-Naser, S. (2022). Classification of Sign-Language Using MobileNet- Deep Learning. International Journal of Academic Information Systems Research, 6 (7), 29-40.
Butploy, N. and Boonying, S. (2020). Classification of Benjapakee Buddha amulets image by deep learning. RMUTSB Academic Journal, 8(1), 100-111. (in Thai)
Chow, B. and Reyes-Aldasoro, C. (2022). Automatic Gemstone Classification Using Computer Vision. Minerals, 12(1), 1-21.
Department of International Trade Promotion. (2022). Information on the export situation of gems and jewelry products. [Online]. Retrieved Dec 1, 2022, from: https://www.ditp.go.th/ditp_web61/article_sub.php?cate=474&catetab=790&d=474 (in Thai)
Gem and Jewelry Institute of Thailand. (2022). Gem testing laboratory sdards jewelry and precious metals. [Online]. Retrieved Nov 12, 2022, from: https://www.gitsdard.com (in Thai)
Haritha, D. Swaroop, N., and Mounika, M. (2020). Prediction of COVID-19 Cases Using CNN with X-rays. The Proceedings of 5th International Conference on Computing, Communication and Security (ICCCS), October 2020 at Patna, India, 2020, 1-6.
Howard, A. Zhu, M. Chen, B. Kalenichenko, D. Wang, W., and Weyand, T. (2017). Mobilenets: Efficient convolutional neural networks for mobile vision applications. [Online]. Retrieved Mar 10, 2023, from: https://arxiv.org/abs/1704.04861
Imania, A., Yulinda, P., and Norfa, S. (2021). Implementation of Deep Learning Using Convolutional Neural Network Algorithm for Classification Rose Flower. Journal of Physice: Conference Series, 1842(1), 1-11.
Petagon, R., and Pantho, O. (2020). Drone for Detecting Forest Fires using Deep Learning Technique. Sripatum Review of Science and Technology, 12(1), 65-78. (in Thai)
Phimphisan, S., and Sriwiboon, N. (2020). Image Processing for Fundus Image Classification using Deep Learning. Journal of Information Science and Technology, 10(2), 19-25. (in Thai)
Phromrit, N., and Waijanya, S. (2021). Fundamental of Deep Learning in Practice. Bangkok: IDC Premier Publishing. (in Thai)
Promrangka, P., Wanthong, S., and Ratapoka, C. (2022). Mobile Application for Breeding Bird Classification using Deep Learning Technique. Journal of Information Science and Technology, 12(1), 37-46. (in Thai)
Sae-Lim, W., Wettayaprasit, W., and Aiyarak, P. (2019). Convolutional Neural Networks Using MobileNet for Skin Lesion Classification. The Proceedings of 16th International Joint Conference on Computer Science and Software Engineering (JCSSE), 10-12 July 2019 at Chonburi, Thailand, 242-247.
Saraubon, K. (2022). Learn AI: Deep Learning with Python. Bangkok: Intermedia Publishing. (in Thai)
Tropea, M., Fedele, G., Luca, R., Miriello, D., and Rango, F. (2022). Automatic Stone Classification through a CNN-Based Approach. Sensors, 22 (16), 1-19.
Xuan, Q., Fang, B., Liu, Y., Wang, J., Zhang, J., Zheng, Y., and Bao, G. (2018). Automatic Perl Classification Machine Based on a Multistream Convolutional Neural Network. IEEE Transactions on Industrial Electronics, 65 (8), 6538-6547.