Application of Artificial Intelligence in Quality Analysis and Weight Estimation of Green Coffee Beans
DOI:
https://doi.org/10.24311/jabes/2023.34.5.6Keywords:
Coffee classification, Weight estimates, CNN, Image processing, Artificial IntelligenceAbstract
Vietnam is the second largest country in the world in terms of coffee export volume, in order to maintain this achievement, the quality of green coffee beans plays a very important role. Coffee exporters need to control the quality of coffee from the stage of purchasing each consignment at the household to preliminarily processing at the factory and exporting. However, the quality control of green coffee requires expertise and is being done manually, so it takes time, effort and cost for the exporters. Therefore, the objective of this study is to build a process, design an algorithm to apply artificial intelligence (AI) to analyze the quality and estimate the weight (ULKL) of green coffee beans automatically and quickly and reduce costs. The study was carried out by collecting and labeling samples of coffee bean data according to 12 types of beans, training the model with Yolov5 in object recognition, OpenCV open-source image processing technology, CNN (Convolutional) algorithm Neural Networks) in image processing for classification and weight estimation of each type of coffee bean. The research results show that the applied algorithm models give highly reliable results, which can be applied in practice.
References
Đức Anh. (2021). 10 nước sản xuất cà phê lớn nhất thế giới, Việt Nam đứng thứ 2. Truy cập từ https://vneconomy.vn/10-nuoc-san-xuat-ca-phe-lon-nhat-the-gioi-viet-nam-dung-thu-2.htm
Everingham, M., Eslami, S. M. A., van Gool, L., Williams, C. K. I., Winn, J., & Zisserman, A. (2015). The pascal visual object classes challenge: A retrospective. International Journal of Computer Vision, 111(1), 98–136. doi: 10.1007/s11263-014-0733-5
Hà Mạnh Hùng, Trương Việt Hùng, Đinh Văn Thuật, & Vũ Quang Việt. (2020). Phương pháp xử lý hiện tượng mô hình quá khớp trong xây dựng mô hình học sâu để ước lượng khả năng chịu tải của giàn phi tuyến. Tạp chí Khoa học Công nghệ Xây dựng, 14(1V), 12–20. doi: 10.31814/stce.nuce2020-14(1V)-02
Huang, Y., Cheng, Y., Bapna, A., Firat, O., Chen, M. X., Chen, D., . . . Chen, Z. (2018). GPipe: Efficient training of giant neural networks using pipeline parallelism. Retrieved from https://arxiv.org/abs/1811.06965. doi: 10.48550/ARXIV.1811.06965
Huy, T. V. (2021). EfficientNet understanding. Retrieved from https://huytranvan2010.github.io/EfficientNet-Understanding/
Jumarlis, M., Mirfan, M., & Manga, A. (2022). Classification of Coffee Bean Defects Using Gray-Level Co-Occurrence Matrix and K-Nearest Neighbor. ILKOM Jurnal Ilmiah, 14, 1–9. doi: 10.33096/ilkom.v14i1.910.1-9
Keles, M. C., Salmanoglu, B., Guzel, M. S., Gursoy, B., & Bostanci, G. E. (2022). Evaluation of YOLO models with sliced inference for small object detection. Retrieved from https://arxiv.org/abs/2203.04799. doi: 10.48550/ARXIV.2203.04799
Lee, J. Y., & Jeong, Y. S. (2022). Prediction of defect coffee beans using CNN. Paper presented at the 2022 IEEE International Conference on Big Data and Smart Computing (BigComp).
Lin, T.-Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., . . . Zitnick, C. L. (2014). Microsoft COCO: Common objects in context. Lecture Notes in Computer Science (pp. 740–755). doi: 10.1007/978-3-319-10602-1_48
Luis, V. A. M., Quiñones, M. V. T., & Yumang, A. N. (2022). Classification of defects in robusta green coffee beans using YOLO. Paper presented at the 2022 IEEE International Conference on Artificial Intelligence in Engineering and Technology (IICAIET).
Piao, Y., Chen, A., & Shang, Z. (2019). Housing price prediction based on CNN. Paper presented at the 2019 9th International Conference on Information Science and Technology (ICIST).
Pinto, C., Furukawa, J., Fukai, H., & Tamura, S. (2017). Classification of Green coffee bean images basec on defect types using convolutional neural network (CNN). Paper presented at the 2017 International Conference on Advanced Informatics, Concepts, Theory, and Applications (ICAICTA).
Ren, S., He, K., Girshick, R., & Sun, J. (2015). Faster R-CNN: Towards real-time object detection with region proposal networks. doi: 10.48550/ARXIV.1506.01497
Tan, M., & Le, Q. V. (2019). EfficientNet: Rethinking model scaling for convolutional neural networks. doi:10.48550/ARXIV.1905.11946
Trần Thanh Điện, Thái Nhựt Thanh, & Nguyễn Thái Nghe. (2019). Giải pháp phân loại bài báo khoa học bằng kĩ thuật máy học. Tạp chí Khoa học Trường Đại học Cần Thơ, 55(4A), 29–37. doi: 10.22144/ctu.jvn.2019.093
Xu, R., Lin, H., Lu, K., Cao, L., & Liu, Y. (2021). A forest fire detection system based on ensemble learning. Forests, 12, 217. doi: 10.3390/f12020217
Zhang, B., Guo, N., Huang, J., Gu, B., & Zhou, J. (2020). Computer vision estimation of the volume and weight of apples by using 3D reconstruction and noncontact measuring methods. Journal of Sensors, 2020, 1–12. doi: 10.1155/2020/5053407
Downloads
Published
Issue
Section
License
Copyright (c) 2023 JOURNAL OF ASIAN BUSINESS AND ECONOMIC STUDIES
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
