Image Classification of Green Arabica Coffee Using Transformer-Based Architecture

Image Classification of Green Arabica Coffee Using Transformer-Based Architecture
  IJETT-book-cover           
  
© 2024 by IJETT Journal
Volume-72 Issue-6
Year of Publication : 2024
Author : Maharani Nurul Izza, Gede Putra Kusuma
DOI : 10.14445/22315381/IJETT-V72I6P128

How to Cite?

Maharani Nurul Izza, Gede Putra Kusuma, "Image Classification of Green Arabica Coffee Using Transformer-Based Architecture," International Journal of Engineering Trends and Technology, vol. 72, no. 6, pp. 304-314, 2024. Crossref, https://doi.org/10.14445/22315381/IJETT-V72I6P128

Abstract
Indonesia is the second-largest producer of coffee, yet many still rely on manual classification methods for bean sorting. This manual approach is prone to human error and can lead to significant economic disadvantages. While numerous studies have aimed to classify coffee beans, none have utilized a compact dataset of Indonesian Arabica coffee beans employing a transformer-based architecture solution. Therefore, this paper proposes an evaluation and optimization of a deep learning model for classifying green Arabica coffee using transformer-based architectures. The transformer models utilized include Vision Transformer (ViT), Data Efficient in Transformer (DeiT), and Swin Transformer. Our research demonstrates the highest accuracy on the test data, with 84.75% using Swin Transformer, 82.25% using ViT, and 81.12% using DeiT. These accuracies represent improvements over previous baseline studies.

Keywords
Deep learning, Data efficient in transformer, Swin transformer, Transformer model, Vision transformer.

References
[1] Coffee Report and Outlook April 2023 - ICO, International Coffee Organization, pp. 1-39, 2023. [Online]. Available: https://icocoffee.org/documents/cy2022-23/Coffee_Report_and_Outlook_April_2023_-_ICO.pdf
[2] Alifya Febriana et al., “USK-COFFEE Dataset: A Multi-Class Green Arabica Coffee Bean Dataset for Deep Learning,” 2022 IEEE International Conference on Cybernetics and Computational Intelligence (CyberneticsCom), Malang, Indonesia, pp. 469-4736, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[3] Yudhi Adhitya et al., “Feature Extraction for Cocoa Bean Digital Image Classification Prediction for Smart Farming Application,” Agronomy, vol. 10, no. 11, pp. 1-16, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[4] Nurun Najmi Amanina, and Galuh Wilujeng Saraswati, “Classification of Arabica Coffee Green Beans Using Digital Image Processing Using the K-Nearest Neighbor Method,” Journal of Applied Intelligent System, vol. 7, no. 2, pp. 111-119, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[5] Robby Janandi, and Tjeng Wawan Cenggoro, “An Implementation of Convolutional Neural Network for Coffee Beans Quality Classification in a Mobile Information System,” 2020 International Conference on Information Management and Technology (ICIMTech), Bandung, Indonesia, pp. 218-222, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[6] Igor R. Fermo et al., “Development of A Low-Cost Digital Image Processing System for Oranges Selection Using Hopfield Networks,” Food and Bioproducts Processing, vol. 125, pp. 181-192, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[7] H.L. Gope, and H. Fukai, “Peaberry and Normal Coffee Bean Classification using CNN, SVM, and KNN: Their Implementation in and The Limitations of Raspberry Pi 3,” AIMS Agriculture and Food, vol. 7, no. 1, pp. 149-167, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[8] Alexey Dosovitskiy et al., “An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale,” arXiv, pp. 1-22, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[9] Hugo Touvron et al., “Training Data-Efficient Image Transformers & Distillation through Attention,” Proceedings of the 38th International Conference on Machine Learning, vol. 139, pp. 10347-10357, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[10] Ze Liu et al., “Swin Transformer: Hierarchical Vision Transformer Using Shifted Windows,” 2021 IEEE/CVF International Conference on Computer Vision (ICCV), Montreal, QC, Canada, pp. 9992-10002, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[11] Xilu Wang et al., “Recent Advances in Bayesian Optimization,” ACM Computing Surveys, vol. 55, no. 13s, pp. 1-36, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[12] Edwin R. Arboleda, Arnel C. Fajardo, and Ruji P. Medina, “Classification of Coffee Bean Species using Image Processing, Artificial Neural Network and K Nearest Neighbors,” 2018 IEEE International Conference on Innovative Research and Development (ICIRD), Bangkok, Thailand, pp. 1-5, 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[13] Mila Jumarlis, Mirfan Mirfan, and Abdul Rachman Manga, “Classification of Coffee Bean Defects Using Gray-Level Co-Occurrence Matrix and K-Nearest Neighbor,” ILKOM Jurnal Ilmiah, vol. 14, no. 1, pp. 1-9, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[14] Nelly Oktavia Adiwijaya et al., “The Quality of Coffee Bean Classification System Based on Color by Using K-Nearest Neighbor Method,” Journal of Physics: Conference Series, vol. 2157, pp. 1-8, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[15] Hira Lal Gope, and Hidekazu Fukai, “Normal and Peaberry Coffee Beans Classification from Green Coffee Bean Images Using Convolutional Neural Networks and Support Vector Machine,” International Journal of Computer and Information Engineering, vol. 14, no. 6, pp. 189-196, 2020.
[Google Scholar] [Publisher Link]