Artificial intelligence-based solutions for coffee leaf disease classification

• Published in: IOP conference series. Earth and environmental science Vol. 1278; no. 1; pp. 12004 - 12010
• Main Authors: Pham, Tri Cong, Nguyen, Van Duy, Le, Chi Hieu, Packianather, Michael, Hoang, Van-Dung
• Format: Journal Article
• Language: English
• Published: Bristol IOP Publishing 01.12.2023
• Subjects: Agricultural economics; Algorithms; Artificial intelligence; Artificial neural networks; Automation; Beverages; Classification; Coffee; Computer vision; Deep learning; Disease control; Disease detection; Leaves; Machine learning; Model accuracy; Neural networks; Pest control; Plant diseases; Training
• ISSN: 1755-1307; 1755-1315
• DOI: 10.1088/1755-1315/1278/1/012004

Abstract Coffee is one of the most widely consumed beverages and the quantity and quality of coffee beans depend significantly on the health and condition of coffee plants, particularly their leaves. The automation of coffee leaf disease classification using AI is an essential need, providing not only economic benefits but also contributing to environmental conservation and creating better conditions for sustainable coffee cultivation. Through the application of AI, early disease detection is facilitated, thereby reducing pest and disease control costs, minimizing crop losses, increasing coffee productivity and product quality, and promoting environmental preservation. Many studies have proposed AI algorithms for coffee disease classification. However, numerous algorithms employ classical algorithms, while some utilize deep learning, the current state-of-the-art in computer vision. The challenge lies in the fact that when using deep learning, a substantial amount of data is required for training. The design of deep learning architectures to enhance model accuracy while still working with a small training dataset remains an area of ongoing research. In this study, we propose deep learning-based method for coffee leaf disease classification. We propose the combination of different deep convolutional neural networks to further improve overall classification performance. Early and late fusion have been conducted to evaluate the effectiveness of the pre-trained model. Our experimental results demonstrate that the ensemble method outperforms single-model approaches, achieving high accuracy and precision in BRACOL coffee disease leaf.