Coffee Leaf Disease and Severity Prediction Using Deep Learning

• Published in: TENCON 2023 - 2023 IEEE Region 10 Conference (TENCON) pp. 1175 - 1180
• Main Authors: Chaubey, Harshit Kumar, Arelli, Siri, Raj, Aryan, Naik, Nenavath Srinivas
• Format: Conference Proceeding
• Language: English
• Published: IEEE 31-10-2023
• Subjects: Convolutional neural networks; Deep learning; Diseases; Industries; Measurement; Production; Training
• ISSN: 2159-3450
• DOI: 10.1109/TENCON58879.2023.10322425

Coffee production is a vital industry in many countries, but diseases affecting coffee leaves can lead to significant losses for farmers. To mitigate these losses, timely disease detection and accurate assessment of disease severity are crucial. This work proposes a deep learning approach for classifying coffee leaf diseases based on their severity levels. The proposed methodology involves several steps. Initially, U 2 Net removes the background from the coffee leaf images. Subsequently, the background-removed images are converted into BGR format to identify the diseased regions. DeepLabV3 is then trained to extract and mark the diseased portions of the leaves in red. Using these annotated images, various convolutional neural network (CNN) models, including VGG-16, Inception V3,and MobileNetV2, were trained to classify the diseases based on their severity levels. These models are carefully modified and fine-tuned with hyperparameters to achieve the best performance metrics. Upon model training, the modified MobileNetV2 model performs better than the other CNN models, achieving an impressive F1-score of 97.99%. This outcome highlights the effectiveness of this paper's approach in accurately classifying coffee leaf diseases according to their severity levels. The proposed methodology has significant implications for coffee farmers, enabling them to swiftly detect diseases and assess their severity, allowing for timely and appropriate actions. Furthermore, the findings indicate the superiority of the modified MobileNetV2 model in achieving high accuracy in disease severity classification. This research contributes to advancing deep learning techniques for agricultural applications, offering practical solutions for disease management in the coffee industry.