Integrating advanced deep learning techniques for enhanced detection and classification of citrus leaf and fruit diseases.

Abstract

In this study, we evaluate the performance of four deep learning models, EfficientNetB0, ResNet50, DenseNet121, and InceptionV3, for the classification of citrus diseases from images. Extensive experiments were conducted on a dataset of 759 images distributed across 9 disease classes, including Black spot, Canker, Greening, Scab, Melanose, and healthy examples of fruits and leaves. Both InceptionV3 and DenseNet121 achieved a test accuracy of 99.12%, with a macro average F1-score of approximately 0.986 and a weighted average F1-score of 0.991, indicating exceptional performance in terms of precision and recall across the majority of the classes. ResNet50 and EfficientNetB0 attained test accuracies of 84.58% and 80.18%, respectively, reflecting moderate performance in comparison. These research results underscore the promise of modern convolutional neural networks for accurate and timely detection of citrus diseases, thereby providing effective tools for farmers and agricultural professionals to implement proactive disease management, reduce crop losses, and improve yield quality.

Plant phenotyping relevance

柑橘の葉・果実画像から病害状態を分類する深層学習手法を複数モデルで比較評価しており、植物病害表現型の取得・分類が研究の中心である。

Code and data availability

The paper describes a 759-image citrus disease dataset and four fine-tuned CNN models, but the supplied blocks contain no public dataset deposit, no code availability statement, no repository URL, and no trained model release. Only a contact-for-materials statement is present.

No evidence-backed public reproduction asset is currently recorded.