Smart Diagnosis: Early Detection and Management of Plant Diseases

Abstract

Plant diseases threaten global food security and cause significant financial losses in agriculture. Early detection and precise diagnosis are critical for effective disease management. This study explores a novel approach to plant disease identification using the You Only Look Once (YOLOv12) algorithm combined with few-shot learning techniques. By leveraging a limited dataset, the model is trained to classify citrus plant leaf images into four categories: healthy, greening, black spot, and canker. The proposed system enhances disease detection efficiency, enabling farmers to take timely preventive measures. Our approach demonstrates the potential of few-shot learning in agricultural disease diagnosis, reducing the need for extensive labeled datasets while maintaining high accuracy.

Plant phenotyping relevance

柑橘葉画像から健全・greening・黒点病・かんきつかいよう病を分類するYOLOv12とfew-shot learning手法が研究の中心であり、植物病害状態の画像ベース推定に該当する。

Code and data availability

The paper's phenotyping inputs consist of the public PlantVillage leaf-image dataset (54,000+ images, 38 classes), explicitly named as the data used for the authors' few-shot disease-classification experiments. No author code, models, or supplementary deposits are mentioned, and no dataset URL is provided in the text,故