Enhanced YOLOv8-ECCI Algorithm for High-Precision Detection of Purple Spot Disease in Soybeans.

Abstract

Seed-level disease detection in soybeans presents significant challenges, including small-sample limitations, spectral interference, and dense occlusions, which are less pronounced in leaf-level analysis. To overcome these obstacles, we propose YOLOv8-ECCI, an enhanced algorithm based on YOLOv8 for high-precision identification of purple spot disease directly on soybean seeds. Experimental results demonstrate that YOLOv8-ECCI substantially outperforms the baseline YOLOv8n model, achieving significant gains of +5.7% precision, +6.5% recall, +8.0% mAP@0.5, and +7.1% mAP@0.5:0.95. Crucially, the model exhibits superior generalization capability, validated through rigorous cross-dataset testing on the African Wildlife dataset, where it surpasses conventional methods by +6.0% precision and +2.9% mAP@0.5. These results confirm that YOLOv8-ECCI effectively addresses the critical challenges in seed-level pathology, providing a robust and accurate solution for practical in-field agricultural disease detection and quality control.

Plant phenotyping relevance

大豆種子の病徴を画像から検出するYOLOv8改良手法の開発と、ベースラインおよびクロスデータセットによる技術検証が中心である。

Code and data availability

The paper describes a custom soybean purple spot image dataset (164 images collected at Yangjiang Customs, augmented to 900) and a YOLOv8-ECCI model, but no blocks contain any data or code availability statement, public repository, DOI, or URL for the dataset, annotations, or analysis code. The African Wildlife dataset

No evidence-backed public reproduction asset is currently recorded.