SAM-Based Leaf Segmentation with Morphological Quality Assessment for Enhanced Plant Disease Detection

Abstract

Plant diseases threaten global food security, yet traditional visual inspection often fails to detect early-stage symptoms critical for timely intervention. While deep learning models have shown promise for automated disease detection, their performance often degrades in realistic field conditions. This study investigates whether data-centric preprocessing improves apple leaf disease detection. We present the first systematic evaluation of the Segment Anything Model (SAM) combined with morphological quality assessment for leaf segmentation, compared against whole-image classification using the Plant-Pathology FGVC7 dataset (3,642 apple orchard images). To ensure segmentation reliability, we introduce a five-metric morphological framework (area ratio, aspect ratio, spatial coverage, centroid proximity, border penalty). Experiments with ResNet-18 under 3-fold cross-validation reveal class-specific effects: SAM improves F1 by 3.0% for the minority multiple diseases class, but decreases by$1. 4 {\%}$for healthy leaves where contextual cues aid detection. Rust and scab remain stable above 95% F1, reflecting their distinctive visual signatures. GradCAM ++ confirms that preprocessing redirects attention toward diseaserelevant regions, particularly in complex multiple-disease cases. Overall, these findings show that adaptive preprocessing, rather than universal background removal, offers practical benefits for precision agriculture.

Plant phenotyping relevance

SAMによる葉画像セグメンテーションと形態学的品質評価を中心に、植物病害検出への有効性を体系的に検証しているため、植物表現型取得・抽出手法として収録する。

Code and data availability

公開本文の所在を確認できませんでした。非公開または購読が必要な可能性があります。

No evidence-backed public reproduction asset is currently recorded.