Automated Estimation of Plant Leaf Disease Severity Using Classical Image Segmentation Techniques

Abstract

Aim: This study aimed to propose a computationally cost-effective method for automated estimation of plant leaf disease severity in resource-limited settings. Study Design: The performance of four image segmentation algorithms—global thresholding, adaptive thresholding, Otsu thresholding, and edge detection—was evaluated using nine curated images of disease-affected leaves from tomato, bell pepper, and potato plants. Each image was segmented into healthy and diseased regions, and quantitative metrics—including diseased pixel counts, percentage of affected area, healthy-to-diseased ratios, and computational time—were analyzed to assess algorithm performance. Results: The segmentation methods executed with near-instantaneous speed (0–0.001 seconds per image). Global and Otsu thresholding consistently demonstrated high segmentation accuracy, leading to reliable severity estimations. Adaptive thresholding tended to overestimate disease severity, while edge detection, despite providing precise lesion boundaries, significantly underestimated overall disease severity. Conclusion: Comparative analysis, supported by visual validation, suggests that Otsu thresholding, closely followed by global thresholding, is the most effective approach for leaf disease severity estimation, offering high accuracy with minimal computational overhead. These findings indicate that classical computer vision techniques can play a valuable role in supporting plant disease diagnostics and estimation in resource-constrained environments.