Deep Learning-Based Detection of Early Blight in Potato Leaves Using CNN Architectures

Abstract

Early blight, caused by the fungus Alternaria solani, is a prevalent disease in potato crops that severely impacts yield and quality. Traditional detection methods are time-consuming, require expert knowledge, and depend on laboratory facilities. This study aims to develop an efficient and automated approach for detecting early blight in potato leaves using deep learning techniques. A deep learning-based software solution was created, utilizing a convolutional neural network (CNN) trained on a large, annotated dataset of potato leaf images showing various disease symptoms. Five widely used CNN architectures (ResNet, NasNet, MobileNet, VGG16, InceptionNet) were implemented and compared within a consistent MATLAB environment. The comparative analysis revealed differences in model performance, offering valuable insights into the suitability of each architecture for real-time disease detection on different devices. The study demonstrates that CNN-based models can effectively and automatically detect early blight in potato leaves, with certain architectures offering better adaptability and accuracy for practical, field-level applications.

Plant phenotyping relevance

ジャガイモ葉の病徴を画像から検出するCNNソフトウェアを開発し、複数モデルを比較評価しており、植物病害状態の画像ベース表現型取得が中心である。

Code and data availability

公開状態または取得可能な本文経路を確認できませんでした。

No evidence-backed public reproduction asset is currently recorded.