Detection of Potato Plant Disease from Leaf Images Using Deep Learning Models

Abstract

Potato is an important agricultural product that is consumed extensively throughout the world, but it is a plant that is sensitive to various diseases. Detecting diseases in potato plants at an early stage both prevents outbreaks of plant diseases and increases crop yield. For this purpose, 3 deep learning-based models were used in this study to detect and classify potato plant diseases. These models are 5-layer Convolutional Neural Network (CNN), EfficientNetB2 and ConvNeXtSmall transfer learning models, respectively. These models were trained and tested on the publicly available and widely used PlantVillage dataset. In this dataset, there are three classes: healthy (152), early blight disease (1000) and late blight disease (1000) and a total of 2152 images. The models were first trained on this dataset, and 5-layer CNN gave the best performance, with an average classification accuracy of 98.54% over 10 tests. Afterwards, data augmentation was performed to equalize the number of samples in the classes, and the EfficientNetB2 model gave the best performance on the augmented data with 99.89% accuracy. 99.33% performance was achieved with 5-layer CNN. CNN, designed as 5-layer, and other proposed methods classify potato plant diseases with high performances, and the results obtained are comparable to the literature.

Plant phenotyping relevance

ジャガイモ葉画像から病害状態を推定・分類する深層学習手法が研究の中心であり、植物病害表現型の画像ベース推定に該当する。

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.