A Comparative Study of Convolutional Neural Network based Transfer Learning Models for Plant Disease Detection

Abstract

Background: Plant diseases significantly threaten global food security, reducing potential harvests and sometimes causing total crop failure. Traditional detection methods, which rely on manual inspection and laboratory testing, are time-consuming, costly and prone to human error. Methods: To address these challenges, this study applies transfer learning techniques using deep convolutional neural networks for accurate and efficient plant disease detection. A comparative analysis of nine pretrained models, VGG16, VGG19, ResNet50, ResNet101V2, MobileNetV2, InceptionV3, DenseNet121, InceptionResNetV2 and Xception was conducted on the PlantVillage dataset, focusing on apple, potato and peach leaf images. Result: Results show that DenseNet121 and ResNet101V2 achieved the highest accuracy, particularly for potato leaves with 98.5%, while MobileNetV2 also performed well with up to 99% accuracy for apple and peach leaves. The study demonstrates that transfer learning effectively enhances plant disease classification, enabling faster, more reliable and resource efficient detection for precision agriculture.

Plant phenotyping relevance

植物葉画像から病害状態を推定する深層学習手法を比較評価しており、病害表現型の取得・分類が研究の中心である。

Code and data availability

The paper uses the public PlantVillage dataset from Kaggle, but this is a generic third-party dataset rather than a paper-specific asset. No author analysis code, trained model checkpoints, or data deposits with availability statements or URLs are mentioned.

No evidence-backed public reproduction asset is currently recorded.