Transfer Learning-based Multi-Class Plant Disease Detection Using MobileNetV2 and EfficientNet-B0

Abstract

An early and precise identification of plant diseases helps to increase the efficiency of farming operations and minimize the economic losses associated with plant diseases. Nevertheless, applying deep learning models for plant disease identification in an agricultural setting poses certain difficulties due to high computational costs and insufficient edge device computing power. This paper presents a transfer learning-based framework for multi-class plant disease detection using MobileNetV2 and EfficientNet-B0 models. For the purpose of research, the PlantVillage dataset including potato, bell pepper, and tomato leaves was used. Images from this source underwent pre-processing that included resizing, normalizing, and augmenting images. Both transfer learning approach and fine-tuning helped to modify pre-trained CNNs for multi-class classification of different diseases affecting plants' leaves. Experiments have shown that EfficientNet-B0 model performed much better with accuracy of 95.7% and AUC of 0.98. Moreover, the proposed algorithm was exported as a TensorFlow Lite model and implemented in the Streamlit application for efficient edge deployment.

Plant phenotyping relevance

植物葉画像から病害を推定する深層学習フレームワークの開発・性能評価が研究の中心であり、植物の病害状態を直接推定するため、植物フェノタイピング手法として採録する。

Code and data availability

植物フェノタイピング解析を再現する公開資産であることを、入力本文と直接リンクから確認できなかったため保留しました。

No evidence-backed public reproduction asset is currently recorded.