Improving Image-Based Plant Disease Classification With Generative Adversarial Network Under Limited Training Set.

Abstract

Traditionally, plant disease recognition has mainly been done visually by human. It is often biased, time-consuming, and laborious. Machine learning methods based on plant leave images have been proposed to improve the disease recognition process. Convolutional neural networks (CNNs) have been adopted and proven to be very effective. Despite the good classification accuracy achieved by CNNs, the issue of limited training data remains. In most cases, the training dataset is often small due to significant effort in data collection and annotation. In this case, CNN methods tend to have the overfitting problem. In this paper, Wasserstein generative adversarial network with gradient penalty (WGAN-GP) is combined with label smoothing regularization (LSR) to improve the prediction accuracy and address the overfitting problem under limited training data. Experiments show that the proposed WGAN-GP enhanced classification method can improve the overall classification accuracy of plant diseases by 24.4% as compared to 20.2% using classic data augmentation and 22% using synthetic samples without LSR.

Plant phenotyping relevance

植物葉画像から病害状態を分類するGANベースの画像解析手法を開発・比較評価しており、病害フェノタイピング手法が研究の中心である。

Code and data availability

The paper analyzes two public plant disease image datasets (Kaggle plantdisease and PlantVillage raw color images) and provides authors' Python code for data processing and model training on GitHub.