Diagnosis of Typical Apple Diseases: A Deep Learning Method Based on Multi-Scale Dense Classification Network.

Abstract

Disease has always been one of the main reasons for the decline of apple quality and yield, which directly harms the development of agricultural economy. Therefore, precise diagnosis of apple diseases and correct decision making are important measures to reduce agricultural losses and promote economic growth. In this paper, a novel Multi-scale Dense classification network is adopted to realize the diagnosis of 11 types of images, including healthy and diseased apple fruits and leaves. The diagnosis of different kinds of diseases and the same disease with different grades was accomplished. First of all, to solve the problem of insufficient images of anthracnose and ring rot, Cycle-GAN algorithm was applied to achieve dataset expansion on the basis of traditional image augmentation methods. Cycle-GAN learned the image characteristics of healthy apples and diseased apples to generate anthracnose and ring rot lesions on the surface of healthy apple fruits. The diseased apple images generated by Cycle-GAN were added to the training set, which improved the diagnosis performance compared with other traditional image augmentation methods. Subsequently, DenseNet and Multi-scale connection were adopted to establish two kinds of models, Multi-scale Dense Inception-V4 and Multi-scale Dense Inception-Resnet-V2, which facilitated the reuse of image features of the bottom layers in the classification neural networks. Both models accomplished the diagnosis of 11 different types of images. The classification accuracy was 94.31 and 94.74%, respectively, which exceeded DenseNet-121 network and reached the state-of-the-art level.

Plant phenotyping relevance

リンゴ葉・果実の病害画像と病害グレードを深層学習で診断する画像ベースの植物状態推定法が研究の中心であり、データ拡張、モデル構築、精度比較まで実施している。

Code and data availability

The paper's apple leaf disease images come from a public dataset (AI-Challenger Plant Disease Recognition on Gitee), explicitly cited with URL. The fruit images, Cycle-GAN generated images, and model code are not publicly deposited (data availability directs inquiries to authors), so only the public leaf image dataset,