Identification of Multiple Diseases in Apple Leaf Based on Optimized Lightweight Convolutional Neural Network.

Abstract

In this study, our aim is to find an effective method to solve the problem of disease similarity caused by multiple diseases occurring on the same leaf. This study proposes the use of an optimized RegNet model to identify seven common apple leaf diseases. We conducted comparisons and analyses on the impact of various factors, such as training methods, data expansion methods, optimizer selection, image background, and other factors, on model performance. The findings suggest that utilizing offline expansion and transfer learning to fine-tune all layer parameters can enhance the model's classification performance, while complex image backgrounds significantly influence model performance. Additionally, the optimized RegNet network model demonstrates good generalization ability for both datasets, achieving testing accuracies of 93.85% and 99.23%, respectively. These results highlight the potential of the optimized RegNet network model to achieve high-precision identification of different diseases on the same apple leaf under complex field backgrounds. This will be of great significance for intelligent disease identification in apple orchards in the future.

Code and data availability

The paper's apple leaf disease dataset fuses authors' field-collected images (not publicly deposited) with the public Kaggle Plant Pathology 2020 (FGVC7) dataset, which is directly used in this paper's phenotyping/classification measurements. No author analysis code, trained model checkpoints, or data deposit is stated