Identification of Apple Leaf Diseases Based on Deep Convolutional Neural Networks

TLDR

Apple leaf diseases such as Mosaic, Rust, Brown spot, and Alternaria are common, and early accurate diagnosis is essential for controlling infection and supporting industry health, yet current methods rely on complex preprocessing and often fail to achieve high recognition rates. This paper proposes an accurate identifying approach for apple leaf diseases based on deep convolutional neural networks. The authors generate synthetic pathological images and train a modified AlexNet‑based deep convolutional neural network on a 13,689‑image dataset to detect the four apple leaf diseases. The model achieves 97.62% accuracy, reduces parameters by 51,206,928, and improves accuracy by 10.83% with image generation, demonstrating faster convergence and robust disease control.

Abstract

Mosaic, Rust, Brown spot, and Alternaria leaf spot are the four common types of apple leaf diseases. Early diagnosis and accurate identification of apple leaf diseases can control the spread of infection and ensure the healthy development of the apple industry. The existing research uses complex image preprocessing and cannot guarantee high recognition rates for apple leaf diseases. This paper proposes an accurate identifying approach for apple leaf diseases based on deep convolutional neural networks. It includes generating sufficient pathological images and designing a novel architecture of a deep convolutional neural network based on AlexNet to detect apple leaf diseases. Using a dataset of 13,689 images of diseased apple leaves, the proposed deep convolutional neural network model is trained to identify the four common apple leaf diseases. Under the hold-out test set, the experimental results show that the proposed disease identification approach based on the convolutional neural network achieves an overall accuracy of 97.62%, the model parameters are reduced by 51,206,928 compared with those in the standard AlexNet model, and the accuracy of the proposed model with generated pathological images obtains an improvement of 10.83%. This research indicates that the proposed deep learning model provides a better solution in disease control for apple leaf diseases with high accuracy and a faster convergence rate, and that the image generation technique proposed in this paper can enhance the robustness of the convolutional neural network model.