DS-MENet for the classification of citrus disease

Xuyao Liu, Yaowen Hu, Guoxiong Zhou, Weiwei Cai, Mingfang He, Jialei Zhan, Yahui Hu, Liujun LiFrontiers in Plant Science 2022 · DOI

Abstract

Affected by various environmental factors, citrus frequently suffers from diseases during growth, posing significant obstacles to agricultural development. This paper proposes a novel method for identifying and classifying citrus diseases. We first design an image enhancement method, HFLF-MS, based on the MSRCR algorithm and Laplacian-optimized homomorphic filtering to highlight disease characteristics. Secondly, we introduce DS-MENet, a neural network based on the DenseNet-121 backbone. DS-MENet utilizes depthwise separable convolutions to reduce parameters, the ReMish activation function to improve robustness, and a multi-channel fusion (MCF) module to enhance feature extraction. Experimental results using 10-fold cross-validation show an average classification accuracy of 95.02% even on noisy datasets, demonstrating the system's feasibility for real-world agricultural applications.

Introduction

Citrus production is a vital component of global agriculture. However, the industry faces constant threats from diseases such as canker, scab, and anthracnose. Traditional manual inspection is labor-intensive and error-prone. While automated computer vision systems offer a solution, real-world field conditions—characterized by uneven lighting, motion blur, and complex backgrounds—often degrade image quality, making accurate classification difficult.

Visual examples of the five citrus categories classified by the system.

Furthermore, many citrus diseases exhibit high visual similarity, requiring models that can capture fine-grained features while remaining efficient enough for deployment on mobile devices.

Methodology

The proposed system follows a two-stage pipeline: image enhancement followed by deep learning-based classification.

The working principle of the DS-MENet system, including image enhancement and recognition stages.

HFLF-MS Image Enhancement

To address poor image quality, the authors developed the HFLF-MS (Homomorphic Filtering optimized by Laplacian - Multi-Scale Retinex with Color Restoration) method. This approach combines MSRCR for color restoration and brightness balancing with Laplacian-optimized homomorphic filtering to sharpen edges. This ensures that the subsequent neural network receives high-contrast images with clearly defined disease features.

The DS-MENet Architecture

The core classification model, DS-MENet, is built upon the DenseNet-121 architecture with three primary optimizations:

  1. Depthwise Separable Convolutions: By replacing standard convolutions, the model reduces its parameter count by approximately 85%, facilitating faster inference.
  2. ReMish Activation Function: A hybrid of ReLU and Mish, ReMish prevents "neuron death" by allowing a small gradient for negative values while maintaining the efficiency of ReLU for positive values.
  3. Multi-Channel Fusion (MCF): This module is integrated into the Dense Blocks to group feature maps and apply attention mechanisms, helping the model focus on the most discriminative disease characteristics.

Experimental Results

The model was trained and validated on a dataset of 9,258 images across five categories (Healthy, Canker, Scab, Black Spot, and Anthracnose).

  • Accuracy: DS-MENet achieved a peak average accuracy of 95.25%.
  • Robustness: To simulate real-world sensor noise, researchers added Gaussian and impulse noise to the test set. The model maintained a high accuracy of 95.02%, significantly outperforming standard architectures like ResNet50 and InceptionV4.
  • Generalization: The architecture also showed strong performance (94-96%) on non-agricultural datasets such as Stanford Cars and ImageNetDogs, indicating its effectiveness as a general feature extractor.

Conclusion

DS-MENet provides a robust and efficient solution for citrus disease classification in challenging environments. By combining sophisticated pre-processing with an optimized deep learning architecture, the system achieves high accuracy with low computational overhead. Future work will focus on expanding the dataset to include more varieties and optimizing the model for real-time mobile deployment to assist farmers directly in the field.

Summary updated

Abstract

Affected by various environmental factors, citrus will frequently suffer from diseases during the growth process, which has brought huge obstacles to the development of agriculture. This paper proposes a new method for identifying and classifying citrus diseases. Firstly, this paper designs an image enhancement method based on the MSRCR algorithm and homomorphic filtering algorithm optimized by Laplacian (HFLF-MS) to highlight the disease characteristics of citrus. Secondly, we designed a new neural network DS-MENet based on the DenseNet-121 backbone structure. In DS-MENet, the regular convolution in Dense Block is replaced with depthwise separable convolution, which reduces the network parameters. The ReMish activation function is used to alleviate the neuron death problem caused by the ReLU function and improve the robustness of the model. To further enhance the attention to citrus disease information and the ability to extract feature information, a multi-channel fusion backbone enhancement method (MCF) was designed in this work to process Dense Block. We use the 10-fold cross-validation method to conduct experiments. The average classification accuracy of DS-MENet on the dataset after adding noise can reach 95.02%. This shows that the method has good performance and has certain feasibility for the classification of citrus diseases in real life.
BibTeX
@inproceedings{liu2022ds,
  author = {Xuyao Liu and Yaowen Hu and Guoxiong Zhou and Weiwei Cai and Mingfang He and Jialei Zhan and Yahui Hu and Liujun Li},
  title = {{DS-MENet for the classification of citrus disease}},
  booktitle = {Frontiers in Plant Science},
  year = {2022},
  doi = {10.3389/fpls.2022.884464},
}
Figure