CASM-AMFMNet: A Network Based on Coordinate Attention Shuffle Mechanism and Asymmetric Multi-Scale Fusion Module for Classification of Grape Leaf Diseases

Jiayu Suo, Jialei Zhan, Guoxiong Zhou, Aibin Chen, Yaowen Hu, Weiqi Huang, Weiwei Cai, Yahui Hu, Liujun LiFrontiers in Plant Science 2022 · DOI

Abstract

Grape disease is a significant contributory factor to the decline in grape yield, typically affecting the leaves first. Efficient identification of grape leaf diseases remains a critical unmet need. To mitigate background interference in grape leaf feature extraction and improve the ability to extract small disease spots, we developed a novel method for disease recognition and classification. First, Gaussian filters Sobel smooth de-noising Laplace operator (GSSL) was employed to reduce image noise and enhance texture. A novel network designated coordinated attention shuffle mechanism-asymmetric multi-scale fusion module net (CASM-AMFMNet) was subsequently applied. CoAtNet was employed as the network backbone. The CASM-AMFMNet was further utilized to capture and target grape leaf disease areas, reducing background interference. Finally, an Asymmetric multi-scale fusion module (AMFM) was employed to extract multi-scale features from small disease spots. Experimental results showed that CASM-AMFMNet achieved an accuracy of 95.95%, F1 score of 95.78%, and mAP of 90.27%.

Introduction

Grape cultivation is a global industry, but yield is frequently threatened by fungal and bacterial diseases that manifest first on leaves. While computer vision offers a solution for automated monitoring, three major hurdles remain: image quality issues in real-world photos, background interference from vineyard environments (soil, branches, shadows), and scale variance where early-stage disease spots are microscopic and difficult for standard convolutional neural networks (CNNs) to detect after multiple layers of downsampling.

Methodology

The proposed CASM-AMFMNet architecture utilizes a three-stage pipeline to address these challenges, moving from raw image acquisition through specialized preprocessing to final classification.

Figure 1: The working principle diagram of the CASM-AMFMNet system, illustrating the flow from image acquisition to preprocessing and final recognition.

GSSL Preprocessing

The Gaussian filters Sobel smooth de-noising Laplace operator (GSSL) algorithm grayscales the image, applies high-pass filtering and Sobel operators to create a mask, and uses a Laplace operator to sharpen textures. This ensures the "veined" texture of the leaf is prominent while noise is suppressed.

Network Architecture

  • Backbone (CoAtNet): The model uses CoAtNet, which hybridizes local feature extraction of ConvNets with global modeling capabilities of Transformers, alleviating gradient explosion issues.
  • CASM (Coordinate Attention Shuffle Mechanism): Unlike standard attention modules, CASM embeds positional data along two spatial directions. It uses group convolutions and a "channel shuffle" to integrate feature information across channels efficiently.
  • AMFM (Asymmetric Multi-Scale Fusion Module): To catch tiny spots, this module extracts features at multiple scales using Asymmetric Convolution Blocks (ACB). By replacing standard $3 \times 3$ kernels with $1 \times 3$ and $3 \times 1$ combinations, the model improves robustness to rotations while reducing parameters.

Dataset and Augmentation

The primary evaluation used a self-made grape leaf dataset containing 3,409 original images collected from the Tianlu vineyard in China and online sources.

Figure 2: Overview of the grape leaf disease categories and the dataset distribution before and after data augmentation.

The dataset includes five categories: Healthy, Black Rot, Black Measles, Leaf Blight, and Downy Mildew. To simulate various field conditions, the dataset was expanded to 15,824 images using vertical/horizontal mirroring, contrast adjustment, and perspective transformation.

Results and Discussion

The CASM-AMFMNet demonstrated superior performance across multiple metrics:

  • Accuracy: Achieved 95.95%, a 7.21% improvement over the base CoAtNet model.
  • Precision and mAP: Recorded a precision of 96.00% and a mean Average Precision (mAP) of 90.27%.
  • Efficiency: The optimized architecture reduced training time significantly, with a training batch taking 270 seconds compared to 586 seconds for the unoptimized model.

The model outperformed ten other state-of-the-art models, including YoloV4 and DICNN, particularly in identifying "Black Rot" and "Leaf Blight," which are often confused due to similar early-stage appearances. Key innovations like Switchable Normalization (SN) in the CASM module allowed the model to dynamically adjust to high variance in outdoor lighting.

Conclusion

CASM-AMFMNet provides a feasible scheme for deep learning to correctly recognize grape diseases during agricultural production. While highly effective, future work will focus on identifying "mixed" infections where a single leaf has multiple diseases and optimizing the model for mobile deployment to provide real-time diagnostic tools for farmers.

Summary updated

Abstract

Grape disease is a significant contributory factor to the decline in grape yield, typically affecting the leaves first. Efficient identification of grape leaf diseases remains a critical unmet need. To mitigate background interference in grape leaf feature extraction and improve the ability to extract small disease spots, by combining the characteristic features of grape leaf diseases, we developed a novel method for disease recognition and classification in this study. First, Gaussian filters Sobel smooth de-noising Laplace operator (GSSL) was employed to reduce image noise and enhance the texture of grape leaves. A novel network designated coordinated attention shuffle mechanism-asymmetric multi-scale fusion module net (CASM-AMFMNet) was subsequently applied for grape leaf disease identification. CoAtNet was employed as the network backbone to improve model learning and generalization capabilities, which alleviated the problem of gradient explosion to a certain extent. The CASM-AMFMNet was further utilized to capture and target grape leaf disease areas, therefore reducing background interference. Finally, Asymmetric multi-scale fusion module (AMFM) was employed to extract multi-scale features from small disease spots on grape leaves for accurate identification of small target diseases. The experimental results based on our self-made grape leaf image dataset showed that, compared to existing methods, CASM-AMFMNet achieved an accuracy of 95.95%, F1 score of 95.78%, and mAP of 90.27%. Overall, the model and methods proposed in this report could successfully identify different diseases of grape leaves and provide a feasible scheme for deep learning to correctly recognize grape diseases during agricultural production that may be used as a reference for other crops diseases.
BibTeX
@inproceedings{suo2022casm,
  author = {Jiayu Suo and Jialei Zhan and Guoxiong Zhou and Aibin Chen and Yaowen Hu and Weiqi Huang and Weiwei Cai and Yahui Hu and Liujun Li},
  title = {{CASM-AMFMNet: A Network Based on Coordinate Attention Shuffle Mechanism and Asymmetric Multi-Scale Fusion Module for Classification of Grape Leaf Diseases}},
  booktitle = {Frontiers in Plant Science},
  year = {2022},
  doi = {10.3389/fpls.2022.846767},
}
Figure