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

被引:13
作者
Suo, Jiayu [1 ]
Zhan, Jialei [1 ]
Zhou, Guoxiong [1 ]
Chen, Aibin [1 ]
Hu, Yaowen [1 ]
Huang, Weiqi [1 ]
Cai, Weiwei [1 ]
Hu, Yahui [2 ]
Li, Liujun [3 ]
机构
[1] Cent South Univ Forestry & Technol, Coll Comp & Informat Engn, Changsha, Peoples R China
[2] Hunan Acad Agr Sci HNAAS, Plant Protect Res Inst, Changsha, Peoples R China
[3] Missouri Univ Sci & Technol, Dept Civil Architectural & Environm Engn, Rolla, MO USA
来源
FRONTIERS IN PLANT SCIENCE | 2022年 / 13卷
基金
中国国家自然科学基金;
关键词
CASM-AMFMNet; coordinate attention shuffle mechanism asymmetric; multi-scale fusion module; grape leaf diseases; GSSL; image enhancement; IMAGE; IDENTIFICATION;
D O I
10.3389/fpls.2022.846767
中图分类号
Q94 [植物学];
学科分类号
071001 ;
摘要
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.
引用
收藏
页数:22
相关论文
共 6 条
  • [1] AM-MSFF: A Pest Recognition Network Based on Attention Mechanism and Multi-Scale Feature Fusion
    Zhang, Meng
    Yang, Wenzhong
    Chen, Danny
    Fu, Chenghao
    Wei, Fuyuan
    ENTROPY, 2024, 26 (05)
  • [2] An automatic classification framework for identifying type of plant leaf diseases using multi-scale feature fusion-based adaptive deep network
    Nagachandrika, Bathula
    Prasath, R.
    Joe, I. R. Praveen
    BIOMEDICAL SIGNAL PROCESSING AND CONTROL, 2024, 95
  • [3] Heuristically Improvised rice disease classification framework based on adaptive segmentation with the fusion of LSTM layer into Multi-Scale Residual attention Network
    Mehzabeen, S. M.
    Gayathri, R.
    BIOMEDICAL SIGNAL PROCESSING AND CONTROL, 2025, 99
  • [4] Pyramid-attention based multi-scale feature fusion network for multispectral pan-sharpening
    Chi, Yang
    Li, Jinjiang
    Fan, Hui
    APPLIED INTELLIGENCE, 2022, 52 (05) : 5353 - 5365
  • [5] Multi-scale generative adversarial inpainting network based on cross-layer attention transfer mechanism
    Shao, Mingwen
    Zhang, Wentao
    Zuo, Wangmeng
    Meng, Deyu
    KNOWLEDGE-BASED SYSTEMS, 2020, 196 (196)
  • [6] Convolutional Neural Network-Vision Transformer Architecture with Gated Control Mechanism and Multi-Scale Fusion for Enhanced Pulmonary Disease Classification
    Chibuike, Okpala
    Yang, Xiaopeng
    DIAGNOSTICS, 2024, 14 (24)