Efficient deep learning-based tomato leaf disease detection through global and local feature fusion

被引:0
|
作者
Sun, Hao [1 ]
Fu, Rui [1 ]
Wang, Xuewei [1 ]
Wu, Yongtang [1 ]
Al-Absi, Mohammed Abdulhakim [2 ]
Cheng, Zhenqi [1 ]
Chen, Qian [3 ]
Sun, Yumei [1 ]
机构
[1] Weifang Univ Sci & Technol, Shandong Facil Hort Bioengn Res Ctr, Weifang 262700, Peoples R China
[2] Kyungdong Univ, Dept Smart Comp, 46 4 Gil, Giosung 24764, Gangwon Do, South Korea
[3] Sichuan Technol & Business Univ, Chengdu 611745, Sichuan, Peoples R China
来源
BMC PLANT BIOLOGY | 2025年 / 25卷 / 01期
关键词
Tomato disease detection; Local Feature Enhance Pyramid; Comprehensive Multi-Kernel Module; CSWinTransformer; Deep learning; TRANSFORMER;
D O I
10.1186/s12870-025-06247-w
中图分类号
Q94 [植物学];
学科分类号
071001 ;
摘要
In the context of intelligent agriculture, tomato cultivation involves complex environments, where leaf occlusion and small disease areas significantly impede the performance of tomato leaf disease detection models. To address these challenges, this study proposes an efficient Tomato Disease Detection Network (E-TomatoDet), which enhances tomato leaf disease detection effectiveness by integrating and amplifying global and local feature perception capabilities. First, CSWinTransformer (CSWinT) is integrated into the backbone of the detection network, substantially improving tomato leaf diseases' global feature-capturing capacity. Second, a Comprehensive Multi-Kernel Module (CMKM) is designed to effectively incorporate large, medium, and small local capturing branches to learn multi-scale local features of tomato leaf diseases. Moreover, the Local Feature Enhance Pyramid (LFEP) neck network is developed based on the CMKM module, which integrates multi-scale features across different detection layers to acquire more comprehensive local features of tomato leaf diseases, thereby significantly improving the detection performance of tomato leaf disease targets at various scales under complex backgrounds. Finally, the proposed model's effectiveness was validated on two datasets. Notably, on the tomato leaf disease dataset, E-TomatoDet improved the mean Average Precision (mAP50) by 4.7% compared to the baseline model, reaching 97.2% and surpassing the advanced real-time detection network YOLOv10s. This research provides an effective solution for efficiently detecting vegetable pests and disease issues.
引用
收藏
页数:13
相关论文
共 50 条
  • [1] Deep learning-based segmentation and classification of leaf images for detection of tomato plant disease
    Shoaib, Muhammad
    Hussain, Tariq
    Shah, Babar
    Ullah, Ihsan
    Shah, Sayyed Mudassar
    Ali, Farman
    Park, Sang Hyun
    FRONTIERS IN PLANT SCIENCE, 2022, 13
  • [2] A Lightweight Deep Learning-Based Model for Tomato Leaf Disease Classification
    Ullah, Naeem
    Khan, Javed Ali
    Almakdi, Sultan
    Alshehri, Mohammed S.
    Al Qathrady, Mimonah
    Aldakheel, Eman Abdullah
    Khafaga, Doaa Sami
    CMC-COMPUTERS MATERIALS & CONTINUA, 2023, 77 (03): : 3969 - 3992
  • [3] A Deep Learning-Based Approach in Classification and Validation of Tomato Leaf Disease
    Wagle, Shivali Amit
    Harikrishnan, R.
    TRAITEMENT DU SIGNAL, 2021, 38 (03) : 699 - 709
  • [4] Deep Learning-Based Object Detection Improvement for Tomato Disease
    Zhang, Yang
    Song, Chenglong
    Zhang, Dongwen
    IEEE ACCESS, 2020, 8 : 56607 - 56614
  • [5] Automated Image Capturing System for Deep Learning-based Tomato Plant Leaf Disease Detection and Recognition
    de Luna, Robert G.
    Dadios, Elmer P.
    Bandala, Argel A.
    PROCEEDINGS OF TENCON 2018 - 2018 IEEE REGION 10 CONFERENCE, 2018, : 1414 - 1419
  • [6] Deep Learning-Based Automated Feature Engineering for Rice Leaf Disease Prediction
    Das, Ankur
    Mallick, Chirantana
    Dutta, Soumi
    COMPUTATIONAL INTELLIGENCE IN PATTERN RECOGNITION, CIPR 2020, 2020, 1120 : 133 - 141
  • [7] Deep Learning-based Marine Target Detection Method with Multiple Feature Fusion
    Wang X.
    Wang Y.
    Chen X.
    Zang C.
    Cui G.
    Journal of Radars, 2024, 13 (03) : 554 - 564
  • [8] Learning Feature Fusion in Deep Learning-Based Object Detector
    Hassan, Ehtesham
    Khalil, Yasser
    Ahmad, Imtiaz
    JOURNAL OF ENGINEERING, 2020, 2020
  • [9] Sewer pipe defect detection via deep learning with local and global feature fusion
    Li, Dawei
    Xie, Qian
    Yu, Zhenghao
    Wu, Qiaoyun
    Zhou, Jun
    Wang, Jun
    AUTOMATION IN CONSTRUCTION, 2021, 129
  • [10] A deep learning-based model for biotic rice leaf disease detection
    Kaur, Amandeep
    Guleria, Kalpna
    Trivedi, Naresh Kumar
    MULTIMEDIA TOOLS AND APPLICATIONS, 2024, 83 (36) : 83583 - 83609