TeaDiseaseNet: multi-scale self-attentive tea disease detection

被引:8
作者
Sun, Yange [1 ,2 ]
Wu, Fei [1 ]
Guo, Huaping [1 ,2 ]
Li, Ran [1 ]
Yao, Jianfeng [1 ,3 ]
Shen, Jianbo [4 ]
机构
[1] Xinyang Normal Univ, Sch Comp & Informat Technol, Xinyang, Peoples R China
[2] Chinese Acad Sci, Inst Automat, Res Ctr Precis Sensing & Control, Beijing, Peoples R China
[3] Xinyang Normal Univ, Henan Key Lab Tea Plant Biol, Xinyang, Peoples R China
[4] Beijing Acad Agr & Forestry Sci, Intelligent Equipment Res Ctr, Beijing, Peoples R China
基金
中国国家自然科学基金;
关键词
tea disease detection; deep learning; multi-scale feature; self-attention; convolutional neural networks; IDENTIFICATION;
D O I
10.3389/fpls.2023.1257212
中图分类号
Q94 [植物学];
学科分类号
071001 ;
摘要
Accurate detection of tea diseases is essential for optimizing tea yield and quality, improving production, and minimizing economic losses. In this paper, we introduce TeaDiseaseNet, a novel disease detection method designed to address the challenges in tea disease detection, such as variability in disease scales and dense, obscuring disease patterns. TeaDiseaseNet utilizes a multi-scale self-attention mechanism to enhance disease detection performance. Specifically, it incorporates a CNN-based module for extracting features at multiple scales, effectively capturing localized information such as texture and edges. This approach enables a comprehensive representation of tea images. Additionally, a self-attention module captures global dependencies among pixels, facilitating effective interaction between global information and local features. Furthermore, we integrate a channel attention mechanism, which selectively weighs and combines the multi-scale features, eliminating redundant information and enabling precise localization and recognition of tea disease information across diverse scales and complex backgrounds. Extensive comparative experiments and ablation studies validate the effectiveness of the proposed method, demonstrating superior detection results in scenarios characterized by complex backgrounds and varying disease scales. The presented method provides valuable insights for intelligent tea disease diagnosis, with significant potential for improving tea disease management and production.
引用
收藏
页数:14
相关论文
共 64 条
[1]   Plant diseases recognition on images using convolutional neural networks: A systematic review [J].
Abade, Andre ;
Ferreira, Paulo Afonso ;
Vidal, Flavio de Barros .
COMPUTERS AND ELECTRONICS IN AGRICULTURE, 2021, 185
[2]   OPNN: Optimized Probabilistic Neural Network based Automatic Detection of Maize Plant Disease Detection [J].
Akanksha, Eisha ;
Sharma, Neeraj ;
Gulati, Kamal .
PROCEEDINGS OF THE 6TH INTERNATIONAL CONFERENCE ON INVENTIVE COMPUTATION TECHNOLOGIES (ICICT 2021), 2021, :1322-1328
[3]  
Alirezazadeh P, 2023, GESUNDE PFLANZ, V75, P49, DOI 10.1007/s10343-022-00796-y
[4]   RTF-RCNN: An Architecture for Real-Time Tomato Plant Leaf Diseases Detection in Video Streaming Using Faster-RCNN [J].
Alruwaili, Madallah ;
Siddiqi, Muhammad Hameed ;
Khan, Asfandyar ;
Azad, Mohammad ;
Khan, Abdullah ;
Alanazi, Saad .
BIOENGINEERING-BASEL, 2022, 9 (10)
[5]   Automated plant leaf disease detection and classification using optimal MobileNet based convolutional neural networks [J].
Ashwinkumar, S. ;
Rajagopal, S. ;
Manimaran, V ;
Jegajothi, B. .
MATERIALS TODAY-PROCEEDINGS, 2022, 51 :480-487
[6]   Crop pest classification with a genetic algorithm-based weighted ensemble of deep convolutional neural networks [J].
Ayan, Enes ;
Erbay, Hasan ;
Varcin, Fatih .
COMPUTERS AND ELECTRONICS IN AGRICULTURE, 2020, 179
[7]   Detection and identification of tea leaf diseases based on AX-RetinaNet [J].
Bao, Wenxia ;
Fan, Tao ;
Hu, Gensheng ;
Liang, Dong ;
Li, Haidong .
SCIENTIFIC REPORTS, 2022, 12 (01)
[8]  
Bhavsar N., 2022, Int. J. Eng. Res. Rev, V10, P52, DOI 10.5281/zenodo.7486512
[9]  
Bochkovskiy A, 2020, Arxiv, DOI [arXiv:2004.10934, DOI 10.48550/ARXIV.2004.10934]
[10]   A deep learning based approach for automated plant disease classification using vision transformer [J].
Borhani, Yasamin ;
Khoramdel, Javad ;
Najafi, Esmaeil .
SCIENTIFIC REPORTS, 2022, 12 (01)