A hybrid deep learning based approach for rice leaf disease detection
IET Conference Proceedings · 01.06.2026 · 2025 (60) · 42-44
DOI: 10.1049/icp.2026.2013 ↗Kurz gefasst
Fachartikel in der Zeitschrift IET Conference Proceedings, erschienen am 01.06.2026. Verfasst von Sonali Mondal und 1 weiteren Autor:innen.
Abstract (Originalsprache)
Rice, a staple food crop feeding over half the world’s population, is highly susceptible to leaf diseases such as bacterial leaf blight, brown spot, leaf blast, leaf scald, and sheath blight. Timely detection of these diseases is critical for ensuring global food security. Traditional plant disease and pest detection methods are often time-consuming, labor-intensive, and resource-dependent, making them inadequate for modern agriculture's needs. Deep learning-based image processing has made significant strides in recent years, improving the detection and identification of plant diseases and pests. In this paper, we propose a hybrid deep learning framework that integrates Convolutional Block Attention Modules (CBAM) with EfficientNet-B5 and ShuffleNetV2 backbones for enhanced feature extraction. Extracted features are fused and optimized through Principal Component Analysis (PCA), followed by classification. Comprehensive experiments conducted on a curated rice leaf dataset demonstrate superior performance across six classes, achieving high classification accuracy and interpretability. Our approach establishes a robust, scalable, and interpretable model suitable for precision agriculture applications. Proposed framework surpasses existing state-of-the-art approaches, achieving a remarkable accuracy of 94%.
Zitieren
APA
Mondal, S., & Lin, S. (2026). A hybrid deep learning based approach for rice leaf disease detection. IET Conference Proceedings, 2025(60), 42-44. https://doi.org/10.1049/icp.2026.2013
Vancouver
Mondal S, Lin S. A hybrid deep learning based approach for rice leaf disease detection. IET Conference Proceedings. 2026;2025(60):42-44. doi:10.1049/icp.2026.2013
BibTeX
@article{Mondal2026,
author = {Mondal, Sonali and Lin, Shinfeng},
title = {A hybrid deep learning based approach for rice leaf disease detection},
journal = {IET Conference Proceedings},
year = {2026},
volume = {2025},
number = {60},
pages = {42--44},
doi = {10.1049/icp.2026.2013}
}
EUVIMED