Deep learning for rice leaf disease detection: A systematic literature review on emerging trends, methodologies and techniques

• Published in: Information processing in agriculture 2024-05
• Main Authors: Simhadri, Chinna Gopi, Kondaveeti, Hari Kishan, Vatsavayi, Valli Kumari, Mitra, Alakananda, Ananthachari, Preethi
• Format: Article
• Language: English
• Subjects: Convolutional Neural Network; Deep learning; Ensemble learning; Rice leaf disease classification; Transfer learning
• ISSN: 2214-3173; 2214-3173
• DOI: 10.1016/j.inpa.2024.04.006

Rice is an essential food crop that is cultivated in many countries. Rice leaf diseases can cause significant damage to crop cultivation, leading to reduced yields and economic losses. Traditional disease detection approaches are often time-consuming, labor-intensive, and require expertise. Automatic leaf disease detection approaches help farmers detect diseases without or with less human interference. Most of the earlier studies on rice leaf disease detection depended on image processing and machine learning techniques. Image processing techniques are used to extract features from diseased leaf images, such as the color, texture, vein patterns, and shape of lesions. Machine learning techniques are used to detect diseases based on the extracted features. In contrast, deep learning techniques learn complex patterns from large datasets without explicit feature extraction techniques and are well-suited for disease detection tasks. This systematic review explores various deep learning approaches used in the literature for rice leaf disease detection, such as Transfer Learning, Ensemble Learning, and Hybrid approaches. This review also discusses the effectiveness of these approaches in addressing various challenges. This review discusses the details of various models and hyperparameter settings used, model fine-tuning techniques followed, and performance evaluation metrics utilized in various studies. This review also discusses the limitations of existing studies and presents future directions for further developing more robust and efficient rice leaf disease detection techniques. [Display omitted] •This review discusses the limitations of traditional approaches used for rice leaf disease detection.•It reviews 82 most relevant and of high quality articles related to leaf disease detection in rice since 2017.•This review conducts a comprehensive systematic literature review of various approaches used for rice leaf disease detection using deep learning.•It discusses challenges and limitations associated for detection of rice plant diseases.•This review suggests directions for future research, such as developing new methods or improving the accuracy and reliability of existing approaches.