Answers are grounded in this paper and cite their sources.
Paddy leaves, fundamental components of rice plants (Oryza sativa), play a critical role in global food production, particularly in countries like India, where paddy production is notably high. Beyond their role as photosynthetic powerhouses, these leaves serve as crucial indicators of plant health. Detecting diseases affecting paddy leaves is imperative for sustaining crop yields and global food security, especially in regions where rice cultivation is a cornerstone of agricultural practices. In our paper, ensemble technique utilizes pre-trained models which are ResNet50, InceptionV3, and MobileNetV2, to address disease detection on our dataset, which encompasses four distinct classes. Trained on a real-world dataset capturing diverse disease features, the models leverage deep training proficiency, multi-scale feature extraction, and efficiency. Experimental results, exhibit reduced false positives and negatives, emphasizing the methodology's accessibility and effectiveness in early disease detection. The InceptionV3 model attains a precision of 82.79%, the ResNet model achieves 91.89%, and the MobileNetV2 model reaches 73.02%. The Stacking Classifier attains the highest accuracy of 96.09%.
No takes yet. Share an insight, caveat, or question.
Sindhu et al. (2024) studied this question.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: