Answers are grounded in this paper and cite their sources.
Rice leaf diseases pose a significant threat to our food security as they can reduce crop yields, cause plant deaths or even complete destruction in some cases, and result in shortfalls for both farmers and global agricultural production.Typically, farmers and other agricultural experts identify these diseases merely through visual examination, which leads to laboriousness, undesirable subjectivity, and faulty diagnosis.The main aim of this study is to provide farmers with accurate visual information so that they can protect their crops on time.Results: To accurately model a disease identification, we first propose our RiceLeafBD dataset.This dataset has been the subject of several studies, but our approach applies a model to it for the first time.We employed a proposed framework, achieving a superior accuracy of 92.75%.Notably, when assessing the performance on the tungro virus class, the model demonstrated exceptional precision, recall, and F1-score values of 100%, 98%, and 99%, respectively.The proposed framework does better than current convolutional neural network (CNN) and hybrid CNNtransfer learning models, according to the results of experiments.It has the highest accuracy and the least amount of model complexity that has been seen so far.
No takes yet. Share an insight, caveat, or question.
Nath et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: