Efficient Rice Disease Classification Using Intelligent Techniques

Rice is a staple crop on which nearly half of our world’s population is dependent. But it is prone to many diseases. Hence, it requires disease management to maintain food security. This research paper proposes a Convolutional Neural Networks (CNN)-based algorithm for the detection of rice diseases. This algorithm is tested on a large dataset of annotated rice images. The proposed model can identify the presence of various diseases in rice leaves. The results of the experiments show that the proposed algorithm outperforms traditional machine learning-based algorithms used for diagnosing rice diseases. The proposed approach can also help to automate the disease diagnosis process and reduce the dependency on expert opinion, thereby reducing the overall cost and time involved. The results demonstrate that our approach can accurately detect different types of rice diseases with high precision compared to other state-of-the-art algorithms. This research stipulates a promising elucidation for efficient and automated rice disease detection, which can be integrated into a decision support system for rice cultivation.