Deep Learning-Based Diagnosis of Rice Sheath Rot Disease: A Wavelet-Filtered Approach for Feature Extraction and Analysis

A major danger to rice farming, rice sheath rot disease affects the quantity and quality of one of the main food crops grown worldwide. This research uses a large dataset gathered from many sources, such as agricultural universities, research centres, and first hand field observations, to provide a unique method of diagnosing Rice Sheath Rot disease using cutting-edge deep learning algorithms. Our work is primarily focused on creating a dependable and effective diagnostic tool using state-of-the-art image processing and machine learning methods. Wavelet filters are applied in the first step of our approach to pre-process photos. This method is essential for eliminating noise and improving the quality of the dataset, which is made up of high-definition photos of rice plants with the disease Sheath Rot. The colour, shape, and texture of the sick spots are then analyzed using advanced feature extraction techniques. When separating plant tissues that are diseased from those that are not, these characteristics are essential. Convolutional Neural Networks (CNN), our primary diagnostic model’s foundation, were selected due to their shown efficacy in picture recognition and classification applications. The preprocessed and feature-enhanced dataset is used to train the CNN model, giving it the ability to recognize the complex patterns and traits connected to Sheath Rot illness. The architecture of the model is built to maximize efficiency and accuracy, guaranteeing quick and accurate illness identification. By utilizing AI and deep learning, the proposed method seeks to not only help farmers and agronomists identify diseases early on but also make a substantial contribution to the area of agricultural disease diagnostics. Combine that our method, which combines CNN-based analysis with wavelet-filtered pre-processing establishes a new standard for the identification and treatment of Rice Sheath Rot disease. This might result in improved crop management techniques and more potent disease control tactics.