Detecting Mulberry Leaf Disease using Convolutional Neural Networks

Because mulberry leaves are the main diet of silkworms in sericulture, it is important to keep them healthy. In disease control and maximization of yield, there is a need for early detection of disease in such leaves. This research uses a deep learning method termed Convolutional Neural Networks (CNNs) in detecting disease in mulberry leaves automatically. This method offers a quicker, more precise, and cheaper solution compared to conventional methods of disease identification by categorizing diseases from leaf images. The dataset employed here is labeled images of infected mulberry leaves. Preprocessing operations like image scaling and normalization were used to improve the performance of the CNN model. The CNN model contains several convolutional layers, pooling layers, and fully connected layers so that it can identify intricate patterns and classify different diseases with precision. In addition to disease detection, the system also provides real-time fertilizer advice relative to the diagnosed illness. As soon as a particular disease is identified, the software decides the best type and quantity of fertilizer required for leaf restoration and optimal development, relative to the level of infection. This ensures accurate and effective fertilizer application. The suggested approach not only proves to be highly accurate in the detection of various mulberry leaf diseases but also offers personalized fertilizer advice, pointing to the capability of CNNs in precision agriculture. The real-time detection and recommendation capabilities of the system can greatly benefit farmers and agricultural specialists by allowing for timely interventions, enhanced crop management, and effective fertilizer use. The findings highlight the capability of deep learning methods to improve disease detection, lower dependency on visual inspections, and increase productivity in mulberry cultivation.