Enhancing Sugarcane Leaf Disease Prediction Model Using DenseNet

Improving crop production and implementing sustainable agricultural methods depend on the timely and precise identification of sugarcane splint conditions. In order to classify sugarcane splint situations from photos, this research proposes an improved deep literacy method that exercises DenseNet201, a densely linked neural network. The suggested model distinguishes between healthy and damaged leaves with great delicacy by utilising DenseNet201's enhanced point birth capabilities. This method achieves notable improvements by being trained and estimated on a carefully selected dataset of pictures of sugarcane splints. Additionally, provide a web-based application that incorporates the model, enabling drug users to upload pictures of their splints and submit immediate complaint forecasts. With the help of this technology, producers and experimenters may identify circumstances in advance, allowing for improved crop operation and early action In terms of delicacy, speed, and robustness, the results show that the DenseNet201-grounded model works better than conventional styles, providing a reliable tool for faultless husbandry.