Development of CNN Model for Detecting Groundnut Leaf Diseases Using Mobile Net

Plants are essential to economic growth, agricultural sustainability, and ecological balance. Plants can become sick from a range of pathogens, including bacteria, fungus, and viruses, just like people can. To avoid significant crop damage, these infections must be recognized and treated as soon as feasible. This paper proposes a deep learning-based model called "MobileNet CNN Plant Disease Detector," which uses images of the leaves to identify different types of diseases in groundnut leaves. In the procedure, data augmentation is employed to boost the dataset's size and variety. Multiple convolution and pooling layers are incorporated in an architecture known as MobileNet CNN. Six disease categories make up the dataset that was utilized to train and assess the algorithm: late leaf spot, early leaf spot,rust, early rust, nutrient deficit, and healthy leaves..