Development of Plant-Leaf Disease Classification Model using Convolutional Neural Network

Agriculture is India’s primary source of income and the second largest producer of agriculture products. Crop production is influenced by various factors, like weather, soil conditions, and multiple illnesses in plant leaves. We have presented plant disease detection in this work utilising image processing techniques. Automated plant disease detection research is critical in agriculture for tracking broad areas of crops. Consequently, it detects illness signals as soon as they emerge on plant leaves. The existing research makes complex use of image preprocessing and is unable to detect plant leaf disease efficiently. We have developed a method for the classification of leaves in healthy and disease-affected leaves using a convolutional neural network (CNN) of 28 layers. The models were trained and validated using an available open dataset of 87.7K RGB images of various plants in a set of 38 different classes of disease and healthy leaf images of plants. We have achieved 98.13% accuracy for the classification of leaves. The suggested deep learning model effectively classifies the plant leaves.