Utilizing Deep Convolutional Neural Networks for Multi-Classification of Plant Diseases from Image Data

Abstract

The economic health of a nation is significantly influenced by the productivity of its agricultural sector. Enhancing this productivity is directly linked to the early detection and management of plant diseases. Automated classification methodologies are instrumental in the early diagnosis of these diseases, offering improved precision over traditional methods. These automated systems initiate disease detection as soon as symptoms begin to manifest on plant leaves, following a four-step process involving pre-processing, segmentation, feature extraction, and classification. In this study, we present an automated methodology for the detection and classification of plant diseases using a deep-learning approach applied to varying quality leaf images. A deep convolutional neural network architecture was trained utilizing an image dataset. The proposed Deep Neural Network Plant Disease Classifier (DNN-PDC) was specifically designed for the multi-categorization of plant diseases. Tomato leaf images from the PlantVillage dataset on Kaggle were selected for the experiments. The proposed deep learning system demonstrated a high level of accuracy in the classification of various tomato leaf diseases, including Early Blight, Septoria Leaf Spot, and Late Blight. Experimental results indicate that the proposed method surpasses existing approaches in the image-based classification of tomato plant diseases. This study underscores the potential of the DNN-PDC model as a highly effective tool for plant disease detection and classification.