A novel approach for tomato leaf disease classification with deep convolutional neural networks

Abstract

Computer-aided automation systems that detect plant diseases are one of the challenging research areas that provide effective results in the agricultural field. Tomato crops are a major product with high commercial value worldwide and are produced in large quantities. This study proposes a new approach for the automatic detection of tomato leaf diseases, which employs classical learning methods and deep neural networks for image classification. Specifically, Local Binary Pattern (LBP) method was used for feature extraction in classical learning methods, while Extreme Learning Machines, k-Nearest Neighborhood (kNN), and Support Vector Machines (SVM) were used for classification. On the other hand, a novel Convolutional Neural Network (CNN) framework with its parameters and layers was employed for deep learning. The study shows that the accuracy values obtained from the proposed approach are better than the state-of-the-art studies. The classification process was carried out with different numbers of classes, including binary classification (healthy vs. unhealthy), 6-class, and 10-class classification for distinguishing different types of diseases. The results indicate that the CNN model outperforms classical learning methods, with accuracy values of 99.5%, 98.50%, and 97.0% obtained for the classification of 2, 6, and 10 classes, respectively. In future studies, computer-aided automated systems can be utilized to detect different diseases for various plant species.