Detection of Tomato Leaf Disease Using Deep Convolutional Neural Networks

Abstract

Agriculture is the backbone of many economies throughout the world including Pakistan. Similarly, tomatoes are the most widely cultivated vegetables in the agricultural field. In addition, the tropical weather increases the throughput yield of tomato crops. However, various climatic conditions and other factors affect the growth of the tomato plant. Rather than such climate conditions and natural disasters, plant diseases are the primary reason for the production crisis resulting in less tomato yield and financial disaster. Traditional methods for detecting diseases in tomato leaves failed to produce the expected outcomes, and disease detection seemed static. However, making the vegetable plants healthy with time is becoming very significant. Identifying diseases in vegetable plants is essential before they cause too severe harm to the vegetables. This research proposes three CNN-based models VGG-16, ResNet-152, and EfficientNet-B4, to classify tomato leaf diseases into normal of disease affected. The proposed research is conducted to find the best possible solution for detecting tomato leaf disease using these deep learning approaches. Employing the Plant-Village dataset with 5524 leaf images, ResNet-152 and EfficientNet-B4 achieved 93.75% and 97.27% accuracy respectively, while VGG-16 achieved 98% accuracy. The efficiency of the system makes it capable of becoming a preference in the agricultural field for real-time tomato leave disease detection applications.