Detection of tomato leaves disease using CNN deep learning

Abstract

The output of tomatoes has increased in Bangladesh in the past few years. In addition to its nutritional benefits, tomato cultivation is important for the employment of many people. However, several illnesses that affect tomato leaves impede tomato output. My study's objective is to use convolutional neural networks (CNNs). This study explores the field of tomato leaf disease detection. My research highlights the revolutionary potential of CNNs in transforming agricultural practices, going beyond their statistical accomplishments. These models' ability to detect diseases early and accurately holds great promise for sustainable crop management and a major improvement in global food security. Three tomato leaf disease categories, including one healthy class, have been included in this study. For testing, 10% of instances were taken out of each class. 20% percent was used for validation and the remaining 70% for training. I extensively investigate the performance, computational efficiency, and ethical implications of five unique architectures: ResNet50, DenseNet201, MobileNetV2, MobileNetV3, and VGG19. The system displayed an accuracy of 95.37%. It is regarded as an easyto-use technology that will assist vegetable farmers, particularly those who cultivate "tomatoes," in reducing pest suppression by detecting leaf illnesses and increasing production by creating additional options for professional marketing and researching various vegetable diseases.