Tomato Disease Classification using Fine-Tuned Convolutional Neural Network

Abstract

Tomatoes have enhanced vitamins that are necessary for mental and physical health. We use tomatoes in our daily life. The global agricultural industry is dominated by vegetables. Farmers typically suffer a significant loss when tomato plants are affected by multiple diseases. Diagnosis of tomato diseases at an early stage can help address this deficit. It is difficult to classify the attacking disease due to its range of manifestations. We can use deep learning models to identify diseased plants at an initial stage and take appropriate measures to minimize loss through early detection. For the initial diagnosis and classification of diseased plants, an effective deep learning model has been proposed in this paper. Our deep learning-based pre-trained model has been tuned twofold using a specific dataset. The dataset includes tomato plant images that show diseased and healthy tomato plants. In our classification, we intend to label each plant with the name of the disease or healthy that is afflicting it. With 98.93% accuracy, we were able to achieve astounding results using the transfer learning method on this dataset of tomato plants. Based on our understanding, this model appears to be lighter than other advanced models with such considerable results and which employ ten classes of tomatoes. This deep learning application is usable in reality to detect plant diseases.