Disease Identification in Tomato Leaves Using Inception V3 Convolutional Neural Networks

Abstract

Tomatoes are the most widely grown vegetable, used in a wide variety of dishes around the world. After potatoes and sweet potatoes, it is the third most extensively cultivated crop in the world. However, due to several diseases, both the quality and quantity of tomato harvests dedine. To maximize tomato yields, it is important to identify and eradicate the many diseases that harm the crop as early as possible. In this paper, we investigate the potential of deep learning techniques for diagnosing diseases on tomato leaves. The use of automatic methods for tomato leaf disease detection is helpful because it reduces the amount of monitoring needed in large-scale crop farms and does so at a very early stage when the signs of the disease identified on plant leaves are still easy to cure. The Kaggle dataset for tomato leaf disease was used for the study. A technique based on convolutional neural networks is used for disease identification and classification. Deep learning models, such as Inception V3 are used in this work. This proposed system obtained an accuracy of 99.60% suggesting that the neural network approach is effective even under difficult situations.