Tomato Leaf Disease Detection Using Deep Learning: A CNN Approach

The world’s population relies on plants as a source of food; hence they play a significant role. When a plant’s normal structure, growth, function, or other activities are consistently interfered with by a causative factor, an abnormal physiological process occurs and the plant develops a disease. This causes significant harm and is characterized by rotten tissue, wilting, scabs, moldy coatings, rust and blotches. Almost any moderately well-drained soil type is suitable for growing tomatoes (Solanum Lycopersicum). We may identify diseases with various leaf symptoms by using the suggested method (Deep learning, Tensor flow) to build models. CNN can immediately process the raw images and automatically extract features. The proposed technique can treat the plant’s affected area, help increase the production of tomatoes, and meet the global market’s demand. In this research work, we provided a novel learning model based on VGG architecture for classifying infected and healthy tomato leaves. The proposed work’s higher performance is confirmed by an accuracy of 92%. The model presented is also computationally efficient