Design and Development of Deep Learning-Based Framework to Detect Disease in Tomato Leaf

A considerable agricultural market in India offers the idyllic atmosphere for a wide range of crops. The tomato crop, which has significant commercial value, is one of the widely produced staples of the Indian market. India’s tropical climate is ideal for its growth, but a few climatic circumstances and a number of other things interfere with tomato plants’ typical growth. Furthermore, plant diseases cause a severe danger to agricultural production and are a significant contributor to financial loss. However, because of the various types of diseases, the quality of the tomato crop declines. Therefore, to maximize agricultural productivity, cutting expenses and early detection of plant diseases are crucial. Monitoring plant diseases manually is prone to mistakes. Many different types of diseases, such as Late Blight, Septoria Spot, Mosaic Virus, to a name of few, seriously harm these tomato leaves. Hence, it is mandatory to find a way to prevent these diseases before they start. Traditional disease detection techniques for tomato crops did not yield the desired results as well as the disease detection times were lengthy. Machine learning has been used to detect plant illnesses early, reducing their negative impacts while also overcoming some of the limitations of constant human monitoring.