Published Paper Details:

It is common knowledge that a country's economy heavily depends on agricultural productivity. It's pretty normal for illnesses to affect plants. Therefore, identifying plant diseases is essential to raising agricultural productivity. When plants are not given the correct care, they might suffer major consequences that have an impact on the quality, quantity, or productivity of the plant's output. For instance, crop failure during The Great Famine (1845-1849) resulted in disease, widespread famine, emigration, and death. Later, biologists came to the conclusion that a natural occurrence called a potato blight was the cause of the famine. Numerous people died, bringing the total to 100,000. Large-scale farms can apply automated disease detection methods on agricultural crops, which will lessen the need for manual crop monitoring and enable the early diagnosis of illness or its signs. This allows the right cure time to work. The application described in this article uses machine learning methods to analyse photos of tomato plant leaves to identify and categorize illnesses. Finding diseases on crops is a time-consuming and vital task in agricultural techniques. It takes a lot of labor, both expert and manual. In this study, computer vision and machine learning approaches are proposed as a smart and effective method for crop disease identification.