A Deep Learning-based study of Crop Diseases Recognition and Classification

Agriculture feeds both human and cattle populations around the world. To increase agricultural productivity effectively, fast and precise disease diagnosis is essential. Farmers face a drag like water shortage, fertility problems, pests, disease attacks, low yield, and sort of monetary problems. Farmers use the normal method for locating these problems. But those techniques aren’t much effective. Detection of the disease in its initial phase will help in preventing the loss of crops, improve the productivity of plants, and therefore the quality of the products. To solve agricultural issues image processing techniques can be used. Deep Learning includes a cutting-edge image processing approach. This involves putting present work in the area of agricultural leaf disease identification and diagnosis utilizing Deep Learning algorithms in its proper context. This study looks at the latest developments and issues in using Deep Learning and advanced picture processing technologies to identify crop leaf disease. The survey looks at the various agricultural problems being researched, the models utilized, the sources of information used, and the total precision attained using the researchers’ performance criteria. By enhancing system reliability and efficiency, the creation of this review enables longer-term study to identify deeper capabilities of Deep Learning when detecting and categorizing crop diseases.