An Automation Perception for Cotton Crop Disease Detection Using Machine Learning

Cotton crop disease detection and classification based on images of leaves is a significant objective in agriculture. Cotton crops play a vital role in India. Every year, due to the attack of diseases, cotton production is decreasing. The main reasons for disease in plants are the pests, insects, and pathogens used; if they are not controlled on time, they affect productivity. In advancing digital image processing technologies, machine learning and other techniques that identify early disease detection in plants are proposed. This paper focuses on improving disease detection in cotton crop plants and leaves. Machine learning is used to identify and predict cotton plant disease using images and leaves collected in an uncontrolled environment. This study uses machine learning to review the different problems identified regarding plant disease. Various experimental configurations are investigated to analyze the impacts of different leaf classes, plant disease combinations, and their categories. Cotton crops are detected to classify the various types of cotton plants. Cotton plant diseases have a wide range of illnesses, from bacterial deficiency to bacterial, fungal, viral, and vitamin and nutrient deficiency. The proposed approach indicates the cotton crop plant in the leaf disease by their implementation results.