An integrated fuzzy-rough set model for identification of tea leaf diseases

Tea is one of the major economic crops of India. People use tiny tea leaves to make beverages. The diseases in tea leaves affect the quality and yield of this cultivation. This paper proposes a disease classification model to prevent the major loss in crop yield.Tea leaf images are captured using a camera, and various image processing techniques are applied to the images to identify which disease is affected. The proposed model works for three major tea leaf diseases: blister blight, scab, and spot. The model extracts the Haralick features using Gray Level Co-occurrence Matrix (GLCM), and the most relevant features are selected with the help of the metaheuristic optimization technique. Fuzzy Rough Nearest Neighbor (FRNN) is used for classification techniques, and the model gave better accuracy than other existing techniques