DISEASE DETECTION IN TEA LEAVES USING IMAGE PROCESSING

Abstract

Plant disease detection plays a vital role in achieving more quantity and better quality of agricultural product. Leaves are considered to have various characteristics, which help in detecting diseases in plants. Finding these diseases is a tedious task, which can be accelerated using image processing techniques. Image processing includes various feature extraction methods that can be used to find abnormalities in leaves. Prior steps for this involve extraction of features like color, texture and shape, from leaf image. Appropriate classification algorithm can be used to train and test the system using extracted features. This paper proposes the detection of disease in Tea leaves. Disease in tea plant is a serious issue which can have a direct impact on its production loss. By using HSV-Gabor filter for texture extraction, SIFT for detecting deformation in its shape in MATLAB and Probabilistic Neural Network Classifier (NNC) for training of the system, these diseases are classified.