Abstract

Identification and classification of the plant leaf is efficient way to preventing loss occurred in agricultural field. The Septoria leaf spot is mainly affect the leaves which caused by a fungus, flu, bacteria. The Production of blueberry fruit is decreasing due to the disease affected on its stem and leaf. Small brown spots are frequently visible on blueberry leaves at specific period in the year. The spots, generally surrounded by bright yellow halos, start on the lower leaves and slowly appear on upper leaves over time. Image processing technology has been proved to be an efficient analysis to identify and detect the disease on a leaf. This proposed paper intends to focus to detect and classify a Septoria leaf spot on blueberry using Image Processing techniques such as, k-means clustering (k-nearest neighbor) for Segmentation, Gray-Level Co-occurrence Matrix for feature extraction and Support Vector Machine classifier to detect the leaf stage whether it is affected by Septoria spot or not. Totally 13 features have been extracted from each Blueberry leaf images where dataset of 40 images were taken for training and testing process partially and obtained the accuracy level was 96.77% using F-measure.