Identification and Classification of Fruit Diseases

Diseases in fruit cause major problem in agricultural industry and also causes economic loss.The diseases in fruits reduce the yield and also deteriorate the variety and its withdraw from the cultivation.So, earlier detection of symptoms of fruit disease is required.In this paper a solution for identification and classification of fruit diseases is proposed and experimentally validated.Ten different fruits has been selected with few of their diseases . The image processing based proposed approach is composed of following main steps,first step is segmentation using K-means and C-Means clustering algorithms,Second step is conducted a performance evaluation of segmentation algorithm by measuring the parameters such as Measure of overlapping (MOL), Measure of under-segmentation (MUS), Measure of over segmentation (MOS), Dice similarity measure (DSM), Error-rate (ER). The segmentation performance is calculated based on the comparison between the manually segmented ground truth G and segmentation result S generated by the image segmentation approach. After segmentation features are extracted using GLCM. The k Nearest Neighbours Algorithm classifier is used to classify the diseases in fruits .The collected database consists of 34 classes with 243 images .The experiment has been conducted on database of 34 classes having training samples of 30,50,70 percent of database .The result of classification has relatively higher accuracy in all cases when segmented using K-Means than C-Means clustering algorithms