Agricultural field plays a major role in development of India. The farmers are supplemented with additional profit by exporting fruits from India. The devastating problem in economic losses and production in agricultural industry is caused by diseases in fruits. Manual identification of defected fruit is time consuming and a difficult approach. Based on the pictures representing the symptoms of the fruit, Web-based system helps non experts also in the identification of the fruit disease. In this paper ten types of apple fruit diseases are classified by using the proposed Hybrid Neural Clustering (HNC) Classifier. The results of the feature extraction vector is supplied as the input to the classifier. There are two phases in this proposed method .The first phase is used to train the images by using the K Means Clustering to cluster the vector points and followed up with the second phase which is used to test by applying the Feed Forward Back propagation neural network (FFBP). The output received is the whole set of images that are classified into the various apple fruit diseases. The various diseases classified are Alternia Rot, Black Rot, Scab, Grey Mould, Bitter Rot, Blister Spot, Brown Rot, White Rot, Blue Mould, Powdery Mildew. The proposed method is evaluated by precision, recall and F Measure and it scored higher values than existing methods. Proposed method provides 98% of accuracy than other existing method.
Read full abstract