Classification of Leaf Disease from Image Processing Technique

Abstract

Disease in palm oil sector is one of the major concerns because it affects the production and economy losses to Malaysia. Diseases appear as spots on the leaf and if not treated on time, cause the growth of the palm oil tree. This work presents the use of digital image processing technique for classification oil palm leaf disease sympthoms. Chimaera and Anthracnose is the most common symtoms infected the oil palm leaf in nursery stage. Here, support vector machine (SVM) acts as a classifier where there are four stages involved. The stages are image acquisition, image enhancement, clustering and classification. The classification shows that SVM achieves accuracy of 97% for Chimaera and 95% for Anthracnose.