THEOBROMA CACAO LEAF INFIRMITY SCRUTINIZATION BASED ON MULTI SUPPORT VECTOR MACHINE USING IMAGE PROCESSING

Abstract

In Global chocolate market, Theobroma Cacao is the fundamental ingredient for the good quality chocolate production.This crop produces cocoa beans which are rich in minerals such as iron, magnesium, zinc and also has greater amount of calcium than in cows milk.Phytophthora pod rot, Cocoa swollen shoot virus (CSSV) and other common leaf diseases that causes the crop to produce a less quality cocoa beans to extract rich chocolates.This research work proposes detection of types of diseasesusing image processing and Multi Support Vector Machine(M-SVM). The methods used Image acquisition, Preprocessing, Segmentation, Feature Extraction and Classification. Using and K Means and Multi-Support Vector Machine(M-SVM) algorithm the type of disease of the cocoa leaf is classified. Once, the type of disease is detected, respective pest and infection control tools can be suggested.Comparatively, visual identification is labour intensive, less accurate and can be done only in small areas.Plant caretakers could be benefited a lot with an early disease detection, in order to prevent the worse to come to the cocoa plant.