An Effective Kapur’s Segmentation Based Detection and Classification Model for Citrus Diseases Diagnosis System

Abstract

Agriculture remains as an important occupation, the decrease in its production will lead to huge economical loss. Under the class of plants, citrus is employed as major nutrient resources such as vitamin C over the globe. But, citrus disease severely affects the growth as well as quality of citrus fruits. From the past ten years, computer vision applications are commonly employed to detect and classify the plant diseases effectively. This paper introduces a new segmentation based classification model to identify the presence of citrus disease. In addition, it classifies the different types of citrus diseases in a significant way. The presented model involves a two stage process namely Kapur’s based segmentation and particle swarm optimization with support vector machine (PSO-SVM) based classification. The presented KPS model is evaluated using Citrus Disease Image Gallery Dataset and the experimentation section validated the superior nature of the KPS model in terms of classification accuracy.