Image Processing Using Correlation Base With Genetic Algorithm (GA) For Determining Rice Disease

Abstract

Mobile technology that is much-loved today is a smartphone. This is due to the ability and intelligence of these mobile devices in helping human life. One area of life that can use mobile devices to help get things done is the world of agriculture. In the agricultural world, one of the problems faced is determining the quality of agricultural crops, especially rice crops. Sometimes it is difficult to see the quality of the rice crop. The disease in rice suffered is one of the main factors to inhibit the production and quality of rice harvest. It takes a long time to detect rice diseases using traditional diagnostic approaches, so farmers often lost the best time to prevent and treat disease. The introduction of rice disease by image is an important research topic in the field of computer vision, where the main task is to find an effective way to represent the sick rice image. In this study, based on image processing techniques and pattern recognition methods, the method of introducing rice disease is proposed. The color transformation structure for RGB input (Red, Green and Blue) is designed first and then the RGB model is converted to HSI (Hue, Saturation and Intensity), YUV and gray models. Thebackgroundwasremovedbasedonaspecific threshold value, and then the disease spot image was segmented with region growing algorithm (RGA).   Thirty-eight classifying features of color, texture and shape were extracted from each spot image. To reduce the dimensions of the feature space and improve the accuracy of the most valuable feature rice disease identification is selected by combining genetic algorithms (GA) and selection of correlation-based features (CFS). In order to try to overcome the problem, made a mobile-based applications that can determine the quality of the plant by doing image processing on plants that want to know the quality

Keyword:  Rice Disease, Disease Leaf Recognition, Regional Growth Algorithm (RGA), Genetic Algorithm And Feature-Based Correlation Selection (GA-CFS), Mobile Device.