A Novel Mining Approach for Automatic Disease Detection in Sugarcane Plant using Thresholding Method

Abstract

Disease infection of agricultural merchandise affects the agriculturists and human health and conjointly degrades the standard and amount of merchandise. The tradition approach for detecting a disease is time consuming and very costly. The plant diseases are detected by automatic detection techniques that scale back an outsized work of continuous observation and observation in massive farms by farmers or specialists. The proposed algorithms detect the variety of diseases infected in sugarcane plants. The images are captured by digital camera. The noises in digital image are removed by low pass filter. This paper presents image segmentation mistreatment thresholding technique that is employed for automatic unwellness detection of sugarcane plants. SIFT method is applied for detecting and describing the local features of the plant species. The features such as colors, size shape and texture of surface is extracted by using GLCM feature extractor. The abnormal pictures are classified by mistreatment SVM classifier. In sugarcane plant, the diseases are detected mechanically and yields ninety nine accuracy rate than existing techniques.