Fruit Disease Recognition and Automatic Classification using MSVM with Multiple Features

Image processing and machine learning play an important role in fruit disease identification and classification by means of image segmentation and pattern recognition. Traditional fault detection in the fruit surface is carried out manually by means of human inspection which is very time consuming and laborious. In this paper we have proposed a method for fruit disease identification using segmentation techniques and use a supervised learning technique for classifying images based on data analyzed from RGB colored images. Three types of common apple diseases are taken into considerations in this paper. The experimental results demonstrate that the proposed approach is promising and effective by showing the classification accuracy which has achieved more than 94% using several features.