Disease detection and analysis in fruits using image processing

Abstract

Fruit diseases are a major problem in the agricultural industry where losses in economic and production are occured. In the existing system, K-means clustering algorithm is used to find whether the fruit is infected or not. Due to low accuracy, it will take more time to show the exact result. In this project, an image processing approach is proposed for identifying apple fruit diseases based on Convolutional Neural Network(CNN).In CNN algorithm, fruit image details are taken by the existing packages in this work. However, it can take a few moments.So, this proposed system can be used to identify fruit diseases quickly and automatically.This proposed approach is composed of the following main steps: getting input image, Image Preprocessing, Identifying affected places, highlighting those affected places, Verifying training set, showing results.Few types of fruit diseases, namely bitter rot, sooty blotch, powdery mildew and fungus images were used for this approach.This approach was tested according to fruit disease type and its stages, such as fresh and affected. The algorithm was used for detecting the disease of the fruit. Images were provided for training, such as fresh apple images, fresh banana images, bitter rot images, sooty blotch images, powdery mildew images and fungus images.