An Approach for Detection and Classification of Fruit Disease

Abstract

Agriculture is the mother of all cultures. Due to increasing demand in the agricultural industry, the need to effectively grow a plant and increase its yield is very important. Diseases in fruit cause devastating problem in economic losses and production in agricultural industry worldwide. So to protect the product, it is important to monitor the plant during its growth period, as well as, at the time of harvest. In this paper, a solution for the detection and classification of Strawberry fruit diseases is proposed and experimentally validated. For Fruit Disease Detection, the image processing based proposed approach is composed with the following main steps; in first step, Image acquisition is done, After that in second step Preprocessing is done including Noise Remove using masking and Image Enhancement using Discrete Cosine Transform (DCT). In third step Feature Extraction is done, in which, Color Feature Extraction using Color Space Conversion and Texture Feature Extraction using Canny Edge Detection and Dilation. As same as, For Fruit Leaf Disease Detection, the image processing based proposed approach is composed with the following main steps; in first step, Image acquisition is done, in this images are collected from Internet. After that in second step Preprocessing is carried out. In which, Image Enhancement is done using Equalize Histogram and Color Space Conversion. In third step Feature Extraction is done using Gray Level Co-occurrence Matrix (GLCM) for Texture Feature Extraction. After that, classification is done using Support Vector Machine (SVM) Classifier.