Fusion classification technique used to detect downy and Powdery Mildew grape leaf diseases

Abstract

Grape constitutes one of the most widely grown fruit crop in the India. Manual observation of experts is used in practice for detection of leaf diseases, which takes more time for further control action. Without accurate disease diagnosis, proper control actions cannot be taken at appropriate time. This is where modern agriculture technique is required to detect and prevent the leaf from different diseases. This paper aims to introduce a new approach for detection of grape leaf diseases using image processing, which will minimize the loss and increase its profit due to automation. In this system, classification is done using Support Vector Machine (SVM) and Artificial Neural Network (ANN) classifies separately. A new classifier is proposed using fusion classification technique which ensembles classifiers from SVM and ANN to regenerate base classifier for grape leaf disease detection. Based on detection of disease the proper mixture of fungicides will be provided to the grape farmers.