Detection of Grape Leaf Diseases Using a Traditional Neural Network

Having diseases is quite natural in crops due to changing climatic and environmental conditions. Diseases affect the growth and produce of the crops and often difficult to control. To ensure good quality and high production, it is necessary to have accurate disease diagnosis and control actions to prevent them in time. Grape which is widely grown crop in India and it may be affected by different types of diseases on leaf, stem and fruit. Leaf diseases which are the early symptoms caused due to fungi, bacteria and virus. So, there is a need to have an automatic system that can be used to detect the type of diseases and to take appropriate actions. This project proposes an automatic system for detecting the disease in the grape leaf using convolutional neural network. The CNN classified image is fed to the image processing operation. In image processing operation block Gaussian filter is used. The fuzzy inference system segments the processed image using Fuzzy c-means segmentation. A healthy leaf percentage are discovered using the fuzzy inference approach. This project is implemented with MATLAB simulation software and the output reveals the healthy percentage.