Leaf Disease Detection Using Deep Learning

Abstract

The main objective of this project is to construct a system to detect the betel leaf diseases which are leaf spot or anthracnose, bacterial leaf spot and leaf stem. This project concentrate on the image processing techniques used to improve the quality of the image and neural network technique to classify the disease. The methodology is based on tensorflow and retraining image classifier using convolutional neural network. The model has been trained on three different disease of betel leaf. When a sample test image will be given it will test the image using the trained convolutional network model. Consequently, by implementing the technique leaf diseases are recognized about 90 percent accuracy rates.