Rice Leaf Disease Prediction Using Machine Learning

In the realm of agricultural data, automated detection and diagnosis of rice leaf diseases is greatly sought. Machine learning plays an important role here and can handle these difficulties in leaf disease identification rather well. We present a novel rice disease detection approach based on machine learning techniques in this paper. Here we have considered various rice leaf diseases and used different machine learning techniques for the classification of these diseases. In this study we first extract the features of rice leaf disease images. Then we apply various machine learning techniques in order to classify the images and found that an accuracy of 81.8% was achieved using Quadratic SVM classifier. Shape features such as area, roundness, area to lesion ratio, etc; were also used to differentiate between different types of rice diseases. The results obtained were good and met the required expectations.