Identification and Recognition of Rice Diseases and Pests Using Deep Convolutional Neural Networks

An accurate and timely detection of diseases and pests in rice plants can help to reduce economic losses substantially. It can help farmers in applying timely treatment. Recent developments in deep learning based convolutional neural networks (CNN) have allowed researchers to greatly improve the accuracy of image classification. In this paper, we present a deep learning based approach to detect diseases and pests in rice plants using images captured in real life scenerio with heterogeneous background. We have experimented with various state-of-the-art convolutional neural networks on our large dataset of rice diseases and pests, which contain both inter-class and intra-class variations. The results show that we can effectively detect and recognize nine classes of rice diseases and pests including healthy plant class using a deep convolutional neural network, with the best accuracy of 99.53% on test set.