Rice Disease Detection Using Deep Learning
V. Vanitha
V. Vanitha, Vel Tech Rangarajan Dr. Sagunthala R & D Institute of Science and Technology, Avadi, Chennai (Tamil Nadu), India.
Manuscript received on 25 April 2019 | Revised Manuscript received on 03 May 2019 | Manuscript Published on 08 May 2019 | PP: 534-542 | Volume-7 Issue-5S3 February 2019 | Retrieval Number: E11940275S19/19©BEIESP
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Rice bacterial leaf blight, Rice sheath bight and rice blast are the commonly occurring pathology in rice. Early identification and accurate diagnosis can help to limit the spread of diseases and ensure the quality of crop. Automatic detection of the commonly occurring plant diseases are desirable to support farmers. This paper proposes an automatic plat disease identification approach using deep convolutional neural network. A dataset of 500 images of healthy and diseased samples were collected and the model is trained to identify the three common diseases on paddy. We have experimented with the convolutional neural networks to improve the accuracy for identification of rice diseases. The results show that we can effectively detect and recognize three classes of rice diseases best accuracy of 99.53% on test set.
Keywords: Identification of Rice Diseases, Convolutional Neural Networks, Deep Learning, Image Recognition.
Scope of the Article: Deep Learning