Analysis of Automatic Rice Disease Classification Using Image Processing Techniques
G. Jayanthi1, K.S. Archana2, A. Saritha3
1G.Jayanthi, PG Student, Department of Computer Science and Engineering, Vels University, Chennai (Tamil Nadu), India.
2K.S. Archana, Assistant Professor, Department of Computer Science and Engineering, Vels University, Chennai (Tamil Nadu), India.
3A.Saritha, Assistant Professor, Department of Computer Science and Engineering, Vels University, Chennai (Tamil Nadu), India.
Manuscript received on 25 May 2019 | Revised Manuscript received on 03 June 2019 | Manuscript Published on 22 June 2019 | PP: 15-20 | Volume-8 Issue-3S, February 2019 | Retrieval Number: C10040283S19/19©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: Agriculture is the most important sector in today’s life. Based on the detailed study the agriculture is highly affected by number of diseases. So automatic analyze have to take attention to predict the rice disease from early symptoms. The manual consumption of farmer to monitor the field to decrease the growth of the yield, because once the disease occurs to any of the plant it gradually goes to another plant at last it destroyed the whole farm. So the automatic diseases identification is carried out before destroying the whole yield. This paper presents the detailed study of different image processing techniques to detect the disease in rice plant. Primary colours are RGB image used to spot the disease in segmentation. In Such techniques used to identify the disease from the early symptom of the yield loss. This manuscript would help the researchers to understand rice disease identification using computer vision. At last, this paper has the discussion of different researcher’s pros and cons of all studies related to plant disease identification. In digital image processing techniques, they are used for enhancement of the image. GLCM and SURF features are used for feature extraction. Edge detection and FCM is used for segmentation. ANN is used for classification.
Keywords: Image Acquisition, Edge Detection-Fuzzy C-means, Gray Level Concurrence Matrix, Speeded Up Robust Feature, Artificial Neural Network.
Scope of the Article: Image analysis and Processing