Detection and Recognition of Paddy Plant Leaf Diseases using Machine Learning Technique
Nargis Parven1, Muhammad Rashiduzzaman2, Nasrin Sultana3, Md. Touhidur Rahman4, Md. Ismail Jabiullah5
1Nargis Parven*, Pursuing M.Sc. in Computer Science and Engineering at Daffodil International University, Dhaka, Bangladesh.
2Muhammad Rashiduzzaman, Research Associate, Department of Computer Science and Engineering, Daffodil International University, Dhaka, Bangladesh.
3Nasrin Sultana, pursuing M.Sc. in Computer Science and Engineering at Daffodil International University, Dhaka, Bangladesh.
4Md. Touhidur Rahman, Assistant Programmer, Department of Computer Science and Engineering, University of Dhaka, Dhaka, Bangladesh.
5Md. Ismail Jabiullah, Professor, Department of Computer Science and Engineering, Daffodil International University, Dhaka, Bangladesh.
Manuscript received on February 10, 2020. | Revised Manuscript received on February 24, 2020. | Manuscript published on March 10, 2020. | PP: 634-638 | Volume-9 Issue-5, March 2020. | Retrieval Number: E2509039520/2020©BEIESP | DOI: 10.35940/ijitee.E2509.039520
Open Access | Ethics and Policies | Cite | Mendeley
© 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 is one of the important food crops and the most staple food for half of the world population. Farmers are often faces several obstacles in paddy production because of various paddy leaf diseases. As a result, rice production is extensively reduced. For finding the paddy plant leaf diseases, there are many techniques are available in the computer vision-based area. Now, it is the main concern to fast and accurate recognition of paddy plant diseases in the initial stage. For this reason, we proposed a better approach for early paddy plant leaf disease detection by using simple image processing and machine learning techniques. There are four types of paddy leaf diseases are highlighted in this paper; which are Brown Spot, Sheath Blight, Blast Disease and Narrow Brown Spot. To do this, at first the required normal and diseased paddy plant leaf images are captured directly from different paddy fields. The unnecessary background of the leaves images are eliminated by using mask in the pre-processing section. Then output is fed into the segmentation part where K-means clustering is used to separate the normal portion and diseased portion of the leaf images. Finally, the mentioned diseases are classified using Support Vector Machine (SVM) algorithm. The accuracy of the system is 94%. This technique can be also applied anywhere in the agriculture industry for plant leaf diseases detection.
Keywords: Paddy Plant, Leaf Disease Detection, Image Processing, Machine Learning, Support Vector Machine (SVM), K-Means Clustering.
Scope of the Article: Clustering.