Identification of Pests on Plants using Clustering and Hybrid Approaches
Karkuzhali S1, Krishna Mohan S2, Kavin S3, Karthick V I4
1Karkuzhali S, Associate Professor, Department of Computer Science and Engineering, Arulmigu Kalasalingam College of Engineering, Anna University, Chennai (Tamil Nadu), India.
2Krishna Mohan S, Associate Professor, Department of Computer Science and Engineering, Arulmigu Kalasalingam College of Engineering, Anna University, Chennai (Tamil Nadu), India.
3Kavin S, Associate Professor, Department of Computer Science and Engineering, Arulmigu Kalasalingam College of Engineering, Anna University, Chennai (Tamil Nadu), India.
4Karthick V I, Associate Professor, Department of Computer Science and Engineering, Arulmigu Kalasalingam College of Engineering, Anna University, Chennai (Tamil Nadu), India.
Manuscript received on 24 November 2019 | Revised Manuscript received on 18 December 2019 | Manuscript Published on 30 December 2019 | PP: 507-509 | Volume-9 Issue-1S4 December 2019 | Retrieval Number: A11131291S419/19©BEIESP | DOI: 10.35940/ijeat.A1113.1291S419
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: Enormous agricultural yield is lost each year, because of quick pervasion by pest and insects. A great deal of research is being done worldwide to recognize logical procedures for early discovery/identification of these bio-aggressors. In the past years, a few methodologies dependent on computerization and digital image processing have become known to address this issue. The greater part of the calculations focus on pest identification and location, restricted to a greenhouse environment. Likewise, they include a few complex computations to accomplish the equivalent. In this paper, we developed a unique algorithmic approach to isolate and distinguish pest utilizing clustering and hybrid approaches. The proposed method includes decreased computational complexity and pest detection in green house environment. The whitefly, a bio-aggressor which represents a risk to a huge number of harvests, was picked as the pest of enthusiasm for this paper. The calculation was tried for a few whiteflies influencing various leaves and an accuracy of 96% of whitefly recognition was accomplished.
Keywords: Pest, Clustering, Hybrid Approaches, Segmentation, Classification.
Scope of the Article: Clustering