SVM-based Pest Classification in Agriculture Field
B. Divya1, M. Santhi2
1B. Divya, Department of Electronics and Communication Engineering, Saranathan College of Engineering, Trichy (Tamil Nadu), India.
2M. Santhi, Department of Electronics and Communication Engineering, Saranathan College of Engineering, Trichy (Tamil Nadu), India.
Manuscript received on 23 April 2019 | Revised Manuscript received on 02 May 2019 | Manuscript Published on 08 May 2019 | PP: 150-155 | Volume-7 Issue-5S3 February 2019 | Retrieval Number: E11280275S19/19©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: Integrated Pest Management is currently used to reduce the use of harmful pesticides and chemicals in the agriculture environment. However, the early detection of pest and controlling of the pest population is the critical task and time consuming process and the judgment is mostly based on the manual process which is highly prone for error. In this paper, an image based classification is used to for detection and classification of the pest species which is commonly available in the felid. Digital images were obtained. Detection of pest in the images, segmentation, feature extraction was performed by the algorithms for the detected pest. Finally, SVM was used for classification and results were compared with K-Neural Network. Compared to the KNN, SVM achieved accurate results with combined features with accuracy as its metrics.
Keywords: IPM, Pest, GLCM, LTP, CCV, SVM.
Scope of the Article: Classification