Segmentation and classification of plant disease using SVM–PSO in cloud

Citations of this article
Mendeley users who have this article in their library.
Get full text


Area of agriculture plant disease detection attracts is very important one, main role is diseases detection. To develop the plant diseases detection, it required to identify arrival of the diseases in the leaf and instruction to the agriculturalists. In this proposed work, a leaf disease detection system (LDDS) based on Otsu segment (OS) is developed to identify and classify the diseases in the set of leaves. Clustering scheme is offered from segmented image of the diseased leaf. Otsu segmentation is measured the size of segmented leaf are uploaded to less storage place. In observing location, the amounts are retrieved as well as the features are extracted from the original segmented image. The enhancement as well as classification is used to SVM based on PSO classifier. The overall design of this paper is LDDS take scan be calculated in terms of system efficiency and it is compared with the existing methods. The result indicates the research technique offers a whole detection accuracy of 90.5% and classification accuracy of 90.4%.




Raghavendran, S., Kumar, P., & Silambarasan, K. (2019). Segmentation and classification of plant disease using SVM–PSO in cloud. International Journal of Engineering and Advanced Technology, 9(1), 2242–2247.

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Save time finding and organizing research with Mendeley

Sign up for free