publication . Article . 2020

Automatic Tomato Plant Leaf Disease Classification using Multi-Kernel Support Vector Machine

Jayanthi M. G; D R Shashikumar;
Open Access English
  • Published: 30 Jun 2020
  • Publisher: Zenodo
Abstract
In agriculture the major problem is leaf disease identifying these disease in early stage increases the yield. To reduce the loss identifying the various disease is very important. In this work , an efficient technique for identifying unhealthy tomato leaves using a machine learning algorithm is proposed. Support Vector Machines (SVM) is the methodology of machine learning , and have been successfully applied to a number of applications to identify region of interest, classify the region. The proposed algorithm has three main staggers, namely preprocessing, feature extraction and classification. In preprocessing, the images are converted to RGB and the average filter is used to eliminate the noise in the input image. After the pre-processing stage, features such as texture, color and shape are extracted from each image. Then, the extracted features are presented to the classifier to classify an input tomato leaf as a healthy or unhealthy image. For classification, in this paper, a multi-kernel support vector machine (MKSVM) is used. The performance of the proposed method is analysed on the basis of different metrics, such as accuracy, sensitivity and specificity. The images used in the test are collected from the plant village. The proposed method implemented in MATLAB.
Persistent Identifiers
Subjects
free text keywords: Tomato, Leaf disease, plant, median filter, texture, colour, shape, multi-kernel support vector machine., 2249-8958, E9689069520/2020©BEIESP, Computer Science Applications, General Engineering, Environmental Engineering, Multi kernel, Support vector machine, Median filter, Texture (geology), Leaf disease, Computer science, Pattern recognition, Artificial intelligence, business.industry, business
Any information missing or wrong?Report an Issue