%0 Journal Article
%@ 978-979-96880-8-8
%A Etriana Meirista, .
%A Imam Mukhlash, .
%A Budi Setiyono, .
%D 2015
%F UNY:23298
%I Faculty of Mathematics and Sciences Yogyakarta State University
%J Proceeding of  International Conference On Research, Implementation And Education  Of Mathematics And Sciences 2015 (ICRIEMS 2015), Yogyakarta State University, 17-19 May 2015
%T WATERMELON PLANT CLASSIFICATION BASED ON SHAPE AND TEXTURE FEATURE LEAF USING SUPPORT VECTOR MACHINE (SVM)
%U http://eprints.uny.ac.id/23298/
%X Nowadays, some efforts are used to increase results of agriculture production. One of those is utilizing herbisides to exterminate the weeds. However, there are some of the weeds having resemblance with the plant, with the result that we need to classify the plant and the weeds before utilizing herbisides as an extermination weeds. In this paper, we use watermelon plant classification as case study. The recognition of the plant owned by the similarity of leaves of these plants are divided into three phases. At the first phase we perform preprocessing to convert the RGB image into a grayscale images. Further, the grayscale images are changed into segmentation of edge detection using Canny operator. In the second, we use feature extraction to retrieve important informations for the recognition of those leaves. The last phase we classify that leaves as watermelon plants or weeds using Support Vector Machine (SVM) algorithm. The results of early trials indicate that this method has an accuracy of 91,3%.   Keywords : image, leaf, edge detection, feature extraction, and plant classification esults of early trials