Record Details

KLASIFIKASI LEVEL KEMATANGAN BUAH TOMAT BERDASARKAN FITUR WARNA MENGGUNAKAN MULTI-SVM

Jurnal Ilmiah Informatika

View Archive Info
 
 
Field Value
 
Title KLASIFIKASI LEVEL KEMATANGAN BUAH TOMAT BERDASARKAN FITUR WARNA MENGGUNAKAN MULTI-SVM
 
Creator Riska, Suastika Yulia
Subekti, Puji
 
Subject classification
multi-svm
knn
tomato
adaptive histogram equalization
 
Description Grouping of tomato maturity level is one way to pay attention to the quality of the tomatoes. The traditional way takes a long time and low accuracy, since the determination of the level of subjectively assessed. In addition, the importance of the classification of the level of maturity of tomatoes due to a period of tomato maturation process is relatively quick, so it can reduce the risk of rotting tomatoes. The dataset used in this study was 108 tomato image taken using three types of smartphones. The dataset is divided into 66 training data and testing the data 42. Improvements to the image preprocessing stage is done with adaptive histogram equalization and compared with the histogram equalization. In the feature extraction using color features of the R, G, and A *. The classification of the level of maturity of tomato is done by comparing the accuracy of using multi-SVM and KNN. In the Multi-SVM method using the highest percentage of kernel functions RBG is equal to 77.84%. While the method kNN highest percentage was 77.79% using a value of k = 3.
 
Publisher Department of Science and Technology Ibrahimy University
 
Date 2016-06-18
 
Type info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
Peer-reviewed Article
 
Format application/pdf
 
Identifier https://journal.ibrahimy.ac.id/index.php/JIMI/article/view/442
10.35316/jimi.v1i1.442
 
Source Jurnal Ilmiah Informatika; Vol. 1 No. 1 (2016): Jurnal Imliah Informatika; 39-45
2549-6301
2549-7480
10.35316/jimi.v1i1
 
Language ind
 
Relation https://journal.ibrahimy.ac.id/index.php/JIMI/article/view/442/426
 
Rights Copyright (c) 2016 Jurnal Ilmiah Informatika
https://creativecommons.org/licenses/by-nc/4.0