KLASIFIKASI JENIS DAUN JERUK MENGGUNAKAN ALGORITMA SUPPORT VECTOR MACHINE (SVM)

Aji, Pangestu (2023) KLASIFIKASI JENIS DAUN JERUK MENGGUNAKAN ALGORITMA SUPPORT VECTOR MACHINE (SVM). Other thesis, UPN "Veteran" Yogyajarta.

	Text 2. Cover_123160197_Pangestu Aji.pdf Download (588kB)
	Text 3. Abstrak_123160197_Pangestu Aji.pdf Download (16kB)
	Text 4. Lembar Pengesahan_123160197_Pangestu Aji.pdf Download (947kB)
	Text 6. Daftar Pustaka_123160197_Pangestu Aji.pdf Download (124kB)

Abstract

vii
ABSTRAK
Daun jeruk terdiri dari berbagai macam jenis varietas, antara lain varietas Purut, Bali.Daun
jeruk terdiri dari berbagai macam jenis varietas, antara lain varietas Purut, Bali. Jenis varietas
daun jeruk dapat memiliki banyak kesamaan bentuk, ukuran dan warna hampir sama satu dengan
yang lain, hal ini menunjukkan keragaman genetik yang cukup luas yang ada pada daun jeruk.
Sehingga dari kasat mata masyarakat sulit untuk membedakan antara jenis varietas daun jeruk
yang satu dengan yang lain walaupun berbeda jenisnya. Seiring berjalannya perkembangan
teknologi yang sangat pesat banyak dimanfaatkan termasuk di bidang pertanian. Perkembangan
teknologi menjadi upaya utama dalam menyelesaikan masalah dalam dunia pertanian. Untuk itu,
diperlukan sistem yang juga mampu mengenali varietas jenis daun jeruk secara akurat sehingga
dapat digunakan dalam mengenali jenis varietas daun jeruk.
Dalam proses klasifikasi beberapa tahap dilakukan, Pengolahan citra diawali dengan
melakukan resizing, dilanjutkan dengan mengkonversi citra rgb menjadi grayscale. Kemudian
dilakukan segmentasi menggunakan algoritma k-means clustering. Setelah itu dilakukan
ekstraksi ciri menggunakan parameter metric dan eccentricity. Tahapan terakhir adalah
klasifikasi menggunakan algoritma Support Vector Machine (SVM).
Tujuan dari penelitian ini adalah mengklasifikasi Support Vector Machine ciri fitur
menggunakan Metric dan Eccentrycity dapat mengklasifikasikan jenis jeruk bali dan, daun jeruk
purut dengan nilai kernel terbaik pada kernel Gaussian dengan akurasi terbaik sebesar 97%, presisi
97%, dan recall 100%.
KATA KUNCI : Metode support vector machine, k-means clustering,resizing, graycale, binery,
background removel, metric dan eccentricity.
viii
ABSTRACT
Tangerine leaves consist of various types of varieties, including the Purut variety, Bali.
Types of lime leaf varieties can have many similarities in shape, size and color, almost the same
as one another, this shows the wide genetic diversity that exists in lime leaves. So that from the
naked eye it is difficult for the public to distinguish between types of lime leaf varieties from
one another even though they are of different types. Along with the development of technology
that is very rapidly widely used, including in agriculture. Technological developments are the
main effort in solving problems in the world of agriculture. For this reason, a system is needed
that is also able to accurately identify varieties of lime leaves so that they can be used to identify
varieties of lime leaves.
In the classification process, several stages are carried out. Image processing begins with
resizing, followed by converting the rgb image to grayscale. Then segmentation is performed
using the k-means clustering algorithm. After that, feature extraction is performed using metric
and eccentricity parameters. The final stage is classification using the Support Vector Machine
(SVM) algorithm.
The purpose of this study is to classify the Support Vector Machine feature using Metric
and Eccentrycity to classify grapefruit and kaffir lime leaves with the best kernel value in the
Gaussian kernel with the best accuracy of 97%, 97% precision, and 100% recall.
KEYWORD: Support vector machine method, k-means clustering, resizing, grayscale, binary,
background removel, metric and eccentricity.

Item Type:	Thesis (Other)
Uncontrolled Keywords:	Support vector machine method, k-means clustering, resizing, grayscale, binary, background removel, metric and eccentricity.
Subjects:	Z Bibliography. Library Science. Information Resources > ZA Information resources
Divisions:	Faculty of Engineering, Science and Mathematics > School of Engineering Sciences
Depositing User:	Eko Yuli
Date Deposited:	10 May 2023 02:24
Last Modified:	11 May 2023 02:47
URI:	http://eprints.upnyk.ac.id/id/eprint/35111

Actions (login required)

View Item