Agusta, Sandy Wahyu (2023) Penerapan Kombinasi Ekstraksi Fitur Warna dan Gray Level Co- occurance Matrix dalam Metode K-Nearest Neighbor untuk Identifikasi Penyakit Daun Tomat. Other thesis, UPN "Veteran" Yogyajarta.
Text
Daftar Pustaka.pdf Download (2MB) |
|
Text
Abstrak.pdf Download (2MB) |
|
Text
COVER.pdf Download (1MB) |
|
Text
Daftar Isi.pdf Download (2MB) |
|
Text
Halaman Pengesahan Pembimbing.pdf Download (2MB) |
|
Text
Laporan_TA_123190145_SandyWahyuAgusta.pdf Restricted to Repository staff only Download (2MB) |
Abstract
vi
ABSTRAK
Tanaman tomat merupakan komoditas yang cukup penting di Indonesia. Dengan
kandungan zat yang lengkap dan baik, Tomat menjadi produk yang banyak dikonsumsi
oleh masyarakat. Namun banyak penurunan produksi tanaman tersebut yang disebabkan
oleh organisme penganggu tanaman seperti virus dan bakteri. Identifikasi penyakit
tanaman sejak dini diharapkan dapat mencegah tersebarnya penyakit yang disebabkan oleh
organisme tersebut. Penelitian ini menggunakan metode klasifikasi K-Nearest Neighbor
dengan metode kombinasi ekstraksi ciri pada citra RGB, HSV dan GLCM untuk
mendapatkan nilai akurasi yang terbaik.
K-Neirest Neighbor merupakan metode dengan proses pembelajaran supervised
learning. Dengan memanfaatkan nilai ciri terbaik tentu metode ini akan berkembang dan
mendapatkan akurasi yang cukup tinggi dalam proses identifikasi penyakit pada daun
tomat. Namun, metode ekstraksi warna Red Green Blue dan Hue Saturation Value
memiliki akurasi yang masih belum maksimal atau dapat ditingkatkan kembali dengan
pengujian kombinasi metode ekstraksi tekstur Gray Level Co-occurance Matrix. Dengan
tahapan metodologi penelitian yaitu mulai dari analisis kebutuhan, pengumpulan data,
preprocessing data, pemodelan hingga klasifikasi dan pengujian.
Hasil pengujian diantara metode kombinasi ekstraksi fitur dalam proses identifikasi
penyakit daun tomat yang digolongkan menjadi 7 yaitu pengujian satuan RGB, HSV,
GLCM dilanjutkan dengan kombinasi metode RGB HSV, RGB GLCM, HSV GLCM, dan
RGB HSV GLCM didapatkan nilai perbandingan 71.5%, 72.9%, 79%, 82.5%, 90.6%,
87.4% dan 87.7%. Berdasarkan data tersebut, didapatkan kesimpulan bahwa dengan
kombinasi metode RGB GLCM mendapatkan nilai akurasi terbaik dalam identifikasi
penyakit daun tomat dengan tingkat akurasi mencapai 90.6%.
Kata Kunci : Klasifikasi, K-Nearest Neighbor, RGB, HSV, GLCM
vii
ABSTRACT
Tomato plants are quite important commodities in Indonesia. With a complete and
good substance content, tomatoes are a product that is widely consumed by the community.
However, much of the decline in crop production is caused by plant disruptive organisms
such as viruses and bacteria. Early identification of plant diseases is expected to prevent
the spread of diseases caused by these organisms. This study uses the K-Nearest Neighbor
classification method with a combination method of extracting traits on RGB, HSV and
GLCM images to obtain the best accuracy value.
K-Neirest Neighbor is a method with a supervised learning process. By utilizing the
best characteristic values, of course, this method will develop and get a fairly high
accuracy in the process of identifying diseases on tomato leaves. However, the Red Green
Blue and Hue Saturation Value color extraction methods have accuracy that is still not
optimal or can be improved again by testing the combination of the Gray Level Co-
occurance Matrix texture extraction method. With the stages of research methodology,
starting from needs analysis, data collection, data preprocessing, modeling to
classification and testing.
The test results among the combination methods of feature extraction in the process of
identifying tomato leaf diseases which are classified into 7, namely testing units of RGB,
HSV, GLCM followed by a combination of RGB HSV, RGB GLCM, HSV GLCM, and RGB
HSV GLCM methods obtained a comparison value of 71.5%, 72.9%, 79%, 82.5%, 90.6%,
87.4% and 87.7%. Based on these data, it was concluded that with the combination of the
RGB GLCM method obtained the best accuracy value in the identification of tomato leaf
disease with an accuracy rate of 90.6%.
Keywords : Classification, K-Nearest Neighbor, RGB, HSV, GLCM
Item Type: | Thesis (Other) |
---|---|
Uncontrolled Keywords: | Klasifikasi, K-Nearest Neighbor, RGB, HSV, GLCM |
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: | 11 Jul 2023 01:53 |
Last Modified: | 11 Jul 2023 01:53 |
URI: | http://eprints.upnyk.ac.id/id/eprint/36385 |
Actions (login required)
View Item |