LEWAR, Yovita Sili Tepo (2024) Klasifikasi Citra Warna Bunga Euphorbia Milli Menggunakan Mesin Learning. Undergraduate thesis, Universitas Katolik Widya Mandira Kupang.
Text
ABSTRAK.pdf Download (545kB) |
|
Text
BAB I.pdf Download (138kB) |
|
Text
BAB II.pdf Download (222kB) |
|
Text
BAB III.pdf Download (205kB) |
|
Text
BAB IV.pdf Download (1MB) |
|
Text
BAB V.pdf Download (329kB) |
|
Text
BAB VI.pdf Download (37kB) |
|
Text
DAFTAR PUSTAKA.pdf Download (152kB) |
Abstract
Euphorbia milli flowers are ornamental plants that are easy to find in home gardens and public places. In this research, the image of the Euphorbia milli flower is an interesting object to classify by comparing two methods, namely K-NN and Naïve Bayes. The purpose of comparing the two methods is to determine the level of accuracy of the classification results of the two methods. The dataset with a total of 2832 images was divided into four samples consisting of 708 red images, 708 yellow images, 708 pink images, and 708 white images. The methods used to calcify the image of the Euphorbia milli flower are the K-NN method and the Naïve Bayes method. The results of the classification using the K-NN method obtained an accuracy level of 97.2% and the results of the Naïve Bayes classification obtained an accuracy level of 76.2%. These accuracy results are obtained through the results of the confusion matrix performance in the Orange Data Mining application through a classification process, namely image import, image viewer, image embedding, data table, and test and score. The K-NN method has a higher level of accuracy than the Naïve Bayes method. Keywords: Classification, Flower Image, K-NN and Naïve Bayes.
Item Type: | Thesis (Undergraduate) |
---|---|
Uncontrolled Keywords: | Kata Kunci: Klasifikasi, Citra Bunga, K-NN dan Naïve Bayes. |
Subjects: | T Technology > TN Mining engineering. Metallurgy T Technology > TR Photography |
Divisions: | Fakultas Teknik > Program Studi Ilmu Komputer |
Depositing User: | Yovita Sili Tepo Lewar |
Date Deposited: | 27 May 2024 01:25 |
Last Modified: | 27 May 2024 01:25 |
URI: | http://repository.unwira.ac.id/id/eprint/16183 |
Actions (login required)
View Item |