Faizal, Iman (2019) Identifikasi Daun Tanaman Durian Berdasarkan Ciri Tekstur Menggunakan Metode K-Nearest Neighbor Berbasis Android. Tugas Akhir thesis, University of Technology Yogyakarta.
|
Text
Iman Faizal_5140411010.pdf Download (10kB) | Preview |
Abstract
Durian is one of the types of fruit plants favored by the community, especially the people of Kulon Progo area. The most widely grown durian species in the area of Kulon Progo is the type of durian Bawor, D101, Montong, Duri Hitam, and Menoreh because it tastes good. This study uses three types of durian namely durian Bawor, D101, and Menoreh as the object of research. Various ways can be done to distinguish the type of durian by looking at the texture of the leaves. The texture of the leaves of the durian type Bawor, D101, and Menoreh have many similarities that are difficult to distinguish from the naked eye. The purpose of this study was to identify durian plant leaves based on texture characteristics using the K-Nearest Neighbor based on Android. The texture feature extraction process uses Angular Second Moment, Contrast, Correlation, Variance, Inverse Difference Moment and Entropy from the Gray Level Co-occurrence Matrix (GLCM) matrix approach. The identification method used is K-Nearest Neighbor by calculating Euclidean distance. The results of the consecutive tests with an accuracy of 53.3%, 66.7%, 60% at K = 7, 15, and 25. The highest accuracy value was found at K = 15, which was 66.7%. Keywords: Durian, Texture Feature Extraction, GLCM, KNN, Android
| Item Type: | Thesis (Skripsi, Tugas Akhir or Kerja Praktek) (Tugas Akhir) |
|---|---|
| Subjects: | T Technology > T Technology (General) |
| Divisions: | Fakultas Sains Dan Teknologi > S1 Informatika |
| Depositing User: | Kaprodi S1 Informatika UTY |
| Date Deposited: | 01 Apr 2019 00:03 |
| Last Modified: | 01 Apr 2019 00:03 |
| URI: | http://eprints.uty.ac.id/id/eprint/2631 |
Actions (login required)
 |
View Item |
