SURADIPURWO, ANUGRAH (2013) PERBANDINGAN KINERJA EKSTRAKSI FITUR TINGKAT RENDAH MENGGUNAKAN METODE Gray Level Co-occurrence Matrix (GLCM) dan GABOR FILTER DALAM PENGENALAN MOTIF BATIK. S1 thesis, Universitas Mercu Buana.
|
Text (HAL COVER)
Cover.pdf Download (241kB) | Preview |
|
|
Text (ABSTRAK)
Abstrak.pdf Download (101kB) | Preview |
|
![[img]](https://repository.mercubuana.ac.id/style/images/fileicons/text.png) |
Text (BAB I)
BAB 1 - PENDAHULUAN.pdf Restricted to Registered users only Download (110kB) |
|
|
Text (BAB II)
BAB 2 - LANDASAN TEORI.pdf Restricted to Registered users only Download (561kB) |
|
|
Text (BAB III)
BAB 3 - METODOLOGI PENELITIAN.pdf Restricted to Registered users only Download (448kB) |
|
|
Text (BAB IV)
BAB 4 - HASIL DAN PEMBAHASAN.pdf Restricted to Registered users only Download (479kB) |
|
|
Text (BAB V)
BAB 5 - KESIMPULAN DAN SARAN.pdf Restricted to Registered users only Download (100kB) |
|
|
Text (DAFTAR PUSTAKA DAN LAMPIRAN)
DAFTAR PUSTAKA DAN LAMPIRAN.pdf Restricted to Registered users only Download (519kB) |
Abstract
Salah satu cara untuk mengenali citra adalah dengan membedakan tekstur citra tersebut. Citra dikatakan memiliki tekstur apabila pola citra terjadi secara berulang-ulang memenuhi semua bidang citra. Citra yang berbeda memiliki ciriciri yang berbeda. Ciri-ciri inilah yang menjadi dasar dalam klasifikasi citra berdasarkan tekstur. Sudah banyak metode pengenalan citra yang digunakan untuk pengenalan suatu citra. Pada Tugas Akhir ini akan dibahas bagaimana mengekstraksi fitur motif batik pada kawung dan parang dengan menggunakan metode Gray Level Co-Occurrence Matrix (GLCM) dan metode Gabor Filter. Hasil ekstraksi tersebut akan dihitung menggunakan Euclidean Distance pada nilai mean dan standar deviasi. Dari hasil penelitian yang dilakukan, disimpulkan bahwa metode Gabor Filter berdasarkan nilai standar deviasi memiliki akurasi pengenalan citra lebih besar. Pengujian dilakukan berdasarkan citra latih. Data penelitian menunjukkan akurasi pengenalan citra pada metode Gabor Filter berdasarkan nilai standar deviasi sebesar 80% dari pengujian menggunakan 20 citra latih. Kata kunci : tekstur, Gray Level Co-Occurrence Matrix, Gabor Filter, jarak euclidean, akurasi pengenalan. Another way to recognize the image is by making differentiation of the image texture itself. The image would be textured if the image patern accours contstanly repeat and comply all the image segment. Different image would have different characteristics. This characteristics would be the foundation for the image clasification based on texture. There have been many methode image recognation that are introduced. This final project will be discussed about how to extract the features of Batik motif on kawung and parang by using the Gray Level Co-Occurrence Matrix (GLCM) and the Gabor filter method. The extraction results will be calculated by using the Euclidean Distance on the value of mean and the standard deviation . From the research that has been conducted, it was concluded that a Gabor filter method that use based on standard deviation values have less image recognition accuracy. The research conducted based on trained image. Research data shows the image recognition accuracy method based on Gabor filter standard deviation of 80% from test using 20 training images. Keyword : texture, Gray Level Co-Occurrence Matrix, Gabor Filter, Euclidean Distance, recognition accuracy.
Actions (login required)
 |
View Item |
