PENGENALAN TULISAN TANGAN KARAKTER KERINCI MENGGUNAKAN SPEEDED UP ROBUST FEATURES DAN K-NEAREST NEIGHBORS

ISWARI, SAYEKTI DYAH and Samsuryadi, Samsuryadi and Miraswan, Kanda Januar (2019) PENGENALAN TULISAN TANGAN KARAKTER KERINCI MENGGUNAKAN SPEEDED UP ROBUST FEATURES DAN K-NEAREST NEIGHBORS. Undergraduate thesis, Sriwijaya University.

	Text RAMA_55201_09021281520096.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (3MB) | Request a copy
	Text RAMA_55201_09021281520096_TURNITIN.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (15MB) | Request a copy
Preview	Text RAMA_55201_09021281520096_0004027101_0009019002_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (1MB) | Preview
	Text RAMA_55201_09021281520096_0004027101_0009019002_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (849kB) | Request a copy
	Text RAMA_55201_09021281520096_0004027101_0009019002_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (541kB) | Request a copy
	Text RAMA_55201_09021281520096_0004027101_0009019002_04.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (1MB) | Request a copy
	Text RAMA_55201_09021281520096_0004027101_0009019002_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (816kB) | Request a copy
	Text RAMA_55201_09021281520096_0004027101_0009019002_06.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (185kB) | Request a copy
	Text RAMA_55201_09021281520096_0004027101_0009019002_06_ref.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (129kB) | Request a copy
	Text RAMA_55201_09021281520096_0004027101_0009019002_07_lamp.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (394kB) | Request a copy

Abstract

Budaya Indonesia memiliki kekayaan yang beraneka ragam. Hal ini menyebabkan Indonesia memiliki banyak aksara kuno, salah satunya aksara Kerinci yang berasal dari Provinsi Jambi. Aksara/karakter kuno merupakan salah satu warisan budaya yang perlu dilestarikan. Penelitian ini dilakukan sebagai salah satu upaya untuk melesetarikan karakter Kerinci melalui pendekatan teknologi. Hal ini dimaksudkan untuk mempermudah mengenali karakter Kerinci secara cepat. Penelitian ini menggunakan metode Speeded Up Robust Features (SURF) sebagai ekstraksi ciri dan K-Nearest Neighbor (K-NN) sebagai metode klasifikasi. Perangkat lunak yang dikembangkan menunjukkan karakter Latin dari karakter Kerinci yang dikenali. Dilakukan tiga pengujian terhadap 336 citra data uji dengan nilai threshold yang berbeda yaitu; 0.001, 0,005, dan 0,009. Nilai akurasi tertinggi yang diperoleh dari pengujian tersebut adalah 70 % dengan nilai threshold 0.009.

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	Pengenalan Pola, Pengolahan Citra, SURF, K-NN
Subjects:	T Technology > T Technology (General) > T1-995 Technology (General) T Technology > TA Engineering (General). Civil engineering (General) > TA1501-1820 Applied optics. Photonics > TA1632.A48 Image processing. T Technology > TA Engineering (General). Civil engineering (General) > TA1501-1820 Applied optics. Photonics > TA1632.B35 Image processing--Digital techniques. Pattern recognition systems
Divisions:	09-Faculty of Computer Science > 55201-Informatics (S1)
Depositing User:	Users 3529 not found.
Date Deposited:	05 Dec 2019 08:35
Last Modified:	05 Dec 2019 08:35
URI:	http://repository.unsri.ac.id/id/eprint/20156

Actions (login required)

View Item