DETEKSI WAJAH MENGGUNAKAN VIOLA JONES PADA CITRA SMALL FACE

AFRIANA, FITRAH and Erwin, Erwin and Fachrurrozi, M. (2020) DETEKSI WAJAH MENGGUNAKAN VIOLA JONES PADA CITRA SMALL FACE. Undergraduate thesis, Sriwijaya University.

[thumbnail of RAMA_55201_09021381520055.pdf] Text
RAMA_55201_09021381520055.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (6MB) | Request a copy
[thumbnail of RAMA_55201_09021381520055_0029017101_0222058001_01_front_ref.pdf]
Preview
Text
RAMA_55201_09021381520055_0029017101_0222058001_01_front_ref.pdf - Accepted Version
Available under License Creative Commons Public Domain Dedication.

Download (1MB) | Preview
[thumbnail of RAMA_55201_09021381520055_0029017101_0222058001_02.pdf] Text
RAMA_55201_09021381520055_0029017101_0222058001_02.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (779kB) | Request a copy
[thumbnail of RAMA_55201_09021381520055_0029017101_0222058001_03.pdf] Text
RAMA_55201_09021381520055_0029017101_0222058001_03.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (747kB) | Request a copy
[thumbnail of RAMA_55201_09021381520055_0029017101_0222058001_04.pdf] Text
RAMA_55201_09021381520055_0029017101_0222058001_04.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (1MB) | Request a copy
[thumbnail of RAMA_55201_09021381520055_0029017101_0222058001_05.pdf] Text
RAMA_55201_09021381520055_0029017101_0222058001_05.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (4MB) | Request a copy
[thumbnail of RAMA_55201_09021381520055_0029017101_0222058001_06.pdf] Text
RAMA_55201_09021381520055_0029017101_0222058001_06.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (10kB) | Request a copy
[thumbnail of RAMA_55201_09021381520055_0029017101_0222058001_06_ref.pdf] Text
RAMA_55201_09021381520055_0029017101_0222058001_06_ref.pdf - Bibliography
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (297kB) | Request a copy
[thumbnail of RAMA_55201_09021381520055_0029017101_0222058001_07_lamp.pdf] Text
RAMA_55201_09021381520055_0029017101_0222058001_07_lamp.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (460kB) | Request a copy
[thumbnail of RAMA_55201_09021381520055_TURNITIN.pdf] Text
RAMA_55201_09021381520055_TURNITIN.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (10MB) | Request a copy

Abstract

Deteksi wajah adalah deteksi objek berupa wajah yang didalamnya terdapat fitur–fitur khusus yang merepresentasikan bentuk wajah pada umumnya. Small face (wajah kecil) adalah wajah yang sulit dideteksi karena skalanya berukuran kecil dan memiliki tingkat kesulitan deteksi yang tinggi maka dikategorikan sebargai hard face. Penelitian ini menggunakan metode Viola Jones untuk mendeteksi small face. Metode ini mempunyai empat proses utama yaitu, integral image, haar-like feature, adaboost, dan cascade classifier. Haar-like feature merupakan kumpulan fitur khusus yang merepresentasikan wajah dan integral image adalah cara cepat menghitung haar feature. Sedangkan adaboost adalah pembobotan secara statistik nilai–nilai fitur yang didapat menggunakan cascade classifier. Hasil terakhir berupa deteksi–deteksi yang lolos cascade classifier. Data citra yang digunakan dalam penelitian ini adalah single frontal face yang berformat Portable Network Graphics (.png). Dari hasil penelitian, didapat bahwa metode Viola Jones mempunyai hasil akurasi yang bersumber dari data primer untuk ukuran 24 x 24 piksel sebesar 72,94%, ukuran 48 x 48 piksel sebesar 62,35%, dan ukuran 72 x 72 piksel sebesar 70,58%. Sedangkan metode Viola Jones sumber dari data sekunder menghasilkan hasil nilai akurasi untuk ukuran 24 x 24 piksel sebesar 38,57%, ukuran 48 x 48 piksel sebesar 77,14%, dan ukuran 72 x 72 piksel sebesar 77,14%.

Item Type: Thesis (Undergraduate)
Uncontrolled Keywords: Deteksi Wajah, Small Face, Single Frontal Face, Viola Jones, Haar-Like Feature, Integral Image, Adaboost, Cascade Clasifier.
Subjects: Q Science > Q Science (General) > Q334-342 Computer science. Artificial intelligence. Algorithms. Robotics. Automation.
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 7481 not found.
Date Deposited: 18 Aug 2020 07:21
Last Modified: 18 Aug 2020 07:21
URI: http://repository.unsri.ac.id/id/eprint/33303

Actions (login required)

View Item View Item