PENGENALAN WAJAH MANUSIA DENGAN VARIASI PENCAHAYAAN MENGGUNAKAN METODE LOCAL BINARY PATTERN (LBP)

HUDA, MOCHAMAD MIFTAKHUL (2020) PENGENALAN WAJAH MANUSIA DENGAN VARIASI PENCAHAYAAN MENGGUNAKAN METODE LOCAL BINARY PATTERN (LBP). S1 thesis, Universitas Mercu Buana.

[img]
Preview
Text (HAL COVER)
1. COVER.pdf

Download (777kB) | Preview
[img] Text (BAB I)
2. BAB 1.pdf
Restricted to Registered users only

Download (72kB)
[img] Text (BAB II)
3. BAB 2.pdf
Restricted to Registered users only

Download (532kB)
[img] Text (BAB III)
4. BAB 3.pdf
Restricted to Registered users only

Download (180kB)
[img] Text (BAB IV)
5. BAB 4.pdf
Restricted to Registered users only

Download (316kB)
[img] Text (BAB V)
6. BAB 5.pdf
Restricted to Registered users only

Download (31kB)
[img] Text (DAFTAR PUSTAKA)
7. DAFTAR PUSTAKA.pdf
Restricted to Registered users only

Download (56kB)
[img] Text (LAMPIRAN)
8. LAMPIRAN.pdf
Restricted to Registered users only

Download (478kB)

Abstract

In 2020, developments in technology and science are running very rapidly, especially in the multimedia field. Applications that use images and videos are increasingly diverse, some are for security, business and sales, even for a company's database. The facial recognition system is a biometric technique that allows a computer or machine to recognize human faces through a digital image by matching facial patterns with a stored database. The facial recognition system for various lighting has problems with facial recognition system performance, especially in lighting. An example of the case is in a smartphone who have problems with the facial recognition system in dark room conditions. This study aims to develop a facial recognition system in the problem of lighting variations in order to improve the accuracy of the facial recognition system in recognizing the user's face smartphone. This system will use methods Local Binary Pattern (LBP), and will be combined with several Pre-Processes, namely Histogram Equalization, Sharpening, Gaussian Filter, and Median Filter which functions as feature extraction in human face recognition with variations in lighting. Then this system adds a classification feature using the method Nearest Neightbor which serves to classify human faces into predetermined classes. This human face recognition process uses 4 experiments with each Pre Process, where the first experiment is Pre Process Histogram + Local Binary Pattern Equalization and Classification nearest neighbor get good accuracy results, namely 80%, Second Trial Pre Process Sharpening + Local Binary Pattern and Classification nearest neighbor get good accuracy results, namely 80%, the third trial Pre Process Gaussian Filter + Local Binary Pattern and Classification nearest neighbor get good accuracy results, namely 80%, and the fourth trial is Pre Process Median Filter + Local Binary Pattern and Classification nearest neighbor get a good accuracy of 80%. With the average percentage results, get an accuracy percentage of 80%. Keywords: Local Binary Pattern, Matlab, Extended Yale B, k-Nearest Neighbor, Pre Process. Pada tahun 2020, perkembangan di bidang teknologi dan sains berjalan dengan sangat pesat, terutama di bidang multimedia. Aplikasi penggunaan gambar dan video semakin beragam macamnya, ada yang untuk keamanan, bisnis dan penjualan, bahkan untuk basis data sebuah perusahaan. Sistem pengenalan wajah adalah teknik biometrik yang memungkinkan komputer atau mesin untuk mengenal wajah manusia melalui sebuah gambar digital dengan cara mencocokan pola wajah dengan basis data yang tersimpan. Sistem pengenalan wajah variasi pencahayaan mempunyai kendala pada performa sistem pengenalan wajah, terutama pada pencahayaan. Contoh kasus nya ada pada sebuah smartphone yang mempunyai masalah pada sistem pengenalan wajah pada kondisi ruangan yang gelap. Penelitian ini bertujuan untuk mengembangkan sistem pengenalan wajah dalam permasalahan variasi pencahayaan agar dapat meningkatkan performa keakuratan sistem pengenalan wajah dalam mengenal wajah penggua smartphone. Sistem ini akan menggunakan metode Local Binary Pattern (LBP), dan akan di kombinasikan dengan beberapa Pra Proses, yaitu Ekualisasi Histogram, Sharpening, Gaussian Filter, dan Median Filter yang berfungsi sebagai ekstrasi fitur dalam pengenalan wajah manusia dengan variasi pencahayaan. Kemudian sistem ini menambahkan fitur klasifikasi menggunakan metode Nearest Neightbor yang berfungsi untuk pengklasifikasian wajah manusia ke dalam class class yang sudah ditentukan. Proses pengenalan wajah manusia ini menggunakan 4 percobaan dengan masing-masing Pra Proses, dimana percobaan pertama adalah Pra Proses Ekualisasi Histogram + Local Binary Pattern dan Klasifikasi nearest neighbor mendapatkan hasil akurasi yang bagus yaitu 80%, Percobaan kedua Pra Proses Sharpening + Local Binary Pattern dan Klasifikasi nearest neighbor mendapatkan hasil akurasi yang bagus yaitu 80%, percobaan ketiga Pra Proses Gaussian Filter + Local Binary Pattern dan Klasifikasi nearest neighbor mendapatkan hasil akurasi yang bagus yaitu 80%, dan percobaan yang ke empat Pra Proses Median Filter + Local Binary Pattern dan Klasifikasi nearest neighbor mendapatkan hasil akurasi yang bagus yaitu 80%. Dengan hasil persentasi rata-rata mendapakan hasil persentase akurasi sebesar 80%. Kata Kunci: Local Binary Pattern, Matlab, Extended Yale B, k-Nearest Neighbor, Pra Proses

Item Type: Thesis (S1)
Call Number CD: FT/ELK. 20 244
Call Number: ST/14/21/009
NIM/NIDN Creators: 41416010011
Uncontrolled Keywords: Local Binary Pattern, Matlab, Extended Yale B, k-Nearest Neighbor, Pra Proses
Subjects: 000 Computer Science, Information and General Works/Ilmu Komputer, Informasi, dan Karya Umum > 000. Computer Science, Information and General Works/Ilmu Komputer, Informasi, dan Karya Umum > 003 Systems/Sistem-sistem > 003.1 System Identification/Identifikasi Sistem
000 Computer Science, Information and General Works/Ilmu Komputer, Informasi, dan Karya Umum > 000. Computer Science, Information and General Works/Ilmu Komputer, Informasi, dan Karya Umum > 005 Computer Programmming, Programs, Data/Pemprograman Komputer, Program, Data > 005.4 System Programming and Programs/Sistem Pemrograman dan Program > 005.43 Operating System/Sistem Operasi > 005.432 Specific Operating Systems/Sistem Operasi Tertentu
500 Natural Science and Mathematics/Ilmu-ilmu Alam dan Matematika > 530 Physics/Fisika > 535 Light, Infrared and Ultraviolet Phenomena/Cahaya Optik, Infra Merah dan Fenomena Ultraviolet > 535.1 Theories of Light/Teori tentang Cahaya
600 Technology/Teknologi > 620 Engineering and Applied Operations/Ilmu Teknik dan operasi Terapan > 621 Applied Physics/Fisika terapan > 621.3 Electrical Engineering, Lighting, Superconductivity, Magnetic Engineering, Applied Optics, Paraphotic Technology, Electronics Communications Engineering, Computers/Teknik Elektro, Pencahayaan, Superkonduktivitas, Teknik Magnetik, Optik Terapan, Tekn
Divisions: Fakultas Teknik > Teknik Elektro
Depositing User: Dede Muksin Lubis
Date Deposited: 06 Feb 2022 15:52
Last Modified: 15 Apr 2023 02:36
URI: http://repository.mercubuana.ac.id/id/eprint/55473

Actions (login required)

View Item View Item