EMAIL: PASSWORD:
Front Office
UPT. PERPUSTAKAAN
Institut Teknologi Sepuluh Nopember Surabaya


Kampus ITS Sukolilo - Surabaya 60111

Phone : 031-5921733 , 5923623
Fax : 031-5937774
E-mail : libits@its.ac.id
Website : http://library.its.ac.id

Support (Customer Service) :
timit_perpus@its.ac.id




Welcome..guys!

Have a problem with your access?
Please, contact our technical support below:
LIVE SUPPORT


Moh. Fandika Aqsa


Davi Wahyuni


Tondo Indra Nyata


Anis Wulandari


Ansi Aflacha




ITS » Undergraduate Theses » Teknik Informatika
Posted by dewi007 at 11/09/2009 15:04:17  •  6246 Views


SISTEM PENGENALAN WAJAH DENGAN MENGGUNAKAN METODE ORTHOGONAL NEIGHBORHOOD PRESERVING DISCRIMINANT ANALYSIS

FACE RECOGNITION SYSTEM USING ORTHOGONAL NEIGHBORHOOD PRESERVING DISCRIMINANT ANALYSIS METHOD

Author :
Imansyah, Rona Fajar ( 5105100083 )




ABSTRAK

Algoritma analisis subspace linier sering digunakan dalam pengenalan wajah. Hal ini karena karakteristiknya yang sederhana dan efisien untuk ekstraksi fitur. Beberapa contoh dari algoritma ini antara lain Principal Component Analysis PCA Linear Discriminant Analysis LDA dan Locality Preserving Projection LPP. Dari ketiga metode tersebut LDA dan LPP mempunyai banyak kelebihan dibanding PCA. Kelebihan LDA adalah memiliki daya pembeda yang lebih besar sedangkan kelebihan LPP adalah dapat mempertahankan geometri intrinsik didalam class. Dua kelebihan ini memunculkan metode lain yang menggabungkan keduanya. Metode ini dinamakan metode Orthogonal Neighborhood Preserving Discriminant Analysis ONPDA. Metode ini memiliki dua karakteristik yaitu supervised yang dibawa oleh LDA dan unsupervised yang dibawa oleh LPP. Dengan menggabungkan kelebihan dari kedua metode yang berbeda sifat ini penggunaan metode ONPDA dapat meningkatkan tingkat akurasi pengenalan wajah. Untuk membuktikan keunggulan metode ONPDA digunakan metode Fisherface sebagai metode pembanding. Kedua metode ini diuji dengan menggunakan Basis Data ORL dan Basis Data YALE. Penggunaan kedua basis data wajah tersebut selain untuk membuktikan keunggulan tingkat akurasi metode ONPDA pada citra yang bervariasi juga untuk mengetahui pengaruh variasi citra terhadap tingkat akurasi. Dari hasil pengujian dan analisa metode ONPDA mampu menghasilkan tingkat akurasi yang lebih baik dari pada metode Fisherface baik pada Basis Data ORL maupun YALE. Namun ONPDA memiliki kekurangan dari segi waktu komputasi. Waktu komputasi ONPDA lebih lama dari pada metode Fisherface.


ABSTRACT

Linear subspace analysis algorithm has been widely used in face recognition. This is due to its simplicity and efficiency for feature extraction. Some example of this algorithm is Principal Component Analysis PCA Linear Discriminant Analysis LDA and Locality Preserving Projection LPP. Between this three method LDA and LPP have more merits than PCA. LDA have more strong discriminating power whereas LPP can preserve intrinsic geometry of in-class data. Both of this merits proposed another method of face recognition. Its called Orthogonal Neighborhood Preserving Discriminant Analysis ONPDA. This method have two characteistic supervised and unsupervised that given by LDA and LPP. The combination of these two method cause ONPDA can increase accuracy of face recognition. This is can be shown using Fisherface as comparison method. ONPDA will be tested using Olivetti Research Laboratory ORL face database and YALE face database. The use of these two face database not only to prove better accuracy of ONPDA but also to find influence of face images variation to accuracy level. According to the test result and analysis ONPDA give better accuracy than Fisherface in ORL and YALE database. However this method also have a defect in computation time. ONPDA spend more time than Fisherface.



KeywordsPengenalan wajah ; Orthogonal Neighborhood Preserving Discriminant Analysis (ONPDA)
 
Subject:  Pengawasan komputer
Contributor
  1. Rully Soelaiman, S.Kom, M.Kom
Date Create: 11/09/2009
Type: Text
Format: pdf.
Language: Indonesian
Identifier: ITS-Undergraduate-3100009035022
Collection ID: 3100009035022
Call Number: RSIf 006.4 Ima s


Source
Undergraduate These sof Informatics Engineering, RSIf 006.4 Ima s, 2009

Coverage
ITS Community Only

Rights
Copyright @2009 by ITS Library. This publication is protected by copyright and permission should be obtained from the ITS Library prior to any prohibited reproduction, storage in a retrievel system, or transmission in any form or by any means, electronic, mechanical, photocopying, recording, or likewise. For information regarding permission(s), write to ITS Library




[ Download - Summary ]

ITS-Undergraduate-3100009035022-5437.pdf




 Similar Document...




! ATTENTION !

To facilitate the activation process, please fill out the member application form correctly and completely

Registration activation of our members will process up to max 24 hours (confirm by email). Please wait patiently

POLLING

Bagaimana pendapat Anda tentang layanan repository kami ?

Bagus Sekali
Baik
Biasa
Jelek
Mengecewakan





You are connected from 18.207.106.142
using CCBot/2.0 (https://commoncrawl.org/faq/)



Copyright © ITS Library 2006 - 2020 - All rights reserved.
Dublin Core Metadata Initiative and OpenArchives Compatible
Developed by Hassan