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 » Master Theses » Teknik Informatika - S2
Posted by dewi007 at 04/12/2009 19:59:10  •  4793 Views


PENERAPAN SUBRUANG ORTHOGONAL PADA PENGENALAN WAJAH MENGGUNAKAN LAPLACIANFACES

AN APPLICATION OF ORTHOGONAL SUBSPACES IN FACE RECOGNITION USING LAPLACIANFACES

Author :
Marti, Ni Wayan ( 5104201015 )




ABSTRAK

Sistem pengenalan wajah yang baik sangat diperlukan untuk identifikasi personal berbasis pengenalan wajah yang dapat dimanfaatkan pada suatu sistem pengamanan elektronik. Keuntungan dari sistem pengamanan berbasis pengenalan wajah adalah kemampuan pengamanannya yang relatif sulit untuk ditembus. Penelitian ini berupaya meningkatkan kemampuan diskriminasi dan mendapatkan akurasi pengenalan wajah yang lebih baik dengan menggunakan Metode Orthogonal Laplacianfaces. Metode Principal Component Analysis PCA digunakan untuk mereduksi dimensi untuk menghasilkan vektor basis orthogonal yang disebut eigenfaces. Locality Preserving Projection LPP merupakan metode linier yang dapat menemukan manifold nonlinier data pada dimensi rendah. Vektor basis yang dihasilkan disebut Laplacianfaces. Laplacianfaces tidak memenuhi syarat orthonormal. Untuk mendapatkan hasil pengenalan yang lebih baik akan dibangun sebuah subruang wajah yang direntang oleh vector-vektor basis orthogonal yang disebut dengan Orthogonal Laplacianfaces. Orthogonal Laplacianfaces diperoleh dari proses iterasi pada pemecahan permasalahan vektor eigen dari LPP orthogonal. Percobaan pada penelitian ini dilakukan menggunakan tiga basis data wajah baku yaitu Yale The University of Bern UB dan ORL yang telah dinormalisasi. Hasil percobaan menunjukkan bahwa metode Orthogonal Laplacianfaces memperoleh tingkat pengenalan yang paling baik. Tingkat pengenalan optimal yang diperoleh Eigenfaces Laplacianfaces dan Orthogonal Laplacianfaces menggunakan Basis Data Yale masing-masing adalah 82.67 86.67 dan 94.67. Tingkat pengenalan optimal yang diperoleh Eigenfaces Laplacianfaces dan Orthogonal Laplacianfaces menggunakan Basis Data UB masing-masing adalah 86.90 91.67 dan 98.81. Dan tingkat pengenalan optimal yang diperoleh Eigenfaces Laplacianfaces dan Orthogonal Laplacianfaces menggunakan Basis Data ORL masing-masing adalah 87.50 92.50 dan 99.17.


ABSTRACT

Personal identification system based on face recognition which has a good rate recognition can be used in electronical security system. Advantage of security system based on face recognition is the protection system very well. The purpose of this research is to improve the capability of discrimination and to obtain better accuracy of face recognition by using Orthogonal Laplacianfaces Method. Principal Component Analysis Method PCA is used to reduce dimension to obtain the orthonormal basis vectors which is called Eigenfaces. Locality Preserving Projection LPP is a linear method which is able to find nonlinear manifold of data at low dimension. Basis vectors which are yielded is called Laplacianfaces. The Laplacianfaces does not have orthoonormal. To obtain the better result of recognition we will be builded a face subspace spanned orthogonal basis vectors which is called Orthogonal Laplacianfaces. The Orthogonal Laplacianfaces are obtaind from iterative process on solving of eigenvector problem of orthogonal LPP. The experiment in this research confronted using three normalized face databases i.e. Yale The University of Bern UB and ORL databases. The experiment results show that Orthogonal Laplacianfaces is the best method for face recognition. The optimal recognition accuracy of Eigenfaces Laplacianfaces and Orthogonal Laplacianfaces using Yale database are 82.67 86.67 and 94.67 respectively. The optimal recognition accuracy of Eigenfaces Laplacianfaces and Orthogonal Laplacianfaces using UB database are 86.90 91.67 and 98.81 respectively. And the optimal recognition accuracy of Eigenfaces Laplacianfaces and Orthogonal Laplacianfaces using ORL database are 87.50 92.50 and 99.17 respectively.



KeywordsPCA ; LPP ; Eigenfaces ; Laplacianfaces ; Orthogonal Laplacianfaces ; Subruang Orthogonal
 
Subject:  Pengawasan komputer
Contributor
  1. Rully Soelaiman, S.Kom, M.Kom
Date Create: 04/12/2009
Type: Text
Format: pdf.
Language: Indonesian
Identifier: ITS-master-3100006027882
Collection ID: 3100006027882
Call Number: RTIf 006.4 Mar p


Source
Master Theses of Informatics Engineeirng, RTIf 006.4 Mar p, 2006

Coverage
ITS Community Only

Rights
Copyright @2006 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-master-3100006027882-5770.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 34.234.207.100
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