Reduced Set Kernel Principal Component Analysis (Rskpca) Algorithm for Palm Print Based Mobile Biometric System

Reduced Set Kernel Principal Component Analysis (Rskpca) Algorithm for Palm Print Based Mobile Biometric System

Kemunculan baru dimensi internet dan teknologi tanpa wayar telah membawa era baru dalam teknologi biometrik. Selain sistem biometrik dengan peranti statik, sistem biometrik mudah alih boleh dilaksanakan dan pendekatan ini membawa kepada pelaksanaan yang lebih cekap dan efisien. Dalam kajian ini,...

Full description

Saved in:
Bibliographic Details
Main Author: Ibrahim, Noor Salwani
Format: Thesis
Language:English
Published: 2015
Subjects:
T Technology
TK7800-8360 Electronics
Online Access:http://eprints.usm.my/40766/1/Reduced_Set_Kernel_Principal_Component_Analysis_%28Rskpca%29_Algorithm_for_Palm_Print_Based_Mobile_Biometric_System.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
id my-usm-ep.40766
record_format uketd_dc
spelling my-usm-ep.407662018-06-12T06:56:40Z Reduced Set Kernel Principal Component Analysis (Rskpca) Algorithm for Palm Print Based Mobile Biometric System 2015-05 Ibrahim, Noor Salwani T Technology TK7800-8360 Electronics Kemunculan baru dimensi internet dan teknologi tanpa wayar telah membawa era baru dalam teknologi biometrik. Selain sistem biometrik dengan peranti statik, sistem biometrik mudah alih boleh dilaksanakan dan pendekatan ini membawa kepada pelaksanaan yang lebih cekap dan efisien. Dalam kajian ini, sistem biometrik mudah alih berasaskan tapak tangan telah dibangunkan. Walau bagaimanapun, untuk melaksanakan sistem biometrik mudah alih, masa pemprosesan dan penyimpanan yang cekap adalah faktor penting yang perlu dipertimbangkan.Dalam kajian ini, beberapa algoritma yang melibatkan pemprosesan ciri tapak tangan dinilai berdasarkan penggunaan masa dan memori yang optimum. Beberapa kaedah pemprosesan ciri termasuk Ruang Dikehendaki (ROI), Analisa Komponen Utama (PCA) dan Analisa Komponen Utama Kernel (KPCA) disiasat. Pendekatan baru dalam pengekstrakan ciri yang digelar Analisa Komponen Utama Kernel Set Dikurangi (RSKPCA) dicadangkan untuk mempercepatkan pemprosesan pengekstrakan ciri. RSKPCA yang dicadangkan menggunakan anggaran Kepadatan set Dikurangkan (RSDE) untuk menentukan matriks gram yang wajar. Hasilnya, RSKPCA hanya mengekstrak maklumat yang paling relevan dan penting dari set data. 2400 imej tapak tangan yang telah dikumpul daripada tiga jenis peranti Android mudah alih. Penilaian eksperimen menunjukkan bahawa RSKPCA yang dicadangkan mempunyai prestasi lebih baik berbanding ROI, PCA dan KPCA dengan Kadar Penerimaan Tulen (GAR) adalah lebih daripada 98% dan masa pemadanan kurang daripada 0.5s. Projek ini telah membuktikan bahawa pengektsrakan ciri menggunakan RSKPCA yang dicadangkan memberikan keputusan yang terbaik untuk sistem biometrik mudah alih berasaskan imej tapak tangan. ________________________________________________________________________________________________________________________ The emerging of internet and wireless dimension has brought a new era in biometrics technology. Instead of operating the biometric system with static biometric device, mobile biometric system can be implemented and this approach leads to more efficient and reliable implementation. In this study mobile biometric system based on palm print modality is developed. However, in order to execute mobile biometric system, efficient processing time and storage are some of the important factors that need to be considered. In this research, algorithms involving palm print feature processing are evaluated so as to obtain optimum time and memory consumption. Several feature processing methods including Region of Interest (ROI), Principal Component Analysis (PCA), and Kernel Principal Component Analysis (KPCA) are investigated. A new approach in feature extraction called Reduced-Set Kernel Principal Component Analysis (RSKPCA) is proposed to speed up the processing in feature extraction. The proposed RSKPCA employs a Reduced Set Density Estimate (RSDE) to define a weighted gram matrix. As a result, the RSKPCA only extracts the most relevant and important information from a dataset. 2400 palm print images which were collected from three types of android mobile are employed. Experimental evaluation shows that the proposed RSKPCA has better performance compared to the ROI, PCA and KPCA with the Genuine Acceptance Rates (GAR) is more than 98% and the matching time is less than 0.5s. In this project, it has been proven that the proposed RSKPCA as feature extraction gives the best result for mobile biometric system based on palm print. 2015-05 Thesis http://eprints.usm.my/40766/ http://eprints.usm.my/40766/1/Reduced_Set_Kernel_Principal_Component_Analysis_%28Rskpca%29_Algorithm_for_Palm_Print_Based_Mobile_Biometric_System.pdf application/pdf en public masters Universiti Sains Malaysia Pusat Pengajian Kejuruteraan Elektrik Dan Elektronik
institution Universiti Sains Malaysia
collection USM Institutional Repository
language English
topic T Technology
TK7800-8360 Electronics
spellingShingle T Technology
TK7800-8360 Electronics
Ibrahim, Noor Salwani
Reduced Set Kernel Principal Component Analysis (Rskpca) Algorithm for Palm Print Based Mobile Biometric System
description Kemunculan baru dimensi internet dan teknologi tanpa wayar telah membawa era baru dalam teknologi biometrik. Selain sistem biometrik dengan peranti statik, sistem biometrik mudah alih boleh dilaksanakan dan pendekatan ini membawa kepada pelaksanaan yang lebih cekap dan efisien. Dalam kajian ini, sistem biometrik mudah alih berasaskan tapak tangan telah dibangunkan. Walau bagaimanapun, untuk melaksanakan sistem biometrik mudah alih, masa pemprosesan dan penyimpanan yang cekap adalah faktor penting yang perlu dipertimbangkan.Dalam kajian ini, beberapa algoritma yang melibatkan pemprosesan ciri tapak tangan dinilai berdasarkan penggunaan masa dan memori yang optimum. Beberapa kaedah pemprosesan ciri termasuk Ruang Dikehendaki (ROI), Analisa Komponen Utama (PCA) dan Analisa Komponen Utama Kernel (KPCA) disiasat. Pendekatan baru dalam pengekstrakan ciri yang digelar Analisa Komponen Utama Kernel Set Dikurangi (RSKPCA) dicadangkan untuk mempercepatkan pemprosesan pengekstrakan ciri. RSKPCA yang dicadangkan menggunakan anggaran Kepadatan set Dikurangkan (RSDE) untuk menentukan matriks gram yang wajar. Hasilnya, RSKPCA hanya mengekstrak maklumat yang paling relevan dan penting dari set data. 2400 imej tapak tangan yang telah dikumpul daripada tiga jenis peranti Android mudah alih. Penilaian eksperimen menunjukkan bahawa RSKPCA yang dicadangkan mempunyai prestasi lebih baik berbanding ROI, PCA dan KPCA dengan Kadar Penerimaan Tulen (GAR) adalah lebih daripada 98% dan masa pemadanan kurang daripada 0.5s. Projek ini telah membuktikan bahawa pengektsrakan ciri menggunakan RSKPCA yang dicadangkan memberikan keputusan yang terbaik untuk sistem biometrik mudah alih berasaskan imej tapak tangan. ________________________________________________________________________________________________________________________ The emerging of internet and wireless dimension has brought a new era in biometrics technology. Instead of operating the biometric system with static biometric device, mobile biometric system can be implemented and this approach leads to more efficient and reliable implementation. In this study mobile biometric system based on palm print modality is developed. However, in order to execute mobile biometric system, efficient processing time and storage are some of the important factors that need to be considered. In this research, algorithms involving palm print feature processing are evaluated so as to obtain optimum time and memory consumption. Several feature processing methods including Region of Interest (ROI), Principal Component Analysis (PCA), and Kernel Principal Component Analysis (KPCA) are investigated. A new approach in feature extraction called Reduced-Set Kernel Principal Component Analysis (RSKPCA) is proposed to speed up the processing in feature extraction. The proposed RSKPCA employs a Reduced Set Density Estimate (RSDE) to define a weighted gram matrix. As a result, the RSKPCA only extracts the most relevant and important information from a dataset. 2400 palm print images which were collected from three types of android mobile are employed. Experimental evaluation shows that the proposed RSKPCA has better performance compared to the ROI, PCA and KPCA with the Genuine Acceptance Rates (GAR) is more than 98% and the matching time is less than 0.5s. In this project, it has been proven that the proposed RSKPCA as feature extraction gives the best result for mobile biometric system based on palm print.
format Thesis
qualification_level Master's degree
author Ibrahim, Noor Salwani
author_facet Ibrahim, Noor Salwani
author_sort Ibrahim, Noor Salwani
title Reduced Set Kernel Principal Component Analysis (Rskpca) Algorithm for Palm Print Based Mobile Biometric System
title_short Reduced Set Kernel Principal Component Analysis (Rskpca) Algorithm for Palm Print Based Mobile Biometric System
title_full Reduced Set Kernel Principal Component Analysis (Rskpca) Algorithm for Palm Print Based Mobile Biometric System
title_fullStr Reduced Set Kernel Principal Component Analysis (Rskpca) Algorithm for Palm Print Based Mobile Biometric System
title_full_unstemmed Reduced Set Kernel Principal Component Analysis (Rskpca) Algorithm for Palm Print Based Mobile Biometric System
title_sort reduced set kernel principal component analysis (rskpca) algorithm for palm print based mobile biometric system
granting_institution Universiti Sains Malaysia
granting_department Pusat Pengajian Kejuruteraan Elektrik Dan Elektronik
publishDate 2015
url http://eprints.usm.my/40766/1/Reduced_Set_Kernel_Principal_Component_Analysis_%28Rskpca%29_Algorithm_for_Palm_Print_Based_Mobile_Biometric_System.pdf
_version_ 1747820818465816576

Similar Items