Information fusion of face and palm-print multimodal biometric at matching score level

Multimodal biometric systems that integrate the biometric traits from several modalities are able to overcome the limitations of single modal biometrics. Fusing the information at the middle stage by consolidating the information given by different traits can give a better result due to the richnes...

Full description

Saved in:

Bibliographic Details
Main Author:	Mohammed Elzaroug, Alshrief
Format:	Thesis
Language:	English
Subjects:	Multimodal biometric systems Biometric Fusion Palm-print
Online Access:	http://dspace.unimap.edu.my:80/xmlui/bitstream/123456789/59422/1/Page%201-24.pdf http://dspace.unimap.edu.my:80/xmlui/bitstream/123456789/59422/2/Full%20text.pdf
Tags:	Add Tag No Tags, Be the first to tag this record!

id	my-unimap-59422
record_format	uketd_dc
spelling	my-unimap-594222019-04-10T04:03:20Z Information fusion of face and palm-print multimodal biometric at matching score level Mohammed Elzaroug, Alshrief Dr. Muhammad Imran Ahmad Multimodal biometric systems that integrate the biometric traits from several modalities are able to overcome the limitations of single modal biometrics. Fusing the information at the middle stage by consolidating the information given by different traits can give a better result due to the richness of information at this stage. In this thesis, an information fusion at matching score level is used to integrate face and palm-print modalities. Three types of matching score rule are used which is sum, product and minimum rule. A linear statistical projection method based on the principle component analysis (PCA) is used to capture the important information and reduce feature dimension in the feature space. A fusion process is performed using matching score computed using Euclidean distance classifier. The experiment is conducted using a benchmark ORL face and PolyU palm-print dataset to examine the recognition rates of the propose technique. The best recognition rate is 98.96% achieved by using sum rule fusion method. Recognition rate can also be improved by increasing number of training images and number of PCA coefficients. Universiti Malaysia Perlis (UniMAP) 2014 Thesis en http://dspace.unimap.edu.my:80/xmlui/handle/123456789/59422 http://dspace.unimap.edu.my:80/xmlui/bitstream/123456789/59422/1/Page%201-24.pdf 7188ac09a30fd193ce1989896fbeaea5 http://dspace.unimap.edu.my:80/xmlui/bitstream/123456789/59422/2/Full%20text.pdf 2bfcf262db4e16aab701a405cafbeabb http://dspace.unimap.edu.my:80/xmlui/bitstream/123456789/59422/3/license.txt 8a4605be74aa9ea9d79846c1fba20a33 Multimodal biometric systems Biometric Fusion Palm-print School of Computer and Communication
institution	Universiti Malaysia Perlis
collection	UniMAP Institutional Repository
language	English
advisor	Dr. Muhammad Imran Ahmad
topic	Multimodal biometric systems Biometric Fusion Palm-print
spellingShingle	Multimodal biometric systems Biometric Fusion Palm-print Mohammed Elzaroug, Alshrief Information fusion of face and palm-print multimodal biometric at matching score level
description	Multimodal biometric systems that integrate the biometric traits from several modalities are able to overcome the limitations of single modal biometrics. Fusing the information at the middle stage by consolidating the information given by different traits can give a better result due to the richness of information at this stage. In this thesis, an information fusion at matching score level is used to integrate face and palm-print modalities. Three types of matching score rule are used which is sum, product and minimum rule. A linear statistical projection method based on the principle component analysis (PCA) is used to capture the important information and reduce feature dimension in the feature space. A fusion process is performed using matching score computed using Euclidean distance classifier. The experiment is conducted using a benchmark ORL face and PolyU palm-print dataset to examine the recognition rates of the propose technique. The best recognition rate is 98.96% achieved by using sum rule fusion method. Recognition rate can also be improved by increasing number of training images and number of PCA coefficients.
format	Thesis
author	Mohammed Elzaroug, Alshrief
author_facet	Mohammed Elzaroug, Alshrief
author_sort	Mohammed Elzaroug, Alshrief
title	Information fusion of face and palm-print multimodal biometric at matching score level
title_short	Information fusion of face and palm-print multimodal biometric at matching score level
title_full	Information fusion of face and palm-print multimodal biometric at matching score level
title_fullStr	Information fusion of face and palm-print multimodal biometric at matching score level
title_full_unstemmed	Information fusion of face and palm-print multimodal biometric at matching score level
title_sort	information fusion of face and palm-print multimodal biometric at matching score level
granting_institution	Universiti Malaysia Perlis (UniMAP)
granting_department	School of Computer and Communication
url	http://dspace.unimap.edu.my:80/xmlui/bitstream/123456789/59422/1/Page%201-24.pdf http://dspace.unimap.edu.my:80/xmlui/bitstream/123456789/59422/2/Full%20text.pdf
_version_	1747836835923492864

Information fusion of face and palm-print multimodal biometric at matching score level

Similar Items