Recognizing faces with normalized local Gabor features and Spiking Neuron Patterns

Gabor Wavelets (GW) have been extensively used for facial feature representation due to its inherent multi-resolution and multi-orientation characteristics. In this work we extend the work on Local Gabor Feature Vector (LGFV) and propose a new face recognition method called LGFV//LN//SNP, which empl...

Full description

Bibliographic Details
Main Authors:	Kamaruzaman, Fadhlan, Shafie, Amir Akramin
Format:	Article
Language:	English English
Published:	Elsevier 2016
Subjects:	TK7800 Electronics. Computer engineering. Computer hardware. Photoelectronic devices
Online Access:	http://irep.iium.edu.my/49551/ http://irep.iium.edu.my/49551/ http://irep.iium.edu.my/49551/ http://irep.iium.edu.my/49551/1/1-s2.0-S0031320315004409-main.pdf http://irep.iium.edu.my/49551/4/49551_Recognizing%20faces_wos_scopus.pdf

id	iium-49551
recordtype	eprints
spelling	iium-495512016-12-20T08:48:45Z http://irep.iium.edu.my/49551/ Recognizing faces with normalized local Gabor features and Spiking Neuron Patterns Kamaruzaman, Fadhlan Shafie, Amir Akramin TK7800 Electronics. Computer engineering. Computer hardware. Photoelectronic devices Gabor Wavelets (GW) have been extensively used for facial feature representation due to its inherent multi-resolution and multi-orientation characteristics. In this work we extend the work on Local Gabor Feature Vector (LGFV) and propose a new face recognition method called LGFV//LN//SNP, which employs local normalization filter in pre-processing stage. We propose a novel Spiking Neuron Patterns (SNP) as a dimensionality reduction method to reduce the dimensions of local Gabor features. {SNP} is acquired from projection of LGFV//LN features using Spike Response Model (SRM), a neuron model describing the spike behavior of a biological neuron. Results on AR, FERET, Yale B and {FRGC} 2.0 face datasets showed that {SNP} implementation delivered significant improvement in accuracy. Comparisons with several previously published results also suggested that LGFV//LN//SNP achieved better results in some tests. Additionally, LGFV//LN//SNP requires relatively smaller number of {GW} than LGFV//LN to produce optimal results. Elsevier 2016-05 Article PeerReviewed application/pdf en http://irep.iium.edu.my/49551/1/1-s2.0-S0031320315004409-main.pdf application/pdf en http://irep.iium.edu.my/49551/4/49551_Recognizing%20faces_wos_scopus.pdf Kamaruzaman, Fadhlan and Shafie, Amir Akramin (2016) Recognizing faces with normalized local Gabor features and Spiking Neuron Patterns. Pattern Recognition, 53. 102 - 115. ISSN 0031-3203 http://www.sciencedirect.com/science/article/pii/S0031320315004409 doi:10.1016/j.patcog.2015.11.020
repository_type	Digital Repository
institution_category	Local University
institution	International Islamic University Malaysia
building	IIUM Repository
collection	Online Access
language	English English
topic	TK7800 Electronics. Computer engineering. Computer hardware. Photoelectronic devices
spellingShingle	TK7800 Electronics. Computer engineering. Computer hardware. Photoelectronic devices Kamaruzaman, Fadhlan Shafie, Amir Akramin Recognizing faces with normalized local Gabor features and Spiking Neuron Patterns
description	Gabor Wavelets (GW) have been extensively used for facial feature representation due to its inherent multi-resolution and multi-orientation characteristics. In this work we extend the work on Local Gabor Feature Vector (LGFV) and propose a new face recognition method called LGFV//LN//SNP, which employs local normalization filter in pre-processing stage. We propose a novel Spiking Neuron Patterns (SNP) as a dimensionality reduction method to reduce the dimensions of local Gabor features. {SNP} is acquired from projection of LGFV//LN features using Spike Response Model (SRM), a neuron model describing the spike behavior of a biological neuron. Results on AR, FERET, Yale B and {FRGC} 2.0 face datasets showed that {SNP} implementation delivered significant improvement in accuracy. Comparisons with several previously published results also suggested that LGFV//LN//SNP achieved better results in some tests. Additionally, LGFV//LN//SNP requires relatively smaller number of {GW} than LGFV//LN to produce optimal results.
format	Article
author	Kamaruzaman, Fadhlan Shafie, Amir Akramin
author_facet	Kamaruzaman, Fadhlan Shafie, Amir Akramin
author_sort	Kamaruzaman, Fadhlan
title	Recognizing faces with normalized local Gabor features and Spiking Neuron Patterns
title_short	Recognizing faces with normalized local Gabor features and Spiking Neuron Patterns
title_full	Recognizing faces with normalized local Gabor features and Spiking Neuron Patterns
title_fullStr	Recognizing faces with normalized local Gabor features and Spiking Neuron Patterns
title_full_unstemmed	Recognizing faces with normalized local Gabor features and Spiking Neuron Patterns
title_sort	recognizing faces with normalized local gabor features and spiking neuron patterns
publisher	Elsevier
publishDate	2016
url	http://irep.iium.edu.my/49551/ http://irep.iium.edu.my/49551/ http://irep.iium.edu.my/49551/ http://irep.iium.edu.my/49551/1/1-s2.0-S0031320315004409-main.pdf http://irep.iium.edu.my/49551/4/49551_Recognizing%20faces_wos_scopus.pdf
first_indexed	2023-09-18T21:10:02Z
last_indexed	2023-09-18T21:10:02Z
_version_	1777411191146020864

Recognizing faces with normalized local Gabor features and Spiking Neuron Patterns

Similar Items