Data Augmentation for Face Recognition System Implemented in Multiple Transform Domains

A face recognition system which represents each of the augmented facial images as a superposition of the dominant components in two transform domains is proposed. Each face in the spatial domain is divided into horizontal, vertical halves and diagonal format. These partitions are concatenated to gen...

Full description

Saved in:
Bibliographic Details
Main Authors: Chehata, Ramy C.G., Mikhael, Wasfy B.
Format: Conference Proceeding
Language:English
Subjects:
DCT
Discrete cosine transforms
Discrete wavelet transforms
DWT
Face
FERET
Mutual Approach
ORL
Training
Two dimensional displays
Two Transform Domains
Yale
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by
cites
container_end_page 206
container_issue
container_start_page 203
container_title
container_volume
creator Chehata, Ramy C.G.
Mikhael, Wasfy B.
description A face recognition system which represents each of the augmented facial images as a superposition of the dominant components in two transform domains is proposed. Each face in the spatial domain is divided into horizontal, vertical halves and diagonal format. These partitions are concatenated to generate four more faces per subject in any database used. All images are first preprocessed then compressed using two different domains. The Discrete Wavelet Transform (DWT) and the Discrete Cosine Transform (DCT). Accordingly, each face will have two feature matrices. A voting scheme is used to define ground truth identity. The performance of the proposed system is evaluated using k-fold cross validation of ORL, Yale and FERET databases. Sample results are presented. The proposed technique achieves higher recognition rates while retaining 74% savings in storage recently reported.
doi_str_mv 10.1109/MWSCAS.2019.8885339
format conference_proceeding
fullrecord <record><control><sourceid>ieee_CHZPO</sourceid><recordid>TN_cdi_ieee_primary_8885339</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>8885339</ieee_id><sourcerecordid>8885339</sourcerecordid><originalsourceid>FETCH-LOGICAL-i203t-8c86c037c6920e134186f28907ebcfdc373886a08d9d92a2da03c8dae05a58f83</originalsourceid><addsrcrecordid>eNotkM1OwkAUhUcTExF5AjbzAq13ZmznzrIpoiQQE4thSa7TWzKmP6QtC95eVFYn-XK-szhCzBXESoF72uyKPCtiDcrFiJgY427EzFlUVqPSFhFuxUQlCUYGnbsXD8PwDaCNVW4idgsaSWanQ8PtSGPoWll1vVySZ_nBvju04Q8W52HkRq6aY82_VS5laOXmVI_hQuS2p3a4iI1cdA2FdngUdxXVA8-uORWfy5dt_hat319XebaOggYzRugx9WCsT50GVuZZYVppdGD5y1elN9YgpgRYutJp0iWB8VgSQ0IJVmimYv6_G5h5f-xDQ_15f_3B_ADQRFK_</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Data Augmentation for Face Recognition System Implemented in Multiple Transform Domains</title><source>IEEE Xplore All Conference Series</source><creator>Chehata, Ramy C.G. ; Mikhael, Wasfy B.</creator><creatorcontrib>Chehata, Ramy C.G. ; Mikhael, Wasfy B.</creatorcontrib><description>A face recognition system which represents each of the augmented facial images as a superposition of the dominant components in two transform domains is proposed. Each face in the spatial domain is divided into horizontal, vertical halves and diagonal format. These partitions are concatenated to generate four more faces per subject in any database used. All images are first preprocessed then compressed using two different domains. The Discrete Wavelet Transform (DWT) and the Discrete Cosine Transform (DCT). Accordingly, each face will have two feature matrices. A voting scheme is used to define ground truth identity. The performance of the proposed system is evaluated using k-fold cross validation of ORL, Yale and FERET databases. Sample results are presented. The proposed technique achieves higher recognition rates while retaining 74% savings in storage recently reported.</description><identifier>EISSN: 1558-3899</identifier><identifier>EISBN: 9781728127880</identifier><identifier>EISBN: 1728127882</identifier><identifier>DOI: 10.1109/MWSCAS.2019.8885339</identifier><language>eng</language><publisher>IEEE</publisher><subject>DCT ; Discrete cosine transforms ; Discrete wavelet transforms ; DWT ; Face ; FERET ; Mutual Approach ; ORL ; Training ; Two dimensional displays ; Two Transform Domains ; Yale</subject><ispartof>2019 IEEE 62nd International Midwest Symposium on Circuits and Systems (MWSCAS), 2019, p.203-206</ispartof><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/8885339$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,777,781,786,787,27906,54536,54913</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/8885339$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Chehata, Ramy C.G.</creatorcontrib><creatorcontrib>Mikhael, Wasfy B.</creatorcontrib><title>Data Augmentation for Face Recognition System Implemented in Multiple Transform Domains</title><title>2019 IEEE 62nd International Midwest Symposium on Circuits and Systems (MWSCAS)</title><addtitle>MWSCAS</addtitle><description>A face recognition system which represents each of the augmented facial images as a superposition of the dominant components in two transform domains is proposed. Each face in the spatial domain is divided into horizontal, vertical halves and diagonal format. These partitions are concatenated to generate four more faces per subject in any database used. All images are first preprocessed then compressed using two different domains. The Discrete Wavelet Transform (DWT) and the Discrete Cosine Transform (DCT). Accordingly, each face will have two feature matrices. A voting scheme is used to define ground truth identity. The performance of the proposed system is evaluated using k-fold cross validation of ORL, Yale and FERET databases. Sample results are presented. The proposed technique achieves higher recognition rates while retaining 74% savings in storage recently reported.</description><subject>DCT</subject><subject>Discrete cosine transforms</subject><subject>Discrete wavelet transforms</subject><subject>DWT</subject><subject>Face</subject><subject>FERET</subject><subject>Mutual Approach</subject><subject>ORL</subject><subject>Training</subject><subject>Two dimensional displays</subject><subject>Two Transform Domains</subject><subject>Yale</subject><issn>1558-3899</issn><isbn>9781728127880</isbn><isbn>1728127882</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2019</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><recordid>eNotkM1OwkAUhUcTExF5AjbzAq13ZmznzrIpoiQQE4thSa7TWzKmP6QtC95eVFYn-XK-szhCzBXESoF72uyKPCtiDcrFiJgY427EzFlUVqPSFhFuxUQlCUYGnbsXD8PwDaCNVW4idgsaSWanQ8PtSGPoWll1vVySZ_nBvju04Q8W52HkRq6aY82_VS5laOXmVI_hQuS2p3a4iI1cdA2FdngUdxXVA8-uORWfy5dt_hat319XebaOggYzRugx9WCsT50GVuZZYVppdGD5y1elN9YgpgRYutJp0iWB8VgSQ0IJVmimYv6_G5h5f-xDQ_15f_3B_ADQRFK_</recordid><startdate>201908</startdate><enddate>201908</enddate><creator>Chehata, Ramy C.G.</creator><creator>Mikhael, Wasfy B.</creator><general>IEEE</general><scope>6IE</scope><scope>6IH</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIO</scope></search><sort><creationdate>201908</creationdate><title>Data Augmentation for Face Recognition System Implemented in Multiple Transform Domains</title><author>Chehata, Ramy C.G. ; Mikhael, Wasfy B.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i203t-8c86c037c6920e134186f28907ebcfdc373886a08d9d92a2da03c8dae05a58f83</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2019</creationdate><topic>DCT</topic><topic>Discrete cosine transforms</topic><topic>Discrete wavelet transforms</topic><topic>DWT</topic><topic>Face</topic><topic>FERET</topic><topic>Mutual Approach</topic><topic>ORL</topic><topic>Training</topic><topic>Two dimensional displays</topic><topic>Two Transform Domains</topic><topic>Yale</topic><toplevel>online_resources</toplevel><creatorcontrib>Chehata, Ramy C.G.</creatorcontrib><creatorcontrib>Mikhael, Wasfy B.</creatorcontrib><collection>IEEE Electronic Library (IEL) Conference Proceedings</collection><collection>IEEE Proceedings Order Plan (POP) 1998-present by volume</collection><collection>IEEE Xplore All Conference Proceedings</collection><collection>IEEE Xplore (Online service)</collection><collection>IEEE Proceedings Order Plans (POP) 1998-present</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Chehata, Ramy C.G.</au><au>Mikhael, Wasfy B.</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Data Augmentation for Face Recognition System Implemented in Multiple Transform Domains</atitle><btitle>2019 IEEE 62nd International Midwest Symposium on Circuits and Systems (MWSCAS)</btitle><stitle>MWSCAS</stitle><date>2019-08</date><risdate>2019</risdate><spage>203</spage><epage>206</epage><pages>203-206</pages><eissn>1558-3899</eissn><eisbn>9781728127880</eisbn><eisbn>1728127882</eisbn><abstract>A face recognition system which represents each of the augmented facial images as a superposition of the dominant components in two transform domains is proposed. Each face in the spatial domain is divided into horizontal, vertical halves and diagonal format. These partitions are concatenated to generate four more faces per subject in any database used. All images are first preprocessed then compressed using two different domains. The Discrete Wavelet Transform (DWT) and the Discrete Cosine Transform (DCT). Accordingly, each face will have two feature matrices. A voting scheme is used to define ground truth identity. The performance of the proposed system is evaluated using k-fold cross validation of ORL, Yale and FERET databases. Sample results are presented. The proposed technique achieves higher recognition rates while retaining 74% savings in storage recently reported.</abstract><pub>IEEE</pub><doi>10.1109/MWSCAS.2019.8885339</doi><tpages>4</tpages></addata></record>
fulltext fulltext_linktorsrc
identifier EISSN: 1558-3899
ispartof 2019 IEEE 62nd International Midwest Symposium on Circuits and Systems (MWSCAS), 2019, p.203-206
issn 1558-3899
language eng
recordid cdi_ieee_primary_8885339
source IEEE Xplore All Conference Series
subjects DCT
Discrete cosine transforms
Discrete wavelet transforms
DWT
Face
FERET
Mutual Approach
ORL
Training
Two dimensional displays
Two Transform Domains
Yale
title Data Augmentation for Face Recognition System Implemented in Multiple Transform Domains
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-19T09%3A13%3A25IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-ieee_CHZPO&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=Data%20Augmentation%20for%20Face%20Recognition%20System%20Implemented%20in%20Multiple%20Transform%20Domains&rft.btitle=2019%20IEEE%2062nd%20International%20Midwest%20Symposium%20on%20Circuits%20and%20Systems%20(MWSCAS)&rft.au=Chehata,%20Ramy%20C.G.&rft.date=2019-08&rft.spage=203&rft.epage=206&rft.pages=203-206&rft.eissn=1558-3899&rft_id=info:doi/10.1109/MWSCAS.2019.8885339&rft.eisbn=9781728127880&rft.eisbn_list=1728127882&rft_dat=%3Cieee_CHZPO%3E8885339%3C/ieee_CHZPO%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-i203t-8c86c037c6920e134186f28907ebcfdc373886a08d9d92a2da03c8dae05a58f83%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=8885339&rfr_iscdi=true