Loading…

Sub-pattern non-negative matrix factorization based on random subspace for face recognition

Non-negative matrix factorization (NMF) as a part-based representation method allows only additive combinations of non-negative basis components to represent the original data, so it provides a realistic approximation to the original data. However, NMF does not work well when directly applied to fac...

Full description

Saved in:
Bibliographic Details
Main Author: Yu-Lian Zhu
Format: Conference Proceeding
Language:English
Subjects:
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by
cites
container_end_page 1360
container_issue
container_start_page 1356
container_title
container_volume 3
creator Yu-Lian Zhu
description Non-negative matrix factorization (NMF) as a part-based representation method allows only additive combinations of non-negative basis components to represent the original data, so it provides a realistic approximation to the original data. However, NMF does not work well when directly applied to face recognition due to its global linear decomposition; this intuitively results in a degradation of recognition performance and non-robustness to the variation in illumination, expression and occlusion. In this paper, we propose a robust method, random subspace sub-pattern NMF (RS-SpNMF), especially for face recognition. Unlike the traditional random subspace method (RSM), which completely randomly selects the features from the whole original pattern feature set, the proposed method randomly samples features from each local region (or a sub-image) partitioned from the original face image and performs NMF decomposition on each sampled feature set. More specially, we first divide a face image into several sub-images in a deterministic way, then construct a component classifier on sampled feature subset from each sub-image set, and finally combine all of component classifiers for the final decision. Experiments on three benchmarks face databases (ORL, Yale and AR) show that the proposed method is effective, especially to the occlusive face image.
doi_str_mv 10.1109/ICWAPR.2007.4421645
format conference_proceeding
fullrecord <record><control><sourceid>ieee_CHZPO</sourceid><recordid>TN_cdi_ieee_primary_4421645</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>4421645</ieee_id><sourcerecordid>4421645</sourcerecordid><originalsourceid>FETCH-LOGICAL-i175t-25533323be9331223de90a18d917fdbdee33dec6d3e9f8760ccaf966e6780f9d3</originalsourceid><addsrcrecordid>eNo1UN1KwzAYjajgnH2C3eQFWpN8SdpcjqFuMFD8wQsvRtp8GRGbjrQT9entcJ6b88PhXBxCZpwVnDNzvVq8zh8eC8FYWUgpuJbqhFxyKaTkTGt1SjJTVv9e8TMyEVxVudJGXZCs79_ZCKmgkjAhb0_7Ot_ZYcAUaexiHnFrh_CJtLVDCl_U22boUvgZwy7S2vbo6CiSja5rab-v-51tkPouHapIEzbdNoZD-4qce_vRY3bkKXm5vXleLPP1_d1qMV_ngZdqyIVSACCgRgPAhQCHhlleOcNL72qHCGPUaAdofFVq1jTWG61RlxXzxsGUzP52AyJudim0Nn1vjt_AL_ByV60</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Sub-pattern non-negative matrix factorization based on random subspace for face recognition</title><source>IEEE Xplore All Conference Series</source><creator>Yu-Lian Zhu</creator><creatorcontrib>Yu-Lian Zhu</creatorcontrib><description>Non-negative matrix factorization (NMF) as a part-based representation method allows only additive combinations of non-negative basis components to represent the original data, so it provides a realistic approximation to the original data. However, NMF does not work well when directly applied to face recognition due to its global linear decomposition; this intuitively results in a degradation of recognition performance and non-robustness to the variation in illumination, expression and occlusion. In this paper, we propose a robust method, random subspace sub-pattern NMF (RS-SpNMF), especially for face recognition. Unlike the traditional random subspace method (RSM), which completely randomly selects the features from the whole original pattern feature set, the proposed method randomly samples features from each local region (or a sub-image) partitioned from the original face image and performs NMF decomposition on each sampled feature set. More specially, we first divide a face image into several sub-images in a deterministic way, then construct a component classifier on sampled feature subset from each sub-image set, and finally combine all of component classifiers for the final decision. Experiments on three benchmarks face databases (ORL, Yale and AR) show that the proposed method is effective, especially to the occlusive face image.</description><identifier>ISSN: 2158-5695</identifier><identifier>ISBN: 9781424410651</identifier><identifier>ISBN: 1424410657</identifier><identifier>EISBN: 1424410665</identifier><identifier>EISBN: 9781424410668</identifier><identifier>DOI: 10.1109/ICWAPR.2007.4421645</identifier><language>eng</language><publisher>IEEE</publisher><subject>Degradation ; Face recognition ; Feature extraction ; Lighting ; LNMF ; NMF ; Pattern analysis ; Pattern recognition ; PCA ; Robustness ; RS-SpNMF ; Spatial databases ; SpNMF ; SpPCA ; Voting ; Wavelet analysis</subject><ispartof>2007 International Conference on Wavelet Analysis and Pattern Recognition, 2007, Vol.3, p.1356-1360</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/4421645$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,780,784,789,790,2058,27925,54555,54920,54932</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/4421645$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Yu-Lian Zhu</creatorcontrib><title>Sub-pattern non-negative matrix factorization based on random subspace for face recognition</title><title>2007 International Conference on Wavelet Analysis and Pattern Recognition</title><addtitle>ICWAPR</addtitle><description>Non-negative matrix factorization (NMF) as a part-based representation method allows only additive combinations of non-negative basis components to represent the original data, so it provides a realistic approximation to the original data. However, NMF does not work well when directly applied to face recognition due to its global linear decomposition; this intuitively results in a degradation of recognition performance and non-robustness to the variation in illumination, expression and occlusion. In this paper, we propose a robust method, random subspace sub-pattern NMF (RS-SpNMF), especially for face recognition. Unlike the traditional random subspace method (RSM), which completely randomly selects the features from the whole original pattern feature set, the proposed method randomly samples features from each local region (or a sub-image) partitioned from the original face image and performs NMF decomposition on each sampled feature set. More specially, we first divide a face image into several sub-images in a deterministic way, then construct a component classifier on sampled feature subset from each sub-image set, and finally combine all of component classifiers for the final decision. Experiments on three benchmarks face databases (ORL, Yale and AR) show that the proposed method is effective, especially to the occlusive face image.</description><subject>Degradation</subject><subject>Face recognition</subject><subject>Feature extraction</subject><subject>Lighting</subject><subject>LNMF</subject><subject>NMF</subject><subject>Pattern analysis</subject><subject>Pattern recognition</subject><subject>PCA</subject><subject>Robustness</subject><subject>RS-SpNMF</subject><subject>Spatial databases</subject><subject>SpNMF</subject><subject>SpPCA</subject><subject>Voting</subject><subject>Wavelet analysis</subject><issn>2158-5695</issn><isbn>9781424410651</isbn><isbn>1424410657</isbn><isbn>1424410665</isbn><isbn>9781424410668</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2007</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><recordid>eNo1UN1KwzAYjajgnH2C3eQFWpN8SdpcjqFuMFD8wQsvRtp8GRGbjrQT9entcJ6b88PhXBxCZpwVnDNzvVq8zh8eC8FYWUgpuJbqhFxyKaTkTGt1SjJTVv9e8TMyEVxVudJGXZCs79_ZCKmgkjAhb0_7Ot_ZYcAUaexiHnFrh_CJtLVDCl_U22boUvgZwy7S2vbo6CiSja5rab-v-51tkPouHapIEzbdNoZD-4qce_vRY3bkKXm5vXleLPP1_d1qMV_ngZdqyIVSACCgRgPAhQCHhlleOcNL72qHCGPUaAdofFVq1jTWG61RlxXzxsGUzP52AyJudim0Nn1vjt_AL_ByV60</recordid><startdate>200711</startdate><enddate>200711</enddate><creator>Yu-Lian Zhu</creator><general>IEEE</general><scope>6IE</scope><scope>6IL</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIL</scope></search><sort><creationdate>200711</creationdate><title>Sub-pattern non-negative matrix factorization based on random subspace for face recognition</title><author>Yu-Lian Zhu</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i175t-25533323be9331223de90a18d917fdbdee33dec6d3e9f8760ccaf966e6780f9d3</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2007</creationdate><topic>Degradation</topic><topic>Face recognition</topic><topic>Feature extraction</topic><topic>Lighting</topic><topic>LNMF</topic><topic>NMF</topic><topic>Pattern analysis</topic><topic>Pattern recognition</topic><topic>PCA</topic><topic>Robustness</topic><topic>RS-SpNMF</topic><topic>Spatial databases</topic><topic>SpNMF</topic><topic>SpPCA</topic><topic>Voting</topic><topic>Wavelet analysis</topic><toplevel>online_resources</toplevel><creatorcontrib>Yu-Lian Zhu</creatorcontrib><collection>IEEE Electronic Library (IEL) Conference Proceedings</collection><collection>IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume</collection><collection>IEEE Xplore All Conference Proceedings</collection><collection>IEEE Electronic Library Online</collection><collection>IEEE Proceedings Order Plans (POP All) 1998-Present</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Yu-Lian Zhu</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Sub-pattern non-negative matrix factorization based on random subspace for face recognition</atitle><btitle>2007 International Conference on Wavelet Analysis and Pattern Recognition</btitle><stitle>ICWAPR</stitle><date>2007-11</date><risdate>2007</risdate><volume>3</volume><spage>1356</spage><epage>1360</epage><pages>1356-1360</pages><issn>2158-5695</issn><isbn>9781424410651</isbn><isbn>1424410657</isbn><eisbn>1424410665</eisbn><eisbn>9781424410668</eisbn><abstract>Non-negative matrix factorization (NMF) as a part-based representation method allows only additive combinations of non-negative basis components to represent the original data, so it provides a realistic approximation to the original data. However, NMF does not work well when directly applied to face recognition due to its global linear decomposition; this intuitively results in a degradation of recognition performance and non-robustness to the variation in illumination, expression and occlusion. In this paper, we propose a robust method, random subspace sub-pattern NMF (RS-SpNMF), especially for face recognition. Unlike the traditional random subspace method (RSM), which completely randomly selects the features from the whole original pattern feature set, the proposed method randomly samples features from each local region (or a sub-image) partitioned from the original face image and performs NMF decomposition on each sampled feature set. More specially, we first divide a face image into several sub-images in a deterministic way, then construct a component classifier on sampled feature subset from each sub-image set, and finally combine all of component classifiers for the final decision. Experiments on three benchmarks face databases (ORL, Yale and AR) show that the proposed method is effective, especially to the occlusive face image.</abstract><pub>IEEE</pub><doi>10.1109/ICWAPR.2007.4421645</doi><tpages>5</tpages></addata></record>
fulltext fulltext_linktorsrc
identifier ISSN: 2158-5695
ispartof 2007 International Conference on Wavelet Analysis and Pattern Recognition, 2007, Vol.3, p.1356-1360
issn 2158-5695
language eng
recordid cdi_ieee_primary_4421645
source IEEE Xplore All Conference Series
subjects Degradation
Face recognition
Feature extraction
Lighting
LNMF
NMF
Pattern analysis
Pattern recognition
PCA
Robustness
RS-SpNMF
Spatial databases
SpNMF
SpPCA
Voting
Wavelet analysis
title Sub-pattern non-negative matrix factorization based on random subspace for face recognition
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-25T01%3A46%3A21IST&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=Sub-pattern%20non-negative%20matrix%20factorization%20based%20on%20random%20subspace%20for%20face%20recognition&rft.btitle=2007%20International%20Conference%20on%20Wavelet%20Analysis%20and%20Pattern%20Recognition&rft.au=Yu-Lian%20Zhu&rft.date=2007-11&rft.volume=3&rft.spage=1356&rft.epage=1360&rft.pages=1356-1360&rft.issn=2158-5695&rft.isbn=9781424410651&rft.isbn_list=1424410657&rft_id=info:doi/10.1109/ICWAPR.2007.4421645&rft.eisbn=1424410665&rft.eisbn_list=9781424410668&rft_dat=%3Cieee_CHZPO%3E4421645%3C/ieee_CHZPO%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-i175t-25533323be9331223de90a18d917fdbdee33dec6d3e9f8760ccaf966e6780f9d3%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=4421645&rfr_iscdi=true