<?xml version="1.0" encoding="UTF-8" ?>
<oai_dc:dc schemaLocation="http://www.openarchives.org/OAI/2.0/oai_dc/ http://www.openarchives.org/OAI/2.0/oai_dc.xsd">
<dc:title>Face recognition for long-term interaction</dc:title>
<dc:creator>Sravanajyothi, Narayanaraju</dc:creator>
<dc:subject>Reconeixement facial (Informàtica)</dc:subject>
<dc:subject>004 - Informàtica</dc:subject>
<dc:description>Face recognition is one of the few biometric methods that possess both accuracy and intrusiveness. For this reason it has drawn attention of many researchers and numerous algorithms have been proposed. Various fields such as network security, surveillance benefits from the face recognition because it provides more efficient coding scheme. Since the face recognition is a real world problem and there are cases when not all the input data is not known beforehand. In this project the focus is on the online learning strategy. We implemented online nonparametric discriminant analysis methodology for long-term face recognition problem. The advantage of using NDA over LDA is explained briefly. Besides reviewing the online version of NDA, we propose an optimized version based on 'affective forgetting'. In order to guarantee real-time response, the online learning strategy has been extended with a pruning mechanism which gets rid of the oldest samples. Experimental results on the FRIENDS dataset demonstrated that the performance of classification is not affected by replacing the former samples with new ones.</dc:description>
<dc:contributor>Universitat Autònoma de Barcelona. Escola d'Enginyeria</dc:contributor>
<dc:contributor>Raducanu, Bogdan</dc:contributor>
<dc:date>2015-06</dc:date>
<dc:type>info:eu-repo/semantics/bachelorThesis</dc:type>
<dc:format>25 p.</dc:format>
<dc:identifier>http://hdl.handle.net/2072/252403</dc:identifier>
<dc:source>RECERCAT (Dipòsit de la Recerca de Catalunya)</dc:source>
<dc:language>eng</dc:language>
<dc:rights>info:eu-repo/semantics/openAccess</dc:rights>
<dc:rights>L'accés als continguts d'aquest document queda condicionat a l'acceptació de les condicions d'ús establertes per la següent llicència Creative Commons: http://creativecommons.org/licenses/by-nc-nd/3.0/es/</dc:rights>
</oai_dc:dc>
<?xml version="1.0" encoding="UTF-8" ?>
<didl:DIDL schemaLocation="urn:mpeg:mpeg21:2002:02-DIDL-NS http://standards.iso.org/ittf/PubliclyAvailableStandards/MPEG-21_schema_files/did/didl.xsd ">
<didl:DIDLInfo>
<dcterms:created schemaLocation="http://purl.org/dc/terms/ ">2016-02-20T04:38:26Z</dcterms:created>
</didl:DIDLInfo>
<didl:Item id="uuid-febf07a2-171b-468e-a8ef-cdacc6144a1c">
<didl:Descriptor>
<didl:Statement mimeType="application/xml; charset=utf-8">
<dii:Identifier schemaLocation="urn:mpeg:mpeg21:2002:01-DII-NS http://standards.iso.org/ittf/PubliclyAvailableStandards/MPEG-21_schema_files/dii/dii.xsd">urn:hdl:2072/252403</dii:Identifier>
</didl:Statement>
</didl:Descriptor>
<didl:Descriptor>
<didl:Statement mimeType="application/xml; charset=utf-8">
<oai_dc:dc schemaLocation="http://www.openarchives.org/OAI/2.0/oai_dc/ http://www.openarchives.org/OAI/2.0/oai_dc.xsd">
<dc:title>Face recognition for long-term interaction</dc:title>
<dc:creator>Sravanajyothi, Narayanaraju</dc:creator>
<dc:subject>Reconeixement facial (Informàtica)</dc:subject>
<dc:subject>004 - Informàtica</dc:subject>
<dc:description>Face recognition is one of the few biometric methods that possess both accuracy and intrusiveness. For this reason it has drawn attention of many researchers and numerous algorithms have been proposed. Various fields such as network security, surveillance benefits from the face recognition because it provides more efficient coding scheme. Since the face recognition is a real world problem and there are cases when not all the input data is not known beforehand. In this project the focus is on the online learning strategy. We implemented online nonparametric discriminant analysis methodology for long-term face recognition problem. The advantage of using NDA over LDA is explained briefly. Besides reviewing the online version of NDA, we propose an optimized version based on 'affective forgetting'. In order to guarantee real-time response, the online learning strategy has been extended with a pruning mechanism which gets rid of the oldest samples. Experimental results on the FRIENDS dataset demonstrated that the performance of classification is not affected by replacing the former samples with new ones.</dc:description>
<dc:contributor>Universitat Autònoma de Barcelona. Escola d'Enginyeria</dc:contributor>
<dc:contributor>Raducanu, Bogdan</dc:contributor>
<dc:date>2015-06</dc:date>
<dc:type>info:eu-repo/semantics/bachelorThesis</dc:type>
<dc:format>25 p.</dc:format>
<dc:identifier>http://hdl.handle.net/2072/252403</dc:identifier>
<dc:source>RECERCAT (Dipòsit de la Recerca de Catalunya)</dc:source>
<dc:language>eng</dc:language>
<dc:rights>info:eu-repo/semantics/openAccess</dc:rights>
<dc:rights>L'accés als continguts d'aquest document queda condicionat a l'acceptació de les condicions d'ús establertes per la següent llicència Creative Commons: http://creativecommons.org/licenses/by-nc-nd/3.0/es/</dc:rights>
</oai_dc:dc>
</didl:Statement>
</didl:Descriptor>
<didl:Component id="uuid-b4ec44b4-39b1-4be9-809c-839bce4356cf">
</didl:Component>
</didl:Item>
</didl:DIDL>
<?xml version="1.0" encoding="UTF-8" ?>
<record schemaLocation="http://www.loc.gov/MARC21/slim http://www.loc.gov/standards/marcxml/schema/MARC21slim.xsd">
<leader>am 3u</leader>
<datafield ind1=" " ind2=" " tag="042">
<subfield code="a">dc</subfield>
</datafield>
<datafield ind1=" " ind2=" " tag="260">
<subfield code="c">2015-07-21T14:06:51Z</subfield>
</datafield>
<datafield ind1=" " ind2=" " tag="520">
<subfield code="a">Face recognition is one of the few biometric methods that possess both accuracy and intrusiveness. For this reason it has drawn attention of many researchers and numerous algorithms have been proposed. Various fields such as network security, surveillance benefits from the face recognition because it provides more efficient coding scheme. Since the face recognition is a real world problem and there are cases when not all the input data is not known beforehand. In this project the focus is on the online learning strategy. We implemented online nonparametric discriminant analysis methodology for long-term face recognition problem. The advantage of using NDA over LDA is explained briefly. Besides reviewing the online version of NDA, we propose an optimized version based on 'affective forgetting'. In order to guarantee real-time response, the online learning strategy has been extended with a pruning mechanism which gets rid of the oldest samples. Experimental results on the FRIENDS dataset demonstrated that the performance of classification is not affected by replacing the former samples with new ones.</subfield>
</datafield>
<datafield ind1="8" ind2=" " tag="024">
<subfield code="a">http://hdl.handle.net/2072/252403</subfield>
</datafield>
<datafield ind1=" " ind2=" " tag="546">
<subfield code="a">eng</subfield>
</datafield>
<datafield ind1=" " ind2=" " tag="653">
<subfield code="a">Reconeixement facial (Informàtica)</subfield>
</datafield>
<datafield ind1=" " ind2=" " tag="653">
<subfield code="a">004 - Informàtica</subfield>
</datafield>
<datafield ind1="0" ind2="0" tag="245">
<subfield code="a">Face recognition for long-term interaction</subfield>
</datafield>
</record>
<?xml version="1.0" encoding="UTF-8" ?>
<mets LABEL="DSpace Item" OBJID="hdl:2072/252403" schemaLocation="http://www.loc.gov/METS/ http://www.loc.gov/standards/mets/mets.xsd http://www.loc.gov/mods/v3 http://www.loc.gov/standards/mods/v3/mods-3-0.xsd">
<metsHdr CREATEDATE="2016-02-20T05:38:26">
<agent ROLE="CUSTODIAN" TYPE="ORGANIZATION">
<name>RECERCAT (Diposit de la Recerca de Catalunya)</name>
</agent>
</metsHdr>
<dmdSec ID="DMD_hdl_2072/252403">
<mdWrap MDTYPE="MODS">
<xmlData>
<mods:name>
<mods:namePart>Universitat Autònoma de Barcelona. Escola d'Enginyeria</mods:namePart>
</mods:name>
<mods:name>
<mods:namePart>Raducanu, Bogdan</mods:namePart>
</mods:name>
<mods:name>
<mods:role>
<mods:roleTerm type="text">author</mods:roleTerm>
</mods:role>
<mods:namePart>Sravanajyothi, Narayanaraju</mods:namePart>
</mods:name>
<mods:extension>
<mods:dateAccessioned encoding="iso8601">2015-07-21T14:06:51Z</mods:dateAccessioned>
</mods:extension>
<mods:extension>
<mods:dateAvailable encoding="iso8601">2015-07-21T14:06:51Z</mods:dateAvailable>
</mods:extension>
<mods:originInfo>
<mods:dateCreated encoding="iso8601">2015</mods:dateCreated>
</mods:originInfo>
<mods:originInfo>
<mods:dateIssued encoding="iso8601">2015-06</mods:dateIssued>
</mods:originInfo>
<mods:identifier type="uri">http://hdl.handle.net/2072/252403</mods:identifier>
<mods:abstract>Face recognition is one of the few biometric methods that possess both accuracy and intrusiveness. For this reason it has drawn attention of many researchers and numerous algorithms have been proposed. Various fields such as network security, surveillance benefits from the face recognition because it provides more efficient coding scheme. Since the face recognition is a real world problem and there are cases when not all the input data is not known beforehand. In this project the focus is on the online learning strategy. We implemented online nonparametric discriminant analysis methodology for long-term face recognition problem. The advantage of using NDA over LDA is explained briefly. Besides reviewing the online version of NDA, we propose an optimized version based on 'affective forgetting'. In order to guarantee real-time response, the online learning strategy has been extended with a pruning mechanism which gets rid of the oldest samples. Experimental results on the FRIENDS dataset demonstrated that the performance of classification is not affected by replacing the former samples with new ones.</mods:abstract>
<mods:physicalDescription>
<mods:extent>25 p.</mods:extent>
</mods:physicalDescription>
<mods:language>
<mods:languageTerm authority="rfc3066">eng</mods:languageTerm>
</mods:language>
<mods:accessCondition type="useAndReproduction">info:eu-repo/semantics/openAccess</mods:accessCondition>
<mods:accessCondition type="useAndReproduction">L'accés als continguts d'aquest document queda condicionat a l'acceptació de les condicions d'ús establertes per la següent llicència Creative Commons: http://creativecommons.org/licenses/by-nc-nd/3.0/es/</mods:accessCondition>
<mods:relatedItem type="original">RECERCAT (Dipòsit de la Recerca de Catalunya)</mods:relatedItem>
<mods:subject authority="local">Reconeixement facial (Informàtica)</mods:subject>
<mods:titleInfo>Face recognition for long-term interaction</mods:titleInfo>
<mods:genre>info:eu-repo/semantics/bachelorThesis</mods:genre>
</xmlData>
</mdWrap>
</dmdSec>
<amdSec ID="TMD_hdl_2072/252403">
<rightsMD>
<mdWrap MDTYPE="OTHER" MIMETYPE="text/plain" OTHERMDTYPE="TEXT">
<binData>aHR0cDovL2NyZWF0aXZlY29tbW9ucy5vcmcvbGljZW5zZXMvYnktbmMtbmQvMy4wL2VzLw==</binData>
</mdWrap>
</rightsMD>
</amdSec>
<fileSec>
<fileGrp USE="ORIGINAL">
<file CHECKSUM="6552e821fc980f9b84ce5b99f7476791" CHECKSUMTYPE="MD5" GROUPID="GROUP_2072_252403_1" ID="2072_252403_1" MIMETYPE="application/pdf" OWNERID="http://www.recercat.cat//bitstream/2072/252403/1/PFC_NarayanarajuSravanajyothi.pdf" SIZE="652763">
</file>
</fileGrp>
</fileSec>
<structMap>
</structMap>
</mets>
<?xml version="1.0" encoding="UTF-8" ?>
<atom:entry>
<atom:id>http://www.recercat.cat//oai/metadata/handle/2072/252403/ore.xml</atom:id>
<atom:published>2016-02-20T05:38:26.063+01:00</atom:published>
<atom:updated>2016-02-20T05:38:26.063+01:00</atom:updated>
<atom:source>
<atom:generator uri="http://www.recercat.cat//oai">RECERCAT (Diposit de la Recerca de Catalunya)</atom:generator>
</atom:source>
<atom:title>Face recognition for long-term interaction</atom:title>
<atom:author>
<atom:name>Sravanajyothi, Narayanaraju</atom:name>
</atom:author>
<oreatom:triples>
<rdf:Description about="http://www.recercat.cat//oai/metadata/handle/2072/252403/ore.xml">
<dcterms:modified>2015-07-21T16:06:51.602+02:00</dcterms:modified>
</rdf:Description>
<rdf:Description about="http://www.recercat.cat//bitstream/handle/2072/252403/license_url?sequence=2">
<dcterms:description>CC-LICENSE</dcterms:description>
</rdf:Description>
<rdf:Description about="http://www.recercat.cat//bitstream/handle/2072/252403/license_text?sequence=3">
<dcterms:description>CC-LICENSE</dcterms:description>
</rdf:Description>
<rdf:Description about="http://www.recercat.cat//bitstream/handle/2072/252403/license_rdf?sequence=4">
<dcterms:description>CC-LICENSE</dcterms:description>
</rdf:Description>
<rdf:Description about="http://www.recercat.cat//bitstream/handle/2072/252403/PFC_NarayanarajuSravanajyothi.pdf?sequence=1">
<dcterms:description>ORIGINAL</dcterms:description>
</rdf:Description>
</oreatom:triples>
</atom:entry>
<?xml version="1.0" encoding="UTF-8" ?>
<dc:contributor schemaLocation="http://purl.org/dc/terms/ http://dublincore.org/schemas/xmls/qdc/2006/01/06/dcterms.xsd http://purl.org/dc/elements/1.1/ http://dublincore.org/schemas/xmls/qdc/2006/01/06/dc.xsd">Universitat Autònoma de Barcelona. Escola d'Enginyeria</dc:contributor>
<?xml version="1.0" encoding="UTF-8" ?>
<rdf:RDF schemaLocation="http://www.w3.org/1999/02/22-rdf-syntax-ns# http://www.openarchives.org/OAI/2.0/rdf.xsd">
<ow:Publication about="oai:www.recercat.cat:2072/252403">
<dc:contributor>Universitat Autònoma de Barcelona. Escola d'Enginyeria</dc:contributor>
<dc:contributor>Raducanu, Bogdan</dc:contributor>
<dc:creator>Sravanajyothi, Narayanaraju</dc:creator>
<dc:date>2015-07-21T14:06:51Z</dc:date>
<dc:date>2015</dc:date>
<dc:date>2015-06</dc:date>
<dc:identifier>http://hdl.handle.net/2072/252403</dc:identifier>
<dc:description>Face recognition is one of the few biometric methods that possess both accuracy and intrusiveness. For this reason it has drawn attention of many researchers and numerous algorithms have been proposed. Various fields such as network security, surveillance benefits from the face recognition because it provides more efficient coding scheme. Since the face recognition is a real world problem and there are cases when not all the input data is not known beforehand. In this project the focus is on the online learning strategy. We implemented online nonparametric discriminant analysis methodology for long-term face recognition problem. The advantage of using NDA over LDA is explained briefly. Besides reviewing the online version of NDA, we propose an optimized version based on 'affective forgetting'. In order to guarantee real-time response, the online learning strategy has been extended with a pruning mechanism which gets rid of the oldest samples. Experimental results on the FRIENDS dataset demonstrated that the performance of classification is not affected by replacing the former samples with new ones.</dc:description>
<dc:language>eng</dc:language>
<dc:rights>info:eu-repo/semantics/openAccess</dc:rights>
<dc:rights>L'accés als continguts d'aquest document queda condicionat a l'acceptació de les condicions d'ús establertes per la següent llicència Creative Commons: http://creativecommons.org/licenses/by-nc-nd/3.0/es/</dc:rights>
<dc:source>RECERCAT (Dipòsit de la Recerca de Catalunya)</dc:source>
<dc:subject>Reconeixement facial (Informàtica)</dc:subject>
<dc:title>Face recognition for long-term interaction</dc:title>
<dc:type>info:eu-repo/semantics/bachelorThesis</dc:type>
<dc:subject>004 - Informàtica</dc:subject>
<dc:embargo>cap</dc:embargo>
<dc:source>Escola d'Enginyeria</dc:source>
<dc:source>Universitat Autònoma de Barcelona</dc:source>
<dc:source>Projectes i treballs de final de carrera. Enginyeria Informàtica</dc:source>
</ow:Publication>
</rdf:RDF>