Time flies by: Analyzing the Impact of Face Ageing on the Recognition Performance with Synthetic Data

The vast progress in synthetic image synthesis enables the generation of facial images in high resolution and photorealism. In biometric applications, the main motivation for using synthetic data is to solve the shortage of publicly-available biometric data while reducing privacy risks when processi...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Grimmer, Marcel, Zhang, Haoyu, Ramachandra, Raghavendra, Raja, Kiran, Busch, Christoph
Format: Tagungsbericht
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page 6
container_issue
container_start_page 1
container_title
container_volume
creator Grimmer, Marcel
Zhang, Haoyu
Ramachandra, Raghavendra
Raja, Kiran
Busch, Christoph
description The vast progress in synthetic image synthesis enables the generation of facial images in high resolution and photorealism. In biometric applications, the main motivation for using synthetic data is to solve the shortage of publicly-available biometric data while reducing privacy risks when processing such sensitive information. These advantages are exploited in this work by simulating human face ageing with recent face age modification algorithms to generate mated samples, thereby studying the impact of ageing on the performance of an open-source biometric recognition system. Further, a real dataset is used to evaluate the effects of short-term ageing, comparing the biometric performance to the synthetic domain. The main findings indicate that short-term ageing in the range of 1-5 years has only minor effects on the general recognition performance. However, the correct verification of mated faces with long-term age differences beyond 20 years poses still a significant challenge and requires further investigation.
doi_str_mv 10.1109/BIOSIG55365.2022.9897043
format Conference Proceeding
fullrecord <record><control><sourceid>ieee</sourceid><recordid>TN_cdi_ieee_primary_9897043</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>9897043</ieee_id><sourcerecordid>9897043</sourcerecordid><originalsourceid>FETCH-LOGICAL-i253t-9090b6f8aaf462a79decb0f2cd419b84ecedd61e3f8a81a545bcd8211d196e3e3</originalsourceid><addsrcrecordid>eNotkM1Kw0AcxFdBsNY-gZd9gcT9zq63WG0NFCq2nstm8992pUlKsiDx6Ru1cxmG-TGHQQhTklJKzONzsd4USym5kikjjKVGm4wIfoXuqFJSZEopcY0mVNEskULpWzTr-y8yKiNMZnqCYBtqwP4YoMfl8ITzxh6Hn9DscTwALuqTdRG3Hi-sA5zv4bdpm7_yA1y7b0IMY36HzrddbZuR-g7xgDdDMzIxOPxio71HN94ee5hdfIo-F6_b-VuyWi-Leb5KApM8JoYYUiqvrfVCMZuZClxJPHOVoKbUAhxUlaLAR0RTK4UsXaUZpRU1CjjwKXr43w0AsDt1obbdsLu8ws-_vlix</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Time flies by: Analyzing the Impact of Face Ageing on the Recognition Performance with Synthetic Data</title><source>Elektronische Zeitschriftenbibliothek - Frei zugängliche E-Journals</source><creator>Grimmer, Marcel ; Zhang, Haoyu ; Ramachandra, Raghavendra ; Raja, Kiran ; Busch, Christoph</creator><creatorcontrib>Grimmer, Marcel ; Zhang, Haoyu ; Ramachandra, Raghavendra ; Raja, Kiran ; Busch, Christoph</creatorcontrib><description>The vast progress in synthetic image synthesis enables the generation of facial images in high resolution and photorealism. In biometric applications, the main motivation for using synthetic data is to solve the shortage of publicly-available biometric data while reducing privacy risks when processing such sensitive information. These advantages are exploited in this work by simulating human face ageing with recent face age modification algorithms to generate mated samples, thereby studying the impact of ageing on the performance of an open-source biometric recognition system. Further, a real dataset is used to evaluate the effects of short-term ageing, comparing the biometric performance to the synthetic domain. The main findings indicate that short-term ageing in the range of 1-5 years has only minor effects on the general recognition performance. However, the correct verification of mated faces with long-term age differences beyond 20 years poses still a significant challenge and requires further investigation.</description><identifier>EISSN: 1617-5468</identifier><identifier>EISBN: 1665476664</identifier><identifier>EISBN: 9781665476669</identifier><identifier>DOI: 10.1109/BIOSIG55365.2022.9897043</identifier><language>eng</language><publisher>IEEE</publisher><subject>Data privacy ; Face Age Modification ; Face recognition ; Image recognition ; Image resolution ; Image synthesis ; Photorealism ; Synthetic Data ; Three-dimensional displays</subject><ispartof>2022 International Conference of the Biometrics Special Interest Group (BIOSIG), 2022, p.1-6</ispartof><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>309,310,776,780,785,786,23909,23910,25118,27902</link.rule.ids></links><search><creatorcontrib>Grimmer, Marcel</creatorcontrib><creatorcontrib>Zhang, Haoyu</creatorcontrib><creatorcontrib>Ramachandra, Raghavendra</creatorcontrib><creatorcontrib>Raja, Kiran</creatorcontrib><creatorcontrib>Busch, Christoph</creatorcontrib><title>Time flies by: Analyzing the Impact of Face Ageing on the Recognition Performance with Synthetic Data</title><title>2022 International Conference of the Biometrics Special Interest Group (BIOSIG)</title><addtitle>BIOSIG55365</addtitle><description>The vast progress in synthetic image synthesis enables the generation of facial images in high resolution and photorealism. In biometric applications, the main motivation for using synthetic data is to solve the shortage of publicly-available biometric data while reducing privacy risks when processing such sensitive information. These advantages are exploited in this work by simulating human face ageing with recent face age modification algorithms to generate mated samples, thereby studying the impact of ageing on the performance of an open-source biometric recognition system. Further, a real dataset is used to evaluate the effects of short-term ageing, comparing the biometric performance to the synthetic domain. The main findings indicate that short-term ageing in the range of 1-5 years has only minor effects on the general recognition performance. However, the correct verification of mated faces with long-term age differences beyond 20 years poses still a significant challenge and requires further investigation.</description><subject>Data privacy</subject><subject>Face Age Modification</subject><subject>Face recognition</subject><subject>Image recognition</subject><subject>Image resolution</subject><subject>Image synthesis</subject><subject>Photorealism</subject><subject>Synthetic Data</subject><subject>Three-dimensional displays</subject><issn>1617-5468</issn><isbn>1665476664</isbn><isbn>9781665476669</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2022</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><sourceid>RIE</sourceid><recordid>eNotkM1Kw0AcxFdBsNY-gZd9gcT9zq63WG0NFCq2nstm8992pUlKsiDx6Ru1cxmG-TGHQQhTklJKzONzsd4USym5kikjjKVGm4wIfoXuqFJSZEopcY0mVNEskULpWzTr-y8yKiNMZnqCYBtqwP4YoMfl8ITzxh6Hn9DscTwALuqTdRG3Hi-sA5zv4bdpm7_yA1y7b0IMY36HzrddbZuR-g7xgDdDMzIxOPxio71HN94ee5hdfIo-F6_b-VuyWi-Leb5KApM8JoYYUiqvrfVCMZuZClxJPHOVoKbUAhxUlaLAR0RTK4UsXaUZpRU1CjjwKXr43w0AsDt1obbdsLu8ws-_vlix</recordid><startdate>20220101</startdate><enddate>20220101</enddate><creator>Grimmer, Marcel</creator><creator>Zhang, Haoyu</creator><creator>Ramachandra, Raghavendra</creator><creator>Raja, Kiran</creator><creator>Busch, Christoph</creator><general>IEEE</general><scope>6IE</scope><scope>6IL</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIL</scope></search><sort><creationdate>20220101</creationdate><title>Time flies by: Analyzing the Impact of Face Ageing on the Recognition Performance with Synthetic Data</title><author>Grimmer, Marcel ; Zhang, Haoyu ; Ramachandra, Raghavendra ; Raja, Kiran ; Busch, Christoph</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i253t-9090b6f8aaf462a79decb0f2cd419b84ecedd61e3f8a81a545bcd8211d196e3e3</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Data privacy</topic><topic>Face Age Modification</topic><topic>Face recognition</topic><topic>Image recognition</topic><topic>Image resolution</topic><topic>Image synthesis</topic><topic>Photorealism</topic><topic>Synthetic Data</topic><topic>Three-dimensional displays</topic><toplevel>online_resources</toplevel><creatorcontrib>Grimmer, Marcel</creatorcontrib><creatorcontrib>Zhang, Haoyu</creatorcontrib><creatorcontrib>Ramachandra, Raghavendra</creatorcontrib><creatorcontrib>Raja, Kiran</creatorcontrib><creatorcontrib>Busch, Christoph</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 (IEL)</collection><collection>IEEE Proceedings Order Plans (POP All) 1998-Present</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Grimmer, Marcel</au><au>Zhang, Haoyu</au><au>Ramachandra, Raghavendra</au><au>Raja, Kiran</au><au>Busch, Christoph</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Time flies by: Analyzing the Impact of Face Ageing on the Recognition Performance with Synthetic Data</atitle><btitle>2022 International Conference of the Biometrics Special Interest Group (BIOSIG)</btitle><stitle>BIOSIG55365</stitle><date>2022-01-01</date><risdate>2022</risdate><spage>1</spage><epage>6</epage><pages>1-6</pages><eissn>1617-5468</eissn><eisbn>1665476664</eisbn><eisbn>9781665476669</eisbn><abstract>The vast progress in synthetic image synthesis enables the generation of facial images in high resolution and photorealism. In biometric applications, the main motivation for using synthetic data is to solve the shortage of publicly-available biometric data while reducing privacy risks when processing such sensitive information. These advantages are exploited in this work by simulating human face ageing with recent face age modification algorithms to generate mated samples, thereby studying the impact of ageing on the performance of an open-source biometric recognition system. Further, a real dataset is used to evaluate the effects of short-term ageing, comparing the biometric performance to the synthetic domain. The main findings indicate that short-term ageing in the range of 1-5 years has only minor effects on the general recognition performance. However, the correct verification of mated faces with long-term age differences beyond 20 years poses still a significant challenge and requires further investigation.</abstract><pub>IEEE</pub><doi>10.1109/BIOSIG55365.2022.9897043</doi><tpages>6</tpages><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier EISSN: 1617-5468
ispartof 2022 International Conference of the Biometrics Special Interest Group (BIOSIG), 2022, p.1-6
issn 1617-5468
language eng
recordid cdi_ieee_primary_9897043
source Elektronische Zeitschriftenbibliothek - Frei zugängliche E-Journals
subjects Data privacy
Face Age Modification
Face recognition
Image recognition
Image resolution
Image synthesis
Photorealism
Synthetic Data
Three-dimensional displays
title Time flies by: Analyzing the Impact of Face Ageing on the Recognition Performance with Synthetic Data
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-10T02%3A16%3A35IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-ieee&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=Time%20flies%20by:%20Analyzing%20the%20Impact%20of%20Face%20Ageing%20on%20the%20Recognition%20Performance%20with%20Synthetic%20Data&rft.btitle=2022%20International%20Conference%20of%20the%20Biometrics%20Special%20Interest%20Group%20(BIOSIG)&rft.au=Grimmer,%20Marcel&rft.date=2022-01-01&rft.spage=1&rft.epage=6&rft.pages=1-6&rft.eissn=1617-5468&rft_id=info:doi/10.1109/BIOSIG55365.2022.9897043&rft_dat=%3Cieee%3E9897043%3C/ieee%3E%3Curl%3E%3C/url%3E&rft.eisbn=1665476664&rft.eisbn_list=9781665476669&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=9897043&rfr_iscdi=true