Low-resolution face recognition method based on active discriminative cross-domain alignment
The invention discloses a low-resolution face recognition method based on active discrimination cross-domain alignment, and the method specifically comprises the steps: constructing an HR image set and an LR face image set, selecting a source domain sample from the LR face image set, forming a sourc...
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Patent |
| Sprache: | chi ; eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | |
|---|---|
| container_issue | |
| container_start_page | |
| container_title | |
| container_volume | |
| creator | JING JUNFENG LI MINQI CHEN XIAOGAI ZHANG KAIBING ZHENG DONGDONG LU JIAN ZHANG TIANGE |
| description | The invention discloses a low-resolution face recognition method based on active discrimination cross-domain alignment, and the method specifically comprises the steps: constructing an HR image set and an LR face image set, selecting a source domain sample from the LR face image set, forming a source domain sample set, and enabling the remaining LR face images to form a target domain sample set; meanwhile, the statistical distribution difference between source domain samples and target domain samples is reduced; constructing a discrimination alignment moment; establishing a linear transformation relationship between source domain samples and target domain samples; and constructing and solving a target function, calculating a source domain and standard domain sample transformation matrix, and deducing a category label of the face transformation feature of the target domain by using a nearest neighbor classifier. According to the method, the face feature space of the source domain and the face feature space of |
| format | Patent |
| fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN111695456A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN111695456A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN111695456A3</originalsourceid><addsrcrecordid>eNqNjUEKwjAQRbtxIeod4gGyCNqCSymKC3HlUigxmbYDyUzJRL2-oXgAV5_3efCW1ePKH51AOLwyMqneOlAJHA-E8xEhj-zV0wp4Vdi6jG9QHsUljEh2RpdYRHuOFosScKAIlNfVordBYPPbVbU9n-7tRcPEHchUWgS5a2_GmOZQ7-vmuPvH-QINPjyU</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Low-resolution face recognition method based on active discriminative cross-domain alignment</title><source>esp@cenet</source><creator>JING JUNFENG ; LI MINQI ; CHEN XIAOGAI ; ZHANG KAIBING ; ZHENG DONGDONG ; LU JIAN ; ZHANG TIANGE</creator><creatorcontrib>JING JUNFENG ; LI MINQI ; CHEN XIAOGAI ; ZHANG KAIBING ; ZHENG DONGDONG ; LU JIAN ; ZHANG TIANGE</creatorcontrib><description>The invention discloses a low-resolution face recognition method based on active discrimination cross-domain alignment, and the method specifically comprises the steps: constructing an HR image set and an LR face image set, selecting a source domain sample from the LR face image set, forming a source domain sample set, and enabling the remaining LR face images to form a target domain sample set; meanwhile, the statistical distribution difference between source domain samples and target domain samples is reduced; constructing a discrimination alignment moment; establishing a linear transformation relationship between source domain samples and target domain samples; and constructing and solving a target function, calculating a source domain and standard domain sample transformation matrix, and deducing a category label of the face transformation feature of the target domain by using a nearest neighbor classifier. According to the method, the face feature space of the source domain and the face feature space of</description><language>chi ; eng</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; ELECTRIC DIGITAL DATA PROCESSING ; HANDLING RECORD CARRIERS ; PHYSICS ; PRESENTATION OF DATA ; RECOGNITION OF DATA ; RECORD CARRIERS</subject><creationdate>2020</creationdate><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20200922&DB=EPODOC&CC=CN&NR=111695456A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,776,881,25544,76293</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20200922&DB=EPODOC&CC=CN&NR=111695456A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>JING JUNFENG</creatorcontrib><creatorcontrib>LI MINQI</creatorcontrib><creatorcontrib>CHEN XIAOGAI</creatorcontrib><creatorcontrib>ZHANG KAIBING</creatorcontrib><creatorcontrib>ZHENG DONGDONG</creatorcontrib><creatorcontrib>LU JIAN</creatorcontrib><creatorcontrib>ZHANG TIANGE</creatorcontrib><title>Low-resolution face recognition method based on active discriminative cross-domain alignment</title><description>The invention discloses a low-resolution face recognition method based on active discrimination cross-domain alignment, and the method specifically comprises the steps: constructing an HR image set and an LR face image set, selecting a source domain sample from the LR face image set, forming a source domain sample set, and enabling the remaining LR face images to form a target domain sample set; meanwhile, the statistical distribution difference between source domain samples and target domain samples is reduced; constructing a discrimination alignment moment; establishing a linear transformation relationship between source domain samples and target domain samples; and constructing and solving a target function, calculating a source domain and standard domain sample transformation matrix, and deducing a category label of the face transformation feature of the target domain by using a nearest neighbor classifier. According to the method, the face feature space of the source domain and the face feature space of</description><subject>CALCULATING</subject><subject>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</subject><subject>COMPUTING</subject><subject>COUNTING</subject><subject>ELECTRIC DIGITAL DATA PROCESSING</subject><subject>HANDLING RECORD CARRIERS</subject><subject>PHYSICS</subject><subject>PRESENTATION OF DATA</subject><subject>RECOGNITION OF DATA</subject><subject>RECORD CARRIERS</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2020</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNqNjUEKwjAQRbtxIeod4gGyCNqCSymKC3HlUigxmbYDyUzJRL2-oXgAV5_3efCW1ePKH51AOLwyMqneOlAJHA-E8xEhj-zV0wp4Vdi6jG9QHsUljEh2RpdYRHuOFosScKAIlNfVordBYPPbVbU9n-7tRcPEHchUWgS5a2_GmOZQ7-vmuPvH-QINPjyU</recordid><startdate>20200922</startdate><enddate>20200922</enddate><creator>JING JUNFENG</creator><creator>LI MINQI</creator><creator>CHEN XIAOGAI</creator><creator>ZHANG KAIBING</creator><creator>ZHENG DONGDONG</creator><creator>LU JIAN</creator><creator>ZHANG TIANGE</creator><scope>EVB</scope></search><sort><creationdate>20200922</creationdate><title>Low-resolution face recognition method based on active discriminative cross-domain alignment</title><author>JING JUNFENG ; LI MINQI ; CHEN XIAOGAI ; ZHANG KAIBING ; ZHENG DONGDONG ; LU JIAN ; ZHANG TIANGE</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN111695456A3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>chi ; eng</language><creationdate>2020</creationdate><topic>CALCULATING</topic><topic>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>ELECTRIC DIGITAL DATA PROCESSING</topic><topic>HANDLING RECORD CARRIERS</topic><topic>PHYSICS</topic><topic>PRESENTATION OF DATA</topic><topic>RECOGNITION OF DATA</topic><topic>RECORD CARRIERS</topic><toplevel>online_resources</toplevel><creatorcontrib>JING JUNFENG</creatorcontrib><creatorcontrib>LI MINQI</creatorcontrib><creatorcontrib>CHEN XIAOGAI</creatorcontrib><creatorcontrib>ZHANG KAIBING</creatorcontrib><creatorcontrib>ZHENG DONGDONG</creatorcontrib><creatorcontrib>LU JIAN</creatorcontrib><creatorcontrib>ZHANG TIANGE</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>JING JUNFENG</au><au>LI MINQI</au><au>CHEN XIAOGAI</au><au>ZHANG KAIBING</au><au>ZHENG DONGDONG</au><au>LU JIAN</au><au>ZHANG TIANGE</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Low-resolution face recognition method based on active discriminative cross-domain alignment</title><date>2020-09-22</date><risdate>2020</risdate><abstract>The invention discloses a low-resolution face recognition method based on active discrimination cross-domain alignment, and the method specifically comprises the steps: constructing an HR image set and an LR face image set, selecting a source domain sample from the LR face image set, forming a source domain sample set, and enabling the remaining LR face images to form a target domain sample set; meanwhile, the statistical distribution difference between source domain samples and target domain samples is reduced; constructing a discrimination alignment moment; establishing a linear transformation relationship between source domain samples and target domain samples; and constructing and solving a target function, calculating a source domain and standard domain sample transformation matrix, and deducing a category label of the face transformation feature of the target domain by using a nearest neighbor classifier. According to the method, the face feature space of the source domain and the face feature space of</abstract><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | |
| ispartof | |
| issn | |
| language | chi ; eng |
| recordid | cdi_epo_espacenet_CN111695456A |
| source | esp@cenet |
| subjects | CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING ELECTRIC DIGITAL DATA PROCESSING HANDLING RECORD CARRIERS PHYSICS PRESENTATION OF DATA RECOGNITION OF DATA RECORD CARRIERS |
| title | Low-resolution face recognition method based on active discriminative cross-domain alignment |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-27T20%3A32%3A11IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-epo_EVB&rft_val_fmt=info:ofi/fmt:kev:mtx:patent&rft.genre=patent&rft.au=JING%20JUNFENG&rft.date=2020-09-22&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN111695456A%3C/epo_EVB%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true |