Mask detection method based on LFFD

The embodiment of the invention discloses a mask detection method based on LFFD. The mask detection method comprises the following steps: 1, making a training set; 2, constructing a preset SP-LFFD face detection network and a preset classification network, and training; and 3, performing face detect...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	WU XIANSONG, ZHAO DONGNING, YAN GENGXIAO, ZHANG YONG, ZHU JINGCHEN, ZHANG HENG, ZONG TUO
Format:	Patent
Sprache:	chi ; eng
Schlagworte:	CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING HANDLING RECORD CARRIERS PHYSICS PRESENTATION OF DATA RECOGNITION OF DATA RECORD CARRIERS
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	WU XIANSONG ZHAO DONGNING YAN GENGXIAO ZHANG YONG ZHU JINGCHEN ZHANG HENG ZONG TUO
description	The embodiment of the invention discloses a mask detection method based on LFFD. The mask detection method comprises the following steps: 1, making a training set; 2, constructing a preset SP-LFFD face detection network and a preset classification network, and training; and 3, performing face detection on the input picture, obtaining a face position, and sending the face position to the classification network to judge whether each face target of the input picture wears a mask; wherein the preset SP-LFFD face detection network comprises 25 convolution layers, the 25 convolution layers are divided into four parts, and each convolution layer adopts a SPConv convolution unit based on Split to replace conventional convolution. According to the method, an LFFD detection framework and Resnet18 image classification are adopted for a mask wearing detection scene, SPConv convolution is adopted to replace conventional convolution, redundant information in the conventional convolution is reduced, the reasoning speed can
format	Patent
fullrecord	<record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN113762200A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN113762200A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN113762200A3</originalsourceid><addsrcrecordid>eNrjZFD2TSzOVkhJLUlNLsnMz1PITS3JyE9RSEosTk1RAPJ93NxceBhY0xJzilN5oTQ3g6Kba4izh25qQX58anFBYnJqXmpJvLOfoaGxuZmRkYGBozExagCCwyVa</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Mask detection method based on LFFD</title><source>esp@cenet</source><creator>WU XIANSONG ; ZHAO DONGNING ; YAN GENGXIAO ; ZHANG YONG ; ZHU JINGCHEN ; ZHANG HENG ; ZONG TUO</creator><creatorcontrib>WU XIANSONG ; ZHAO DONGNING ; YAN GENGXIAO ; ZHANG YONG ; ZHU JINGCHEN ; ZHANG HENG ; ZONG TUO</creatorcontrib><description>The embodiment of the invention discloses a mask detection method based on LFFD. The mask detection method comprises the following steps: 1, making a training set; 2, constructing a preset SP-LFFD face detection network and a preset classification network, and training; and 3, performing face detection on the input picture, obtaining a face position, and sending the face position to the classification network to judge whether each face target of the input picture wears a mask; wherein the preset SP-LFFD face detection network comprises 25 convolution layers, the 25 convolution layers are divided into four parts, and each convolution layer adopts a SPConv convolution unit based on Split to replace conventional convolution. According to the method, an LFFD detection framework and Resnet18 image classification are adopted for a mask wearing detection scene, SPConv convolution is adopted to replace conventional convolution, redundant information in the conventional convolution is reduced, the reasoning speed can</description><language>chi ; eng</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; HANDLING RECORD CARRIERS ; PHYSICS ; PRESENTATION OF DATA ; RECOGNITION OF DATA ; RECORD CARRIERS</subject><creationdate>2021</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=20211207&DB=EPODOC&CC=CN&NR=113762200A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,776,881,25542,76289</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20211207&DB=EPODOC&CC=CN&NR=113762200A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>WU XIANSONG</creatorcontrib><creatorcontrib>ZHAO DONGNING</creatorcontrib><creatorcontrib>YAN GENGXIAO</creatorcontrib><creatorcontrib>ZHANG YONG</creatorcontrib><creatorcontrib>ZHU JINGCHEN</creatorcontrib><creatorcontrib>ZHANG HENG</creatorcontrib><creatorcontrib>ZONG TUO</creatorcontrib><title>Mask detection method based on LFFD</title><description>The embodiment of the invention discloses a mask detection method based on LFFD. The mask detection method comprises the following steps: 1, making a training set; 2, constructing a preset SP-LFFD face detection network and a preset classification network, and training; and 3, performing face detection on the input picture, obtaining a face position, and sending the face position to the classification network to judge whether each face target of the input picture wears a mask; wherein the preset SP-LFFD face detection network comprises 25 convolution layers, the 25 convolution layers are divided into four parts, and each convolution layer adopts a SPConv convolution unit based on Split to replace conventional convolution. According to the method, an LFFD detection framework and Resnet18 image classification are adopted for a mask wearing detection scene, SPConv convolution is adopted to replace conventional convolution, redundant information in the conventional convolution is reduced, the reasoning speed can</description><subject>CALCULATING</subject><subject>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</subject><subject>COMPUTING</subject><subject>COUNTING</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>2021</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZFD2TSzOVkhJLUlNLsnMz1PITS3JyE9RSEosTk1RAPJ93NxceBhY0xJzilN5oTQ3g6Kba4izh25qQX58anFBYnJqXmpJvLOfoaGxuZmRkYGBozExagCCwyVa</recordid><startdate>20211207</startdate><enddate>20211207</enddate><creator>WU XIANSONG</creator><creator>ZHAO DONGNING</creator><creator>YAN GENGXIAO</creator><creator>ZHANG YONG</creator><creator>ZHU JINGCHEN</creator><creator>ZHANG HENG</creator><creator>ZONG TUO</creator><scope>EVB</scope></search><sort><creationdate>20211207</creationdate><title>Mask detection method based on LFFD</title><author>WU XIANSONG ; ZHAO DONGNING ; YAN GENGXIAO ; ZHANG YONG ; ZHU JINGCHEN ; ZHANG HENG ; ZONG TUO</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN113762200A3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>chi ; eng</language><creationdate>2021</creationdate><topic>CALCULATING</topic><topic>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</topic><topic>COMPUTING</topic><topic>COUNTING</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>WU XIANSONG</creatorcontrib><creatorcontrib>ZHAO DONGNING</creatorcontrib><creatorcontrib>YAN GENGXIAO</creatorcontrib><creatorcontrib>ZHANG YONG</creatorcontrib><creatorcontrib>ZHU JINGCHEN</creatorcontrib><creatorcontrib>ZHANG HENG</creatorcontrib><creatorcontrib>ZONG TUO</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>WU XIANSONG</au><au>ZHAO DONGNING</au><au>YAN GENGXIAO</au><au>ZHANG YONG</au><au>ZHU JINGCHEN</au><au>ZHANG HENG</au><au>ZONG TUO</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Mask detection method based on LFFD</title><date>2021-12-07</date><risdate>2021</risdate><abstract>The embodiment of the invention discloses a mask detection method based on LFFD. The mask detection method comprises the following steps: 1, making a training set; 2, constructing a preset SP-LFFD face detection network and a preset classification network, and training; and 3, performing face detection on the input picture, obtaining a face position, and sending the face position to the classification network to judge whether each face target of the input picture wears a mask; wherein the preset SP-LFFD face detection network comprises 25 convolution layers, the 25 convolution layers are divided into four parts, and each convolution layer adopts a SPConv convolution unit based on Split to replace conventional convolution. According to the method, an LFFD detection framework and Resnet18 image classification are adopted for a mask wearing detection scene, SPConv convolution is adopted to replace conventional convolution, redundant information in the conventional convolution is reduced, the reasoning speed can</abstract><oa>free_for_read</oa></addata></record>
fulltext	fulltext_linktorsrc
identifier
ispartof
issn
language	chi ; eng
recordid	cdi_epo_espacenet_CN113762200A
source	esp@cenet
subjects	CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING HANDLING RECORD CARRIERS PHYSICS PRESENTATION OF DATA RECOGNITION OF DATA RECORD CARRIERS
title	Mask detection method based on LFFD
url	https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-05T10%3A16%3A29IST&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=WU%20XIANSONG&rft.date=2021-12-07&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN113762200A%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