METHOD AND DEVICE FOR HIGH-SPEED IMAGE RECOGNITION USING 3D CNN
The present disclosure provides is a high-speed image recognition method and apparatus using a 3D CNN. The high-speed image recognition method using the 3D CNN includes: inputting each of a first image clips among image clips constituting an input image to the 3D CNN; acquiring softmax function valu...
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Patent |
| Sprache: | 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 | LEE, Hyun Hoon LEE, Young Joo PARK, Gun Ho KIM, Young Seok |
| description | The present disclosure provides is a high-speed image recognition method and apparatus using a 3D CNN. The high-speed image recognition method using the 3D CNN includes: inputting each of a first image clips among image clips constituting an input image to the 3D CNN; acquiring softmax function values calculated in the 3D CNN with respect to each of the first image clips; calculating a score margin by using the softmax function values; comparing the score margin with a predetermined threshold value to determine whether to input at least one additional image clip other than the first image clips among the image clips constituting the input image to the 3D CNN. Therefore, a calculation speed for image recognition can be improved. |
| format | Patent |
| fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_US2022108545A1</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>US2022108545A1</sourcerecordid><originalsourceid>FETCH-epo_espacenet_US2022108545A13</originalsourceid><addsrcrecordid>eNrjZLD3dQ3x8HdRcPRzUXBxDfN0dlVw8w9S8PB099ANDnB1dVHw9HV0d1UIcnX2d_fzDPH091MIDfb0c1cwdlFw9vPjYWBNS8wpTuWF0twMym6uIc4euqkF-fGpxQWJyal5qSXxocFGBkZGhgYWpiamjobGxKkCANcdKp0</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>METHOD AND DEVICE FOR HIGH-SPEED IMAGE RECOGNITION USING 3D CNN</title><source>esp@cenet</source><creator>LEE, Hyun Hoon ; LEE, Young Joo ; PARK, Gun Ho ; KIM, Young Seok</creator><creatorcontrib>LEE, Hyun Hoon ; LEE, Young Joo ; PARK, Gun Ho ; KIM, Young Seok</creatorcontrib><description>The present disclosure provides is a high-speed image recognition method and apparatus using a 3D CNN. The high-speed image recognition method using the 3D CNN includes: inputting each of a first image clips among image clips constituting an input image to the 3D CNN; acquiring softmax function values calculated in the 3D CNN with respect to each of the first image clips; calculating a score margin by using the softmax function values; comparing the score margin with a predetermined threshold value to determine whether to input at least one additional image clip other than the first image clips among the image clips constituting the input image to the 3D CNN. Therefore, a calculation speed for image recognition can be improved.</description><language>eng</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; PHYSICS</subject><creationdate>2022</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=20220407&DB=EPODOC&CC=US&NR=2022108545A1$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,776,881,25542,76289</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20220407&DB=EPODOC&CC=US&NR=2022108545A1$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>LEE, Hyun Hoon</creatorcontrib><creatorcontrib>LEE, Young Joo</creatorcontrib><creatorcontrib>PARK, Gun Ho</creatorcontrib><creatorcontrib>KIM, Young Seok</creatorcontrib><title>METHOD AND DEVICE FOR HIGH-SPEED IMAGE RECOGNITION USING 3D CNN</title><description>The present disclosure provides is a high-speed image recognition method and apparatus using a 3D CNN. The high-speed image recognition method using the 3D CNN includes: inputting each of a first image clips among image clips constituting an input image to the 3D CNN; acquiring softmax function values calculated in the 3D CNN with respect to each of the first image clips; calculating a score margin by using the softmax function values; comparing the score margin with a predetermined threshold value to determine whether to input at least one additional image clip other than the first image clips among the image clips constituting the input image to the 3D CNN. Therefore, a calculation speed for image recognition can be improved.</description><subject>CALCULATING</subject><subject>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</subject><subject>COMPUTING</subject><subject>COUNTING</subject><subject>PHYSICS</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2022</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZLD3dQ3x8HdRcPRzUXBxDfN0dlVw8w9S8PB099ANDnB1dVHw9HV0d1UIcnX2d_fzDPH091MIDfb0c1cwdlFw9vPjYWBNS8wpTuWF0twMym6uIc4euqkF-fGpxQWJyal5qSXxocFGBkZGhgYWpiamjobGxKkCANcdKp0</recordid><startdate>20220407</startdate><enddate>20220407</enddate><creator>LEE, Hyun Hoon</creator><creator>LEE, Young Joo</creator><creator>PARK, Gun Ho</creator><creator>KIM, Young Seok</creator><scope>EVB</scope></search><sort><creationdate>20220407</creationdate><title>METHOD AND DEVICE FOR HIGH-SPEED IMAGE RECOGNITION USING 3D CNN</title><author>LEE, Hyun Hoon ; LEE, Young Joo ; PARK, Gun Ho ; KIM, Young Seok</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_US2022108545A13</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>eng</language><creationdate>2022</creationdate><topic>CALCULATING</topic><topic>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>LEE, Hyun Hoon</creatorcontrib><creatorcontrib>LEE, Young Joo</creatorcontrib><creatorcontrib>PARK, Gun Ho</creatorcontrib><creatorcontrib>KIM, Young Seok</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>LEE, Hyun Hoon</au><au>LEE, Young Joo</au><au>PARK, Gun Ho</au><au>KIM, Young Seok</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>METHOD AND DEVICE FOR HIGH-SPEED IMAGE RECOGNITION USING 3D CNN</title><date>2022-04-07</date><risdate>2022</risdate><abstract>The present disclosure provides is a high-speed image recognition method and apparatus using a 3D CNN. The high-speed image recognition method using the 3D CNN includes: inputting each of a first image clips among image clips constituting an input image to the 3D CNN; acquiring softmax function values calculated in the 3D CNN with respect to each of the first image clips; calculating a score margin by using the softmax function values; comparing the score margin with a predetermined threshold value to determine whether to input at least one additional image clip other than the first image clips among the image clips constituting the input image to the 3D CNN. Therefore, a calculation speed for image recognition can be improved.</abstract><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | |
| ispartof | |
| issn | |
| language | eng |
| recordid | cdi_epo_espacenet_US2022108545A1 |
| source | esp@cenet |
| subjects | CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING PHYSICS |
| title | METHOD AND DEVICE FOR HIGH-SPEED IMAGE RECOGNITION USING 3D CNN |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-06T21%3A27%3A51IST&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=LEE,%20Hyun%20Hoon&rft.date=2022-04-07&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3EUS2022108545A1%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 |