Coal gangue data expansion method based on generative adversarial network and image fusion technology
The invention belongs to the field of intelligent mining, and particularly relates to a coal gangue data expansion method based on a generative adversarial network and an image fusion technology. According to the method, a stylegan3 network is constructed, a depth separable convolution optimization...
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 | YANG QIANGMIN VOUJEAN YUAN YONG LI YONG CHEN JIANG LI HENG CHEN ZHONGSHUN ZHANG BEIYAN WANG KANGHUI TANG YU QIN ZHENGHAN WANG WENMIAO ZHANG ZI'ANG XIA YONGQI |
description | The invention belongs to the field of intelligent mining, and particularly relates to a coal gangue data expansion method based on a generative adversarial network and an image fusion technology. According to the method, a stylegan3 network is constructed, a depth separable convolution optimization discriminator is used for augmenting coal and gangue images, then an image fusion technology is used for extracting new coal images and new gangue images generated in a random number, the new coal images and the new gangue images are subjected to random position fusion with a background image, new coal and gangue mixed images are generated in batches, and the diversity of coal and gangue data is improved. Meanwhile, the new coal gangue image generated by the method has high consistency with the actually measured coal gangue image, the features of the actual coal gangue image can be effectively reflected, and the problem of insufficient coal gangue image training samples in the deep learning process is effectively s |
format | Patent |
fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN116843996A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN116843996A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN116843996A3</originalsourceid><addsrcrecordid>eNqNjDEOgkAQRWksjHqH8QAWBEOkNERjZWVPRvazbIQZsrug3l5iPIDVz0ve-8sEpXJHlsWOIMORCa-BJTgV6hFbNXTnAEMzWwg8RzeB2Ezwgb2bY0F8qn8QiyHXswU147ePqFvRTu17nSwa7gI2v10l2_PpVl52GLRCGLier2NVXtM0P-yzosiP2T_OBzcYP5Q</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Coal gangue data expansion method based on generative adversarial network and image fusion technology</title><source>esp@cenet</source><creator>YANG QIANGMIN ; VOUJEAN ; YUAN YONG ; LI YONG ; CHEN JIANG ; LI HENG ; CHEN ZHONGSHUN ; ZHANG BEIYAN ; WANG KANGHUI ; TANG YU ; QIN ZHENGHAN ; WANG WENMIAO ; ZHANG ZI'ANG ; XIA YONGQI</creator><creatorcontrib>YANG QIANGMIN ; VOUJEAN ; YUAN YONG ; LI YONG ; CHEN JIANG ; LI HENG ; CHEN ZHONGSHUN ; ZHANG BEIYAN ; WANG KANGHUI ; TANG YU ; QIN ZHENGHAN ; WANG WENMIAO ; ZHANG ZI'ANG ; XIA YONGQI</creatorcontrib><description>The invention belongs to the field of intelligent mining, and particularly relates to a coal gangue data expansion method based on a generative adversarial network and an image fusion technology. According to the method, a stylegan3 network is constructed, a depth separable convolution optimization discriminator is used for augmenting coal and gangue images, then an image fusion technology is used for extracting new coal images and new gangue images generated in a random number, the new coal images and the new gangue images are subjected to random position fusion with a background image, new coal and gangue mixed images are generated in batches, and the diversity of coal and gangue data is improved. Meanwhile, the new coal gangue image generated by the method has high consistency with the actually measured coal gangue image, the features of the actual coal gangue image can be effectively reflected, and the problem of insufficient coal gangue image training samples in the deep learning process is effectively s</description><language>chi ; eng</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; PHYSICS</subject><creationdate>2023</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=20231003&DB=EPODOC&CC=CN&NR=116843996A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,780,885,25564,76547</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20231003&DB=EPODOC&CC=CN&NR=116843996A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>YANG QIANGMIN</creatorcontrib><creatorcontrib>VOUJEAN</creatorcontrib><creatorcontrib>YUAN YONG</creatorcontrib><creatorcontrib>LI YONG</creatorcontrib><creatorcontrib>CHEN JIANG</creatorcontrib><creatorcontrib>LI HENG</creatorcontrib><creatorcontrib>CHEN ZHONGSHUN</creatorcontrib><creatorcontrib>ZHANG BEIYAN</creatorcontrib><creatorcontrib>WANG KANGHUI</creatorcontrib><creatorcontrib>TANG YU</creatorcontrib><creatorcontrib>QIN ZHENGHAN</creatorcontrib><creatorcontrib>WANG WENMIAO</creatorcontrib><creatorcontrib>ZHANG ZI'ANG</creatorcontrib><creatorcontrib>XIA YONGQI</creatorcontrib><title>Coal gangue data expansion method based on generative adversarial network and image fusion technology</title><description>The invention belongs to the field of intelligent mining, and particularly relates to a coal gangue data expansion method based on a generative adversarial network and an image fusion technology. According to the method, a stylegan3 network is constructed, a depth separable convolution optimization discriminator is used for augmenting coal and gangue images, then an image fusion technology is used for extracting new coal images and new gangue images generated in a random number, the new coal images and the new gangue images are subjected to random position fusion with a background image, new coal and gangue mixed images are generated in batches, and the diversity of coal and gangue data is improved. Meanwhile, the new coal gangue image generated by the method has high consistency with the actually measured coal gangue image, the features of the actual coal gangue image can be effectively reflected, and the problem of insufficient coal gangue image training samples in the deep learning process is effectively s</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>2023</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNqNjDEOgkAQRWksjHqH8QAWBEOkNERjZWVPRvazbIQZsrug3l5iPIDVz0ve-8sEpXJHlsWOIMORCa-BJTgV6hFbNXTnAEMzWwg8RzeB2Ezwgb2bY0F8qn8QiyHXswU147ePqFvRTu17nSwa7gI2v10l2_PpVl52GLRCGLier2NVXtM0P-yzosiP2T_OBzcYP5Q</recordid><startdate>20231003</startdate><enddate>20231003</enddate><creator>YANG QIANGMIN</creator><creator>VOUJEAN</creator><creator>YUAN YONG</creator><creator>LI YONG</creator><creator>CHEN JIANG</creator><creator>LI HENG</creator><creator>CHEN ZHONGSHUN</creator><creator>ZHANG BEIYAN</creator><creator>WANG KANGHUI</creator><creator>TANG YU</creator><creator>QIN ZHENGHAN</creator><creator>WANG WENMIAO</creator><creator>ZHANG ZI'ANG</creator><creator>XIA YONGQI</creator><scope>EVB</scope></search><sort><creationdate>20231003</creationdate><title>Coal gangue data expansion method based on generative adversarial network and image fusion technology</title><author>YANG QIANGMIN ; VOUJEAN ; YUAN YONG ; LI YONG ; CHEN JIANG ; LI HENG ; CHEN ZHONGSHUN ; ZHANG BEIYAN ; WANG KANGHUI ; TANG YU ; QIN ZHENGHAN ; WANG WENMIAO ; ZHANG ZI'ANG ; XIA YONGQI</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN116843996A3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>chi ; eng</language><creationdate>2023</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>YANG QIANGMIN</creatorcontrib><creatorcontrib>VOUJEAN</creatorcontrib><creatorcontrib>YUAN YONG</creatorcontrib><creatorcontrib>LI YONG</creatorcontrib><creatorcontrib>CHEN JIANG</creatorcontrib><creatorcontrib>LI HENG</creatorcontrib><creatorcontrib>CHEN ZHONGSHUN</creatorcontrib><creatorcontrib>ZHANG BEIYAN</creatorcontrib><creatorcontrib>WANG KANGHUI</creatorcontrib><creatorcontrib>TANG YU</creatorcontrib><creatorcontrib>QIN ZHENGHAN</creatorcontrib><creatorcontrib>WANG WENMIAO</creatorcontrib><creatorcontrib>ZHANG ZI'ANG</creatorcontrib><creatorcontrib>XIA YONGQI</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>YANG QIANGMIN</au><au>VOUJEAN</au><au>YUAN YONG</au><au>LI YONG</au><au>CHEN JIANG</au><au>LI HENG</au><au>CHEN ZHONGSHUN</au><au>ZHANG BEIYAN</au><au>WANG KANGHUI</au><au>TANG YU</au><au>QIN ZHENGHAN</au><au>WANG WENMIAO</au><au>ZHANG ZI'ANG</au><au>XIA YONGQI</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Coal gangue data expansion method based on generative adversarial network and image fusion technology</title><date>2023-10-03</date><risdate>2023</risdate><abstract>The invention belongs to the field of intelligent mining, and particularly relates to a coal gangue data expansion method based on a generative adversarial network and an image fusion technology. According to the method, a stylegan3 network is constructed, a depth separable convolution optimization discriminator is used for augmenting coal and gangue images, then an image fusion technology is used for extracting new coal images and new gangue images generated in a random number, the new coal images and the new gangue images are subjected to random position fusion with a background image, new coal and gangue mixed images are generated in batches, and the diversity of coal and gangue data is improved. Meanwhile, the new coal gangue image generated by the method has high consistency with the actually measured coal gangue image, the features of the actual coal gangue image can be effectively reflected, and the problem of insufficient coal gangue image training samples in the deep learning process is effectively s</abstract><oa>free_for_read</oa></addata></record> |
fulltext | fulltext_linktorsrc |
identifier | |
ispartof | |
issn | |
language | chi ; eng |
recordid | cdi_epo_espacenet_CN116843996A |
source | esp@cenet |
subjects | CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING PHYSICS |
title | Coal gangue data expansion method based on generative adversarial network and image fusion technology |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-24T04%3A04%3A57IST&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=YANG%20QIANGMIN&rft.date=2023-10-03&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN116843996A%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 |