Classification method based on deep migration learning and neighborhood noise reduction

The invention discloses a classification method based on deep migration learning and neighborhood noise reduction. The method comprises steps of migrating CNN shallow network weight parameters pre-trained on the source data set to a target data set; through fine tuning over a network, initializing C...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: CHEN CAILU, LIN LIANLEI, YANG JINGLI
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 CHEN CAILU
LIN LIANLEI
YANG JINGLI
description The invention discloses a classification method based on deep migration learning and neighborhood noise reduction. The method comprises steps of migrating CNN shallow network weight parameters pre-trained on the source data set to a target data set; through fine tuning over a network, initializing CNN deep network weight parameters trained by a target data set network randomly; training again onthe target data set to finish hyperspectral image classification based on transfer learning, then performing optimal neighborhood point noise reduction based on eight neighborhood point mode tags onan image marking result of hyperspectral image classification output through transfer learning, and finally outputting a noise-reduced image classification result. 本发明公开了一种基于深度迁移学习与邻域降噪的分类方法,将在源数据集上预训练的CNN浅层网络权值参数迁移至目标数据集,通过网络微调,随机初始化目标数据集网络训练的CNN深层网络权值参数,并在目标数据集上重新训练,完成基于迁移学习的高光谱图像分类,然后,再对通过迁移学习输出的高光谱图像分类的图像标记结果进行基于八邻域点众数标签的最优邻域点降噪,最终输出降噪后的图像分类结果。
format Patent
fullrecord <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN110503140A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN110503140A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN110503140A3</originalsourceid><addsrcrecordid>eNqNi0EKwjAQRbNxIeodxgMILdUDSFBcuRJclmnymw6kk5LU-1vRA7j6PN77a_O0kUuRXhzPkpRGzEPy1HGBp4U9MNEoIX91BGcVDcTqSSFh6FIe0vLQJAWU4V_uU27NqudYsPvtxuyvl4e9HTClFmViB8Xc2ntdV6eqqY_VufmneQOJjjoz</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Classification method based on deep migration learning and neighborhood noise reduction</title><source>esp@cenet</source><creator>CHEN CAILU ; LIN LIANLEI ; YANG JINGLI</creator><creatorcontrib>CHEN CAILU ; LIN LIANLEI ; YANG JINGLI</creatorcontrib><description>The invention discloses a classification method based on deep migration learning and neighborhood noise reduction. The method comprises steps of migrating CNN shallow network weight parameters pre-trained on the source data set to a target data set; through fine tuning over a network, initializing CNN deep network weight parameters trained by a target data set network randomly; training again onthe target data set to finish hyperspectral image classification based on transfer learning, then performing optimal neighborhood point noise reduction based on eight neighborhood point mode tags onan image marking result of hyperspectral image classification output through transfer learning, and finally outputting a noise-reduced image classification result. 本发明公开了一种基于深度迁移学习与邻域降噪的分类方法,将在源数据集上预训练的CNN浅层网络权值参数迁移至目标数据集,通过网络微调,随机初始化目标数据集网络训练的CNN深层网络权值参数,并在目标数据集上重新训练,完成基于迁移学习的高光谱图像分类,然后,再对通过迁移学习输出的高光谱图像分类的图像标记结果进行基于八邻域点众数标签的最优邻域点降噪,最终输出降噪后的图像分类结果。</description><language>chi ; eng</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; HANDLING RECORD CARRIERS ; IMAGE DATA PROCESSING OR GENERATION, IN GENERAL ; PHYSICS ; PRESENTATION OF DATA ; RECOGNITION OF DATA ; RECORD CARRIERS</subject><creationdate>2019</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&amp;date=20191126&amp;DB=EPODOC&amp;CC=CN&amp;NR=110503140A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,780,885,25564,76547</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=20191126&amp;DB=EPODOC&amp;CC=CN&amp;NR=110503140A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>CHEN CAILU</creatorcontrib><creatorcontrib>LIN LIANLEI</creatorcontrib><creatorcontrib>YANG JINGLI</creatorcontrib><title>Classification method based on deep migration learning and neighborhood noise reduction</title><description>The invention discloses a classification method based on deep migration learning and neighborhood noise reduction. The method comprises steps of migrating CNN shallow network weight parameters pre-trained on the source data set to a target data set; through fine tuning over a network, initializing CNN deep network weight parameters trained by a target data set network randomly; training again onthe target data set to finish hyperspectral image classification based on transfer learning, then performing optimal neighborhood point noise reduction based on eight neighborhood point mode tags onan image marking result of hyperspectral image classification output through transfer learning, and finally outputting a noise-reduced image classification result. 本发明公开了一种基于深度迁移学习与邻域降噪的分类方法,将在源数据集上预训练的CNN浅层网络权值参数迁移至目标数据集,通过网络微调,随机初始化目标数据集网络训练的CNN深层网络权值参数,并在目标数据集上重新训练,完成基于迁移学习的高光谱图像分类,然后,再对通过迁移学习输出的高光谱图像分类的图像标记结果进行基于八邻域点众数标签的最优邻域点降噪,最终输出降噪后的图像分类结果。</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>IMAGE DATA PROCESSING OR GENERATION, IN GENERAL</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>2019</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNqNi0EKwjAQRbNxIeodxgMILdUDSFBcuRJclmnymw6kk5LU-1vRA7j6PN77a_O0kUuRXhzPkpRGzEPy1HGBp4U9MNEoIX91BGcVDcTqSSFh6FIe0vLQJAWU4V_uU27NqudYsPvtxuyvl4e9HTClFmViB8Xc2ntdV6eqqY_VufmneQOJjjoz</recordid><startdate>20191126</startdate><enddate>20191126</enddate><creator>CHEN CAILU</creator><creator>LIN LIANLEI</creator><creator>YANG JINGLI</creator><scope>EVB</scope></search><sort><creationdate>20191126</creationdate><title>Classification method based on deep migration learning and neighborhood noise reduction</title><author>CHEN CAILU ; LIN LIANLEI ; YANG JINGLI</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN110503140A3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>chi ; eng</language><creationdate>2019</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>IMAGE DATA PROCESSING OR GENERATION, IN GENERAL</topic><topic>PHYSICS</topic><topic>PRESENTATION OF DATA</topic><topic>RECOGNITION OF DATA</topic><topic>RECORD CARRIERS</topic><toplevel>online_resources</toplevel><creatorcontrib>CHEN CAILU</creatorcontrib><creatorcontrib>LIN LIANLEI</creatorcontrib><creatorcontrib>YANG JINGLI</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>CHEN CAILU</au><au>LIN LIANLEI</au><au>YANG JINGLI</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Classification method based on deep migration learning and neighborhood noise reduction</title><date>2019-11-26</date><risdate>2019</risdate><abstract>The invention discloses a classification method based on deep migration learning and neighborhood noise reduction. The method comprises steps of migrating CNN shallow network weight parameters pre-trained on the source data set to a target data set; through fine tuning over a network, initializing CNN deep network weight parameters trained by a target data set network randomly; training again onthe target data set to finish hyperspectral image classification based on transfer learning, then performing optimal neighborhood point noise reduction based on eight neighborhood point mode tags onan image marking result of hyperspectral image classification output through transfer learning, and finally outputting a noise-reduced image classification result. 本发明公开了一种基于深度迁移学习与邻域降噪的分类方法,将在源数据集上预训练的CNN浅层网络权值参数迁移至目标数据集,通过网络微调,随机初始化目标数据集网络训练的CNN深层网络权值参数,并在目标数据集上重新训练,完成基于迁移学习的高光谱图像分类,然后,再对通过迁移学习输出的高光谱图像分类的图像标记结果进行基于八邻域点众数标签的最优邻域点降噪,最终输出降噪后的图像分类结果。</abstract><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier
ispartof
issn
language chi ; eng
recordid cdi_epo_espacenet_CN110503140A
source esp@cenet
subjects CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
HANDLING RECORD CARRIERS
IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
PHYSICS
PRESENTATION OF DATA
RECOGNITION OF DATA
RECORD CARRIERS
title Classification method based on deep migration learning and neighborhood noise reduction
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-23T07%3A46%3A22IST&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=CHEN%20CAILU&rft.date=2019-11-26&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN110503140A%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