面向手语识别的视频关键帧提取和优化算法

TP391; 基于计算机视觉的手语识别技术可以为聋校的双语教学带来很大的便利,而手语识别技术的难点之一在于视频关键帧的提取.根据手语视频关键帧的特点和手语者的手语习惯,提出了一种面向手语识别的视频关键帧提取和优化算法.首先利用卷积自编码器提取视频帧的深度特征,对其进行K-means聚类,在每类视频帧中采用清晰度筛选取出最清晰的视频帧作为初次提取的关键帧;然后利用点密度方法对初次提取的关键帧进行二次优化,得到最终提取的关键帧进行手语识别.实验结果表明,本文算法能大量消除冗余帧,并能提高手语识别的准确率和效率....

Full description

Saved in:
Bibliographic Details
Published in华东理工大学学报（自然科学版） Vol. 47; no. 1; pp. 81 - 88
Main Authors 周舟, 韩芳, 王直杰
Format Journal Article
LanguageChinese
Published 东华大学信息科学与技术学院,上海 201620 28.02.2021
Subjects
K-means
卷积自编码器
视频关键帧
手语识别
点密度
Online AccessGet full text
ISSN1006-3080
DOI10.14135/j.cnki.1006-3080.20191201002

Cover

Abstract TP391; 基于计算机视觉的手语识别技术可以为聋校的双语教学带来很大的便利,而手语识别技术的难点之一在于视频关键帧的提取.根据手语视频关键帧的特点和手语者的手语习惯,提出了一种面向手语识别的视频关键帧提取和优化算法.首先利用卷积自编码器提取视频帧的深度特征,对其进行K-means聚类,在每类视频帧中采用清晰度筛选取出最清晰的视频帧作为初次提取的关键帧;然后利用点密度方法对初次提取的关键帧进行二次优化,得到最终提取的关键帧进行手语识别.实验结果表明,本文算法能大量消除冗余帧,并能提高手语识别的准确率和效率.
AbstractList TP391; 基于计算机视觉的手语识别技术可以为聋校的双语教学带来很大的便利,而手语识别技术的难点之一在于视频关键帧的提取.根据手语视频关键帧的特点和手语者的手语习惯,提出了一种面向手语识别的视频关键帧提取和优化算法.首先利用卷积自编码器提取视频帧的深度特征,对其进行K-means聚类,在每类视频帧中采用清晰度筛选取出最清晰的视频帧作为初次提取的关键帧;然后利用点密度方法对初次提取的关键帧进行二次优化,得到最终提取的关键帧进行手语识别.实验结果表明,本文算法能大量消除冗余帧,并能提高手语识别的准确率和效率.
Author 韩芳
周舟
王直杰
AuthorAffiliation 东华大学信息科学与技术学院,上海 201620
AuthorAffiliation_xml – name: 东华大学信息科学与技术学院,上海 201620
Author_FL HAN Fang
ZHOU Zhou
WANG Zhijie
Author_FL_xml – sequence: 1
  fullname: ZHOU Zhou
– sequence: 2
  fullname: HAN Fang
– sequence: 3
  fullname: WANG Zhijie
Author_xml – sequence: 1
  fullname: 周舟
– sequence: 2
  fullname: 韩芳
– sequence: 3
  fullname: 王直杰
BookMark eNo9j7tKA0EYhaeIYIx5DAuLXf9_Zmd2p5TgDQI2WoedvcTEMAEXMQ-gQTGQRDSKYJMmhZgUaSx8HGez-xYuKDbnwFd8h7NBSrqrI0K2EGx0kPGdth3o85aNAMJi4IFNASUWAUBLpPzP10k1SVqqoJR7KLBMZP42NaNxenefLT6yRd_cvq9er7NZP5-Ozc0yf5ybz1k6HJnhxDwMvr9ezGCymj-ny6dNshb7nSSq_nWFnO7vndQOrfrxwVFtt24lCA5asVAIDFjEQ4VMxLEKlJTSF16ECpTyWBgFwMMAXCkd5avIRdfhEIDDaYyCVcj2r_fK17Gvm4129_JCF4uNs7DTDHs9RYFicRWR_QBt7GGk
ClassificationCodes TP391
ContentType Journal Article
Copyright Copyright © Wanfang Data Co. Ltd. All Rights Reserved.
Copyright_xml – notice: Copyright © Wanfang Data Co. Ltd. All Rights Reserved.
DBID 2B.
4A8
92I
93N
PSX
TCJ
DOI 10.14135/j.cnki.1006-3080.20191201002
DatabaseName Wanfang Data Journals - Hong Kong
WANFANG Data Centre
Wanfang Data Journals
万方数据期刊 - 香港版
China Online Journals (COJ)
China Online Journals (COJ)
DatabaseTitleList
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
DocumentTitle_FL Video Key Frame Extraction and Optimization Algorithm for Sign Language Recognition
EndPage 88
ExternalDocumentID hdlgdxxb202101011
GrantInformation_xml – fundername: (国家自然科学基金); 中央高校基本科研业务费专项资金; (东华大学"励志计划")
  funderid: (国家自然科学基金); 中央高校基本科研业务费专项资金; (东华大学"励志计划")
GroupedDBID -02
2B.
4A8
92I
93N
ALMA_UNASSIGNED_HOLDINGS
CCEZO
CDRFL
P2P
PSX
TCJ
U1G
U5L
UY8
ID FETCH-LOGICAL-s1041-f6b10303e5db136ffbcb999a68e1b0bb83dec05dc07994babe717450c0452f163
ISSN 1006-3080
IngestDate Thu May 29 03:59:03 EDT 2025
IsPeerReviewed true
IsScholarly true
Issue 1
Keywords K-means
卷积自编码器
视频关键帧
手语识别
点密度
Language Chinese
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-s1041-f6b10303e5db136ffbcb999a68e1b0bb83dec05dc07994babe717450c0452f163
PageCount 8
ParticipantIDs wanfang_journals_hdlgdxxb202101011
PublicationCentury 2000
PublicationDate 2021-02-28
PublicationDateYYYYMMDD 2021-02-28
PublicationDate_xml – month: 02
  year: 2021
  text: 2021-02-28
  day: 28
PublicationDecade 2020
PublicationTitle 华东理工大学学报（自然科学版）
PublicationTitle_FL Journal of East China University of Science and Technology(Natural Science Edition)
PublicationYear 2021
Publisher 东华大学信息科学与技术学院,上海 201620
Publisher_xml – name: 东华大学信息科学与技术学院,上海 201620
SSID ssib002258161
ssib001104923
ssib057620135
ssib035757162
ssib036434644
ssib006703735
ssib000947709
ssib006595864
ssib051370438
ssib023167207
ssib001050798
ssj0039901
Score 2.2997332
Snippet TP391; 基于计算机视觉的手语识别技术可以为聋校的双语教学带来很大的便利,而手语识别技术的难点之一在于视频关键帧的提取.根据手语视频关键帧的特点和手语者的手语习惯,...
SourceID wanfang
SourceType Aggregation Database
StartPage 81
Title 面向手语识别的视频关键帧提取和优化算法
URI https://d.wanfangdata.com.cn/periodical/hdlgdxxb202101011
Volume 47
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVEBS
  databaseName: Inspec with Full Text
  issn: 1006-3080
  databaseCode: ADMLS
  dateStart: 20191201
  customDbUrl:
  isFulltext: true
  dateEnd: 99991231
  titleUrlDefault: https://www.ebsco.com/products/research-databases/inspec-full-text
  omitProxy: false
  ssIdentifier: ssib057620135
  providerName: EBSCOhost
link http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnR1Ja9ZAdOgCogdxxZ0izkm-mmUmmTkm-fJRxHqxhd5KJksryifYFkrPWhQLbUWrCF566UFsD0Xw4M8xXf6F703W0iLVS5jkLfOWJPNeMvOGkHssSnicYuXH2OEdpmKrIxXnHRkxFkeCp6Ze9T7-2BmbZA-n-NTA4I_WrKWFeTUaL524ruR_vArXwK-4SvYfPFszhQvQBv_CETwMx1P5mIaSyi71LBpyKg0qTRo6VEgqfBoK6vWo1y0bwkEcAW0AuVR6VDANcjVIIhMkBxxOfVtzZtQL8Yqv0ZBzD3tBHGhohtKiIqAho35ApdCgQINcpJWaCrgVO1xWQbBG61IRakJBZaBFMkohfaDl2PCY7pejFp7TaoAknsbpYb-gFCgigMpDPqCXXwjglhqVVK62jKio6i8gWg-TegUbEKfXQMAKYESpIR5o0kBclF8UxvSpz1Aq8IVvtL-jWGZrXTre-S2NaxscVxRwoNfCmSZ67wRtNB8k18YQhu4_0Mg1DkivHWsFFb6nHYI2vg8xmWMZrUHJ0PMTix2vqlGrqFN65OkshqBiB5wqmBEnDpMQuXA9Tsb9Z09Ha_4401GaOD_CsJr4oJ61OZs8n0kWFxVaD0sTmoNk2HIdxxoiw153_NGTVtzO3CN1AQ1IO1p5PcScrJ23w6AizNYCayxy2d42wIFxyW3iegvLN1jNdwsbco6qEpo-hzCbOU3cyk3bxT_e9TlEAJD61HmyjT-H9bSI0hBnCK3M9OBvRtIr_fpZ1J9pBaUTF8j5Mpsc8YpXw0UysDR7iZxr1Ri9TOTh1818bX3v7buDne8HO8v5m2_7X14dbC0fbq7nr3cPP2znP7f2Vtfy1Y38_crvX5_zlY397U97ux-vkMleOBGMdcr9UjpzYE-zkzkKNw20U54o03ayTMUK8r_IEampDKWEnaSxwZMYfCGZilTqmi7jRozbKmSQmF0lQ_0X_fQaGcEKGVEWcyYNmyUyknAauYrLWKaxzMzr5G6p-HT5PpybPnZ73DgN0k1ytnkab5Gh-ZcL6W2I8-fVnfKu-gMWoLam
linkProvider EBSCOhost
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=%E9%9D%A2%E5%90%91%E6%89%8B%E8%AF%AD%E8%AF%86%E5%88%AB%E7%9A%84%E8%A7%86%E9%A2%91%E5%85%B3%E9%94%AE%E5%B8%A7%E6%8F%90%E5%8F%96%E5%92%8C%E4%BC%98%E5%8C%96%E7%AE%97%E6%B3%95&rft.jtitle=%E5%8D%8E%E4%B8%9C%E7%90%86%E5%B7%A5%E5%A4%A7%E5%AD%A6%E5%AD%A6%E6%8A%A5%EF%BC%88%E8%87%AA%E7%84%B6%E7%A7%91%E5%AD%A6%E7%89%88%EF%BC%89&rft.au=%E5%91%A8%E8%88%9F&rft.au=%E9%9F%A9%E8%8A%B3&rft.au=%E7%8E%8B%E7%9B%B4%E6%9D%B0&rft.date=2021-02-28&rft.pub=%E4%B8%9C%E5%8D%8E%E5%A4%A7%E5%AD%A6%E4%BF%A1%E6%81%AF%E7%A7%91%E5%AD%A6%E4%B8%8E%E6%8A%80%E6%9C%AF%E5%AD%A6%E9%99%A2%2C%E4%B8%8A%E6%B5%B7+201620&rft.issn=1006-3080&rft.volume=47&rft.issue=1&rft.spage=81&rft.epage=88&rft_id=info:doi/10.14135%2Fj.cnki.1006-3080.20191201002&rft.externalDocID=hdlgdxxb202101011
thumbnail_s http://utb.summon.serialssolutions.com/2.0.0/image/custom?url=http%3A%2F%2Fwww.wanfangdata.com.cn%2Fimages%2FPeriodicalImages%2Fhdlgdxxb%2Fhdlgdxxb.jpg