웨이브릿 변환 영역에서 특징추출을 이용한 내용기반 영상 검색

In this paper, we present a content-based image retrieval method which is based on the feature extraction in the wavelet transform domain. In order to overcome the drawbacks of the feature vector making up methods which use the global wavelet coefficients in subbands, we utilize the energy value of...

Full description

Saved in:
Bibliographic Details
Published in멀티미디어학회논문지 Vol. 5; no. 4; pp. 415 - 425
Main Authors 최인호(In Ho Choi), 이상훈(Sang Hun Lee)
Format Journal Article
LanguageKorean
Published 한국멀티미디어학회 2002
Subjects
Online AccessGet full text

Cover

Loading…
Abstract In this paper, we present a content-based image retrieval method which is based on the feature extraction in the wavelet transform domain. In order to overcome the drawbacks of the feature vector making up methods which use the global wavelet coefficients in subbands, we utilize the energy value of wavelet coefficients, and the shape-based retrieval of objects is processed by moment which is invariant in translation, scaling, rotation of the objects The proposed methods reduce feature vector size, and make progress performance of classification retrieval which provides fast retrievals times. To offer the abilities of region-based image retrieval, we discussed the image segmentation method which can reduce the effect of an irregular light sources. The image segmentation method uses a region-merging, and candidate regions which are merged were selected by the energy values of high frequency bands in discrete wavelet transform. The region-based image retrieval is executed by using the segmented region information, and the images are retrieved by a color, texture, shape feature vector. 본 논문에서는 웨이브릿 변환 영역에서 추출된 특징을 기반으로 한 내용기반 영상검색 방법에 관해 연구하였다. 기존의 웨이브릿 기반의 방법에서의 문제점인 특징벡터의 크기를 줄이기 위해 웨이브릿 계수의 영역별 에너지 값을 이용하였으며, 대상물의 이동, 회전, 크기 변화에 영향을 받지 않는 모멘트 특성을 이용한 검색방법을 제안하였다. 본 방법은 특징벡터의 크기를 줄이고, 기존의 특징벡터와 비교해서 검색시간을 단축하면서 분류검색의 효율성을 향상시켰다. 영역기반 영상검색 기능을 제공하기 위해 영상분할 방법에 대해 연구하였으며, 불규칙한 광원에 의한 영향을 최소화할 수 있는 영상분할 방법을 제안하였다 영상분할은 영역병합을 이용하였고, 병합후보영역은 웨이브릿 변환의 고주파 대역 에너지 값을 이용하여 선정하였다 분할된 영역정보를 이용하여 칼라와 질감, 모양 특징벡터를 구성하여 영역기반 영상검색을 수행하였다.
AbstractList KCI Citation Count: 1
In this paper, we present a content-based image retrieval method which is based on the feature extraction in the wavelet transform domain. In order to overcome the drawbacks of the feature vector making up methods which use the global wavelet coefficients in subbands, we utilize the energy value of wavelet coefficients, and the shape-based retrieval of objects is processed by moment which is invariant in translation, scaling, rotation of the objects The proposed methods reduce feature vector size, and make progress performance of classification retrieval which provides fast retrievals times. To offer the abilities of region-based image retrieval, we discussed the image segmentation method which can reduce the effect of an irregular light sources. The image segmentation method uses a region-merging, and candidate regions which are merged were selected by the energy values of high frequency bands in discrete wavelet transform. The region-based image retrieval is executed by using the segmented region information, and the images are retrieved by a color, texture, shape feature vector. 본 논문에서는 웨이브릿 변환 영역에서 추출된 특징을 기반으로 한 내용기반 영상검색 방법에 관해 연구하였다. 기존의 웨이브릿 기반의 방법에서의 문제점인 특징벡터의 크기를 줄이기 위해 웨이브릿 계수의 영역별 에너지 값을 이용하였으며, 대상물의 이동, 회전, 크기 변화에 영향을 받지 않는 모멘트 특성을 이용한 검색방법을 제안하였다. 본 방법은 특징벡터의 크기를 줄이고, 기존의 특징벡터와 비교해서 검색시간을 단축하면서 분류검색의 효율성을 향상시켰다. 영역기반 영상검색 기능을 제공하기 위해 영상분할 방법에 대해 연구하였으며, 불규칙한 광원에 의한 영향을 최소화할 수 있는 영상분할 방법을 제안하였다 영상분할은 영역병합을 이용하였고, 병합후보영역은 웨이브릿 변환의 고주파 대역 에너지 값을 이용하여 선정하였다 분할된 영역정보를 이용하여 칼라와 질감, 모양 특징벡터를 구성하여 영역기반 영상검색을 수행하였다.
Author 최인호(In Ho Choi)
이상훈(Sang Hun Lee)
Author_xml – sequence: 1
  fullname: 최인호(In Ho Choi)
– sequence: 2
  fullname: 이상훈(Sang Hun Lee)
BackLink https://www.kci.go.kr/kciportal/ci/sereArticleSearch/ciSereArtiView.kci?sereArticleSearchBean.artiId=ART000865473$$DAccess content in National Research Foundation of Korea (NRF)
BookMark eNpNjD1PwkAAhi8GExH5D11MXJrcR693HQmiokQSg_PlSlvTFItpdXADYcE4OEhAhdWPwYSoITj5f-jxHwRxcHqfvHnedx2kwnroroA0JtzQIYI4BdIIY0tnjKE1kI1j34aGwSiB2EyDY_X4ooafyeQmefrWko_G7L6vqX5T9d5U71a1B9rs-ks9d9X4To0HatjW5rZ6eJ11B1pytaDpZJSMlptWU5u-N1SrswFWPVmL3exfZkBlp1DJ7-ml8m4xnyvpAUKU6FzalCNGbWwSkxPbsCVF1PE8yi1XShdjU3JMXWgwhy9KiSl3GLarsuoQl2TA1vI2jDwRVH1Rl_5vntRFEIncUaUoCKeUwbm6uVQDPz73RejENbGfOyhjCDFCFkbEwNz454UXkX_qOr4UZ3OQ0aU4LG8XIDIhsixCfgB-roH5
ContentType Journal Article
DBID DBRKI
TDB
JDI
ACYCR
DEWEY 006.7
DatabaseName DBPIA - 디비피아
Korean Database (DBpia)
KoreaScience
Korean Citation Index
DatabaseTitleList

DeliveryMethod fulltext_linktorsrc
Discipline Computer Science
DocumentTitleAlternate Content-based Image Retrieval using Feature Extraction inWavelet Transform Domain
DocumentTitle_FL Control-based Image Retrieval using Feature Extraction in Wavelet Transform Domain
EISSN 2384-0102
EndPage 425
ExternalDocumentID oai_kci_go_kr_ARTI_385570
JAKO200211921342840
NODE01601993
GroupedDBID .UV
ALMA_UNASSIGNED_HOLDINGS
DBRKI
TDB
JDI
ACYCR
M~E
ID FETCH-LOGICAL-k1153-8ab58175b263683b4ba515dff589eaae226a825e047d8f589a258d72bcacd3e3
ISSN 1229-7771
IngestDate Fri Nov 17 19:23:51 EST 2023
Fri Dec 22 12:02:23 EST 2023
Fri Oct 18 15:42:44 EDT 2024
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Issue 4
Keywords 영역기반 영상검색
내용기반검색
영상분할
웨이브릿 변환
Language Korean
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-k1153-8ab58175b263683b4ba515dff589eaae226a825e047d8f589a258d72bcacd3e3
Notes KISTI1.1003/JNL.JAKO200211921342840
G704-000883.2002.5.4.008
OpenAccessLink http://click.ndsl.kr/servlet/LinkingDetailView?cn=JAKO200211921342840&dbt=JAKO&org_code=O481&site_code=SS1481&service_code=01
PageCount 11
ParticipantIDs nrf_kci_oai_kci_go_kr_ARTI_385570
kisti_ndsl_JAKO200211921342840
nurimedia_primary_NODE01601993
PublicationCentury 2000
PublicationDate 2002
PublicationDateYYYYMMDD 2002-01-01
PublicationDate_xml – year: 2002
  text: 2002
PublicationDecade 2000
PublicationTitle 멀티미디어학회논문지
PublicationTitleAlternate Journal of Korea Multimedia Society
PublicationYear 2002
Publisher 한국멀티미디어학회
Publisher_xml – name: 한국멀티미디어학회
SSID ssib044753026
ssib001149062
ssib053377227
ssib006781189
ssib036278602
ssib012146251
Score 1.5071182
Snippet In this paper, we present a content-based image retrieval method which is based on the feature extraction in the wavelet transform domain. In order to overcome...
KCI Citation Count: 1
SourceID nrf
kisti
nurimedia
SourceType Open Website
Open Access Repository
Publisher
StartPage 415
SubjectTerms 전자/정보통신공학
Title 웨이브릿 변환 영역에서 특징추출을 이용한 내용기반 영상 검색
URI https://www.dbpia.co.kr/journal/articleDetail?nodeId=NODE01601993
http://click.ndsl.kr/servlet/LinkingDetailView?cn=JAKO200211921342840&dbt=JAKO&org_code=O481&site_code=SS1481&service_code=01
https://www.kci.go.kr/kciportal/ci/sereArticleSearch/ciSereArtiView.kci?sereArticleSearchBean.artiId=ART000865473
Volume 5
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
ispartofPNX 멀티미디어학회논문지, 2002, 5(4), , pp.415-425
link http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV3NT9RAFG-Qi16MRo34QWrinJolQ9vpzhzb7pIVAxyEhFvTTlska7qK7MWDAeGi8eBBAipc_TiYEDUET_4_bPkffG9adrvRxA8uu2-nb2bex3bn97pv3mja7Sh2pMT6dgAWRA0RcY1HIq4lkrEkkZGgaiPtzKzTWrCnF9niyJlHlayl7mo0IZ_8dl_J_3gV2sCvuEv2HzzbHxQagAb_wit4GF7_ysek6RPhEZcrokE8mzQ94nHCfSRch3hThmqyMKOh2SBCEMENxQ5ck4qoE7dREoIiwW0ifAPZuUs8gU0uXGNIeA4R9gnhl_Ny26hIAIRLXKGmY8VIHuHm8DUXxfSoEo7-IhMHeScNxaVyMcomUYXSSkNR6sW9cjB3CgcGAqQsBBWOmrkQppDKLQ3EGfEKS_mql9KT9__AUWqygZrI0kAhgQBcnhmtjuHf7yxXnqYMmUFpobrAVNjlXpgtGa1uZqj0JzH0xGUQmfcNp_RnyjunUrWy8JimgEinOI5mIlFtgKYwQ4gOrVasclPalZXHLnbFliDGNtlgge-nXc7ONZpYURCTNrHeA7VwZZh52hwAaAiYaaWApIMbkQfnEQDaqeOhZSefsVqkRQcAHmIHiNbUOcl9hSDqw1BoGcBbtgKY72zWxYMr4NevAuTmL2jnywhMd4vb6aI20u5c0hbydx_zvW-9w5e99z_03te14zc7er6znm9_zrdf5Zu7-vGL7_mHrfzgdX6wm-9t6sCdv_10vLWr954hdXS439sv-mys60df1vKN55e1-anmvN-qlSeO1NoQGVk1HkaMA6COTMdyuBXZUQh4P05TxkUShgnEKiE3WULtesyxMTQZj-tmJEMZW4l1RRvNOllyVdMdakuWSjBZyiDCp2Fan5RpmoqEykjSaEwbV1YJsvjxg2DavTunsqWwOqEF_DYd026BuYK2XA6wAjy-L3WC9koAce6dwOJYOg8G6RszeFhUpwmqTr72J4br2jl1vJF6pnhDG11d6SY3AWWvRuPqi_ETgUeo1w
link.rule.ids 230,315,783,787,888,4033
linkProvider ISSN International Centre
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=%EC%9B%A8%EC%9D%B4%EB%B8%8C%EB%A6%BF+%EB%B3%80%ED%99%98+%EC%98%81%EC%97%AD%EC%97%90%EC%84%9C+%ED%8A%B9%EC%A7%95%EC%B6%94%EC%B6%9C%EC%9D%84+%EC%9D%B4%EC%9A%A9%ED%95%9C+%EB%82%B4%EC%9A%A9%EA%B8%B0%EB%B0%98+%EC%98%81%EC%83%81+%EA%B2%80%EC%83%89&rft.jtitle=%EB%A9%80%ED%8B%B0%EB%AF%B8%EB%94%94%EC%96%B4%ED%95%99%ED%9A%8C%EB%85%BC%EB%AC%B8%EC%A7%80&rft.au=%EC%B5%9C%EC%9D%B8%ED%98%B8%28In+Ho+Choi%29&rft.au=%EC%9D%B4%EC%83%81%ED%9B%88%28Sang+Hun+Lee%29&rft.date=2002&rft.pub=%ED%95%9C%EA%B5%AD%EB%A9%80%ED%8B%B0%EB%AF%B8%EB%94%94%EC%96%B4%ED%95%99%ED%9A%8C&rft.issn=1229-7771&rft.eissn=2384-0102&rft.volume=5&rft.issue=4&rft.spage=415&rft.epage=425&rft.externalDocID=NODE01601993
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1229-7771&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1229-7771&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1229-7771&client=summon