Enhanced SIFT Descriptor Based on Modified Discrete Gaussian-Hermite Moment
The discrete Gaussian-Hermite moment (DGHM) is a global feature representation method that can be applied to square images. We propose a modified DGHM (MDGHM) method and an MDGHM-based scale-invariant feature transform (MDGHM-SIFT) descriptor. In the MDGHM, we devise a movable mask to represent the...
Gespeichert in:
Veröffentlicht in: | ETRI journal 2012-08, Vol.34 (4), p.572-582 |
---|---|
Hauptverfasser: | , , , |
Format: | Artikel |
Sprache: | kor |
Online-Zugang: | Volltext |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
container_end_page | 582 |
---|---|
container_issue | 4 |
container_start_page | 572 |
container_title | ETRI journal |
container_volume | 34 |
creator | Kang, Tae-Koo Zhang, Huazhen Kim, Dong W Park, Gwi-Tae |
description | The discrete Gaussian-Hermite moment (DGHM) is a global feature representation method that can be applied to square images. We propose a modified DGHM (MDGHM) method and an MDGHM-based scale-invariant feature transform (MDGHM-SIFT) descriptor. In the MDGHM, we devise a movable mask to represent the local features of a non-square image. The complete set of non-square image features are then represented by the summation of all MDGHMs. We also propose to apply an accumulated MDGHM using multi-order derivatives to obtain distinguishable feature information in the third stage of the SIFT. Finally, we calculate an MDGHM-based magnitude and an MDGHM-based orientation using the accumulated MDGHM. We carry out experiments using the proposed method with six kinds of deformations. The results show that the proposed method can be applied to non-square images without any image truncation and that it significantly outperforms the matching accuracy of other SIFT algorithms. |
format | Article |
fullrecord | <record><control><sourceid>kyobo_kisti</sourceid><recordid>TN_cdi_kisti_ndsl_JAKO201254059648676</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>4010023470528</sourcerecordid><originalsourceid>FETCH-LOGICAL-k608-7650f65e73f659b733775c4b4385cd4b0bb55ad63e66e998a7849a095a2897963</originalsourceid><addsrcrecordid>eNpNTjtrxDAYM6WFHtf7D1k6Gvz6_Biv935xQ7MHO3GoyZ1d4nTov6-hHbpIQhJCD2jGGOdYcSYf0YwyBlgKyZ_RIufgCFBKFdNqhk6b-GFj67vq_bCtq7XP7Rg-pzRWbzYXN8XqkrrQh6LXoYR-8tXOfpUZG_Hej_dQjEu6-zi9oKfe3rJf_PEc1dtNvdrj83V3WC3PeJBEYyWB9BK84gWNU5wrBa1wgmtoO-GIcwC2k9xL6Y3RVmlhLDFgmTbKSD5Hr7-zQ8hTaGKXb81xeboyQhkIAkYKLdX_3ndyqXEpDW156cdGEEoI40IRYJr_AKz4U3A</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Enhanced SIFT Descriptor Based on Modified Discrete Gaussian-Hermite Moment</title><source>Wiley Online Library website</source><source>Free E-Journal (出版社公開部分のみ)</source><creator>Kang, Tae-Koo ; Zhang, Huazhen ; Kim, Dong W ; Park, Gwi-Tae</creator><creatorcontrib>Kang, Tae-Koo ; Zhang, Huazhen ; Kim, Dong W ; Park, Gwi-Tae</creatorcontrib><description>The discrete Gaussian-Hermite moment (DGHM) is a global feature representation method that can be applied to square images. We propose a modified DGHM (MDGHM) method and an MDGHM-based scale-invariant feature transform (MDGHM-SIFT) descriptor. In the MDGHM, we devise a movable mask to represent the local features of a non-square image. The complete set of non-square image features are then represented by the summation of all MDGHMs. We also propose to apply an accumulated MDGHM using multi-order derivatives to obtain distinguishable feature information in the third stage of the SIFT. Finally, we calculate an MDGHM-based magnitude and an MDGHM-based orientation using the accumulated MDGHM. We carry out experiments using the proposed method with six kinds of deformations. The results show that the proposed method can be applied to non-square images without any image truncation and that it significantly outperforms the matching accuracy of other SIFT algorithms.</description><identifier>ISSN: 1225-6463</identifier><identifier>EISSN: 2233-7326</identifier><language>kor</language><publisher>한국전자통신연구원</publisher><ispartof>ETRI journal, 2012-08, Vol.34 (4), p.572-582</ispartof><rights>COPYRIGHT(C) KYOBO BOOK CENTRE ALL RIGHTS RESERVED</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>230,314,780,784,885</link.rule.ids></links><search><creatorcontrib>Kang, Tae-Koo</creatorcontrib><creatorcontrib>Zhang, Huazhen</creatorcontrib><creatorcontrib>Kim, Dong W</creatorcontrib><creatorcontrib>Park, Gwi-Tae</creatorcontrib><title>Enhanced SIFT Descriptor Based on Modified Discrete Gaussian-Hermite Moment</title><title>ETRI journal</title><addtitle>ETRI journal</addtitle><description>The discrete Gaussian-Hermite moment (DGHM) is a global feature representation method that can be applied to square images. We propose a modified DGHM (MDGHM) method and an MDGHM-based scale-invariant feature transform (MDGHM-SIFT) descriptor. In the MDGHM, we devise a movable mask to represent the local features of a non-square image. The complete set of non-square image features are then represented by the summation of all MDGHMs. We also propose to apply an accumulated MDGHM using multi-order derivatives to obtain distinguishable feature information in the third stage of the SIFT. Finally, we calculate an MDGHM-based magnitude and an MDGHM-based orientation using the accumulated MDGHM. We carry out experiments using the proposed method with six kinds of deformations. The results show that the proposed method can be applied to non-square images without any image truncation and that it significantly outperforms the matching accuracy of other SIFT algorithms.</description><issn>1225-6463</issn><issn>2233-7326</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2012</creationdate><recordtype>article</recordtype><sourceid>JDI</sourceid><recordid>eNpNTjtrxDAYM6WFHtf7D1k6Gvz6_Biv935xQ7MHO3GoyZ1d4nTov6-hHbpIQhJCD2jGGOdYcSYf0YwyBlgKyZ_RIufgCFBKFdNqhk6b-GFj67vq_bCtq7XP7Rg-pzRWbzYXN8XqkrrQh6LXoYR-8tXOfpUZG_Hej_dQjEu6-zi9oKfe3rJf_PEc1dtNvdrj83V3WC3PeJBEYyWB9BK84gWNU5wrBa1wgmtoO-GIcwC2k9xL6Y3RVmlhLDFgmTbKSD5Hr7-zQ8hTaGKXb81xeboyQhkIAkYKLdX_3ndyqXEpDW156cdGEEoI40IRYJr_AKz4U3A</recordid><startdate>20120831</startdate><enddate>20120831</enddate><creator>Kang, Tae-Koo</creator><creator>Zhang, Huazhen</creator><creator>Kim, Dong W</creator><creator>Park, Gwi-Tae</creator><general>한국전자통신연구원</general><general>ETRI</general><scope>P5Y</scope><scope>SSSTE</scope><scope>JDI</scope></search><sort><creationdate>20120831</creationdate><title>Enhanced SIFT Descriptor Based on Modified Discrete Gaussian-Hermite Moment</title><author>Kang, Tae-Koo ; Zhang, Huazhen ; Kim, Dong W ; Park, Gwi-Tae</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-k608-7650f65e73f659b733775c4b4385cd4b0bb55ad63e66e998a7849a095a2897963</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>kor</language><creationdate>2012</creationdate><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Kang, Tae-Koo</creatorcontrib><creatorcontrib>Zhang, Huazhen</creatorcontrib><creatorcontrib>Kim, Dong W</creatorcontrib><creatorcontrib>Park, Gwi-Tae</creatorcontrib><collection>교보문고스콜라</collection><collection>Scholar(스콜라)</collection><collection>KoreaScience</collection><jtitle>ETRI journal</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Kang, Tae-Koo</au><au>Zhang, Huazhen</au><au>Kim, Dong W</au><au>Park, Gwi-Tae</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Enhanced SIFT Descriptor Based on Modified Discrete Gaussian-Hermite Moment</atitle><jtitle>ETRI journal</jtitle><addtitle>ETRI journal</addtitle><date>2012-08-31</date><risdate>2012</risdate><volume>34</volume><issue>4</issue><spage>572</spage><epage>582</epage><pages>572-582</pages><issn>1225-6463</issn><eissn>2233-7326</eissn><abstract>The discrete Gaussian-Hermite moment (DGHM) is a global feature representation method that can be applied to square images. We propose a modified DGHM (MDGHM) method and an MDGHM-based scale-invariant feature transform (MDGHM-SIFT) descriptor. In the MDGHM, we devise a movable mask to represent the local features of a non-square image. The complete set of non-square image features are then represented by the summation of all MDGHMs. We also propose to apply an accumulated MDGHM using multi-order derivatives to obtain distinguishable feature information in the third stage of the SIFT. Finally, we calculate an MDGHM-based magnitude and an MDGHM-based orientation using the accumulated MDGHM. We carry out experiments using the proposed method with six kinds of deformations. The results show that the proposed method can be applied to non-square images without any image truncation and that it significantly outperforms the matching accuracy of other SIFT algorithms.</abstract><pub>한국전자통신연구원</pub><tpages>11</tpages><oa>free_for_read</oa></addata></record> |
fulltext | fulltext |
identifier | ISSN: 1225-6463 |
ispartof | ETRI journal, 2012-08, Vol.34 (4), p.572-582 |
issn | 1225-6463 2233-7326 |
language | kor |
recordid | cdi_kisti_ndsl_JAKO201254059648676 |
source | Wiley Online Library website; Free E-Journal (出版社公開部分のみ) |
title | Enhanced SIFT Descriptor Based on Modified Discrete Gaussian-Hermite Moment |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-25T07%3A35%3A05IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-kyobo_kisti&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Enhanced%20SIFT%20Descriptor%20Based%20on%20Modified%20Discrete%20Gaussian-Hermite%20Moment&rft.jtitle=ETRI%20journal&rft.au=Kang,%20Tae-Koo&rft.date=2012-08-31&rft.volume=34&rft.issue=4&rft.spage=572&rft.epage=582&rft.pages=572-582&rft.issn=1225-6463&rft.eissn=2233-7326&rft_id=info:doi/&rft_dat=%3Ckyobo_kisti%3E4010023470528%3C/kyobo_kisti%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 |