{"id":178418,"updated":"2025-01-20T05:07:44.597748+00:00","links":{},"created":"2025-01-19T00:47:46.045453+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00178418","sets":["1164:3206:9098:9099"]},"path":["9099"],"owner":"11","recid":"178418","title":["二値特徴量のノルムでの並べ替えによる画像間の対応点探索の高速化"],"pubdate":{"attribute_name":"公開日","attribute_value":"2017-03-06"},"_buckets":{"deposit":"8b15aab1-50a2-45e9-a48c-ee72ab4a0834"},"_deposit":{"id":"178418","pid":{"type":"depid","value":"178418","revision_id":0},"owners":[11],"status":"published","created_by":11},"item_title":"二値特徴量のノルムでの並べ替えによる画像間の対応点探索の高速化","author_link":["382035","382033","382034","382031","382036","382032"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"二値特徴量のノルムでの並べ替えによる画像間の対応点探索の高速化"},{"subitem_title":"Fast Binary Descriptor Search for Image Matching by Norm Ordering","subitem_title_language":"en"}]},"item_type_id":"4","publish_date":"2017-03-06","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"(株)富士通研究所"},{"subitem_text_value":"(株)富士通研究所"},{"subitem_text_value":"(株)富士通研究所"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"FUJITSU LABORATORIES LTD.","subitem_text_language":"en"},{"subitem_text_value":"FUJITSU LABORATORIES LTD.","subitem_text_language":"en"},{"subitem_text_value":"FUJITSU LABORATORIES LTD.","subitem_text_language":"en"}]},"item_language":{"attribute_name":"言語","attribute_value_mlt":[{"subitem_language":"jpn"}]},"item_publisher":{"attribute_name":"出版者","attribute_value_mlt":[{"subitem_publisher":"情報処理学会","subitem_publisher_language":"ja"}]},"publish_status":"0","weko_shared_id":-1,"item_file_price":{"attribute_name":"Billing file","attribute_type":"file","attribute_value_mlt":[{"url":{"url":"https://ipsj.ixsq.nii.ac.jp/record/178418/files/IPSJ-CG17166010.pdf","label":"IPSJ-CG17166010.pdf"},"date":[{"dateType":"Available","dateValue":"2019-03-06"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-CG17166010.pdf","filesize":[{"value":"589.0 kB"}],"mimetype":"application/pdf","priceinfo":[{"tax":["include_tax"],"price":"660","billingrole":"5"},{"tax":["include_tax"],"price":"330","billingrole":"6"},{"tax":["include_tax"],"price":"0","billingrole":"28"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"4d5faade-3ce3-405b-9bd9-6f161c144f19","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2017 by the Information Processing Society of Japan"}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"杉村, 昌彦"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"馬場, 孝之"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"上原, 祐介"}],"nameIdentifiers":[{}]}]},"item_4_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Masahiko, Sguimura","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Takayuki, Baba","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Yusuke, Uehara","creatorNameLang":"en"}],"nameIdentifiers":[{}]}]},"item_4_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AN10100541","subitem_source_identifier_type":"NCID"}]},"item_4_textarea_12":{"attribute_name":"Notice","attribute_value_mlt":[{"subitem_textarea_value":"SIG Technical Reports are nonrefereed and hence may later appear in any journals, conferences, symposia, etc."}]},"item_resource_type":{"attribute_name":"資源タイプ","attribute_value_mlt":[{"resourceuri":"http://purl.org/coar/resource_type/c_18gh","resourcetype":"technical report"}]},"item_4_source_id_11":{"attribute_name":"ISSN","attribute_value_mlt":[{"subitem_source_identifier":"2188-8949","subitem_source_identifier_type":"ISSN"}]},"item_4_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"画像間の対応点探索は，画像や映像の検索などに重要な技術である．BRIEF などの二値特徴量を用いることで高速な探索が可能だが，それでも総当たりでの探索は処理時間が大きい．Locality Sensitive Hashing (LSH) などハッシュ法を用いた探索手法は高速化に有効である反面，メモリ消費量が大幅に増加するため適用が難しい場合がある．一方，特徴量をノルムの大きさ順に並べ替え，ノルムの近い特徴量の範囲で探索を行う Norm Ordered Matching (NOM) は，メモリ消費量がほとんど増加しない．しかし，二値特徴量のノルムは二項分布に従う傾向があるため，特徴量のビット数の半分の値の周辺に集中し，そこでの処理時間が大きくなる課題がある．本稿では，二値特徴量の一部のビット値を反転することで，特徴量間の距離を保存したまま，ノルムの分布を平坦化することで，処理を高速化する手法を提案する．評価実験により，提案手法が NOM に対して高速であり，LSH に対して，精度と速度の面で同等であり，メモリ消費量の観点で優れていることを示した．","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"6","bibliographic_titles":[{"bibliographic_title":"研究報告コンピュータグラフィックスとビジュアル情報学（CG）"}],"bibliographicPageStart":"1","bibliographicIssueDates":{"bibliographicIssueDate":"2017-03-06","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"10","bibliographicVolumeNumber":"2017-CG-166"}]},"relation_version_is_last":true,"weko_creator_id":"11"}}