{"created":"2025-01-18T23:33:16.366556+00:00","updated":"2025-01-21T20:46:58.020584+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00077755","sets":["6164:6165:6543:6544:6548"]},"path":["6548"],"owner":"10","recid":"77755","title":["領域分割に基づく見えの変化に頑強な歩容による個人識別"],"pubdate":{"attribute_name":"公開日","attribute_value":"2011-10-01"},"_buckets":{"deposit":"ad687be5-ba3b-4ebf-ac19-e6995f28c11b"},"_deposit":{"id":"77755","pid":{"type":"depid","value":"77755","revision_id":0},"owners":[10],"status":"published","created_by":10},"item_title":"領域分割に基づく見えの変化に頑強な歩容による個人識別","author_link":["0"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"領域分割に基づく見えの変化に頑強な歩容による個人識別"}]},"item_type_id":"18","publish_date":"2011-10-01","item_language":{"attribute_name":"言語","attribute_value_mlt":[{"subitem_language":"jpn"}]},"item_18_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"九州大学大学院システム情報科学府"},{"subitem_text_value":"九州大学大学院システム情報科学研究院"},{"subitem_text_value":"九州大学大学院システム情報科学研究院"}]},"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/77755/files/IPSJ-MIRU2011115.pdf"},"date":[{"dateType":"Available","dateValue":"2013-10-01"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-MIRU2011115.pdf","filesize":[{"value":"928.3 kB"}],"mimetype":"application/pdf","priceinfo":[{"tax":["include_tax"],"price":"0","billingrole":"5"},{"tax":["include_tax"],"price":"0","billingrole":"6"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"8b7008eb-4333-4976-aeac-fa91108a1926","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2011 by the Information Processing Society of Japan"}]},"item_18_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"内野康司"},{"creatorName":"岩下友美"},{"creatorName":"倉爪亮"}],"nameIdentifiers":[{}]}]},"item_resource_type":{"attribute_name":"資源タイプ","attribute_value_mlt":[{"resourceuri":"http://purl.org/coar/resource_type/c_5794","resourcetype":"conference paper"}]},"item_18_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"歩行画像列を用いた個人識別手法では，認識対象の人物像にデータベース作成時と異なる着衣や持ち物が存在した場合，一般に対象人物の見えが変化するために識別率が低下する．これに対し，予想される着衣等の変化を予めデータベース化する手法も考えられるが，全ての見えの変化を網羅するのは困難である．そこで本論文では，着衣の変化や鞄などの持ち物により対象人物の見えが変化する場合でも，見えの変化を予め学習することなく，頑強な個人識別を実現する歩容による個人識別手法を提案する．提案手法ではまず，歩行画像中の対象人物領域を複数領域に分割し，次に各領域において歩行特徴を計算する．これと標準的な歩行画像列から得られた全ての人物の歩行特徴データベースとを比較し，歩行特徴の類似度に応じて各領域の重みを計算する．その後，全領域の類似度の重み付き統合を行い，個人識別を行う．歩行画像データベースCASIA DB-B に対して提案手法を適用し，高い識別率で個人識別が可能であることを示す．","subitem_description_type":"Other"}]},"item_18_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"807","bibliographic_titles":[{"bibliographic_title":"画像の認識・理解シンポジウム(MIRU2011)論文集"}],"bibliographicPageStart":"802","bibliographicIssueDates":{"bibliographicIssueDate":"2011-07-20","bibliographicIssueDateType":"Issued"},"bibliographicVolumeNumber":"2011"}]},"relation_version_is_last":true,"weko_creator_id":"10"},"id":77755,"links":{}}