{"created":"2025-01-19T01:17:50.421908+00:00","updated":"2025-01-19T15:31:59.653650+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00217343","sets":["1164:3206:10884:10885"]},"path":["10885"],"owner":"44499","recid":"217343","title":["顔の特徴点を利用した人物顔画像の感情推定"],"pubdate":{"attribute_name":"公開日","attribute_value":"2022-03-04"},"_buckets":{"deposit":"72f57f23-36da-47e4-b3f3-589c49a0c15d"},"_deposit":{"id":"217343","pid":{"type":"depid","value":"217343","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"顔の特徴点を利用した人物顔画像の感情推定","author_link":["562998","563000","563001","562999"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"顔の特徴点を利用した人物顔画像の感情推定"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"顔画像処理とパラメタライズ","subitem_subject_scheme":"Other"}]},"item_type_id":"4","publish_date":"2022-03-04","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"現在，筑波大学"},{"subitem_text_value":"現在，筑波大学"},{"subitem_text_value":"現在，筑波大学"},{"subitem_text_value":"現在，筑波大学"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Presently with University of Tsukuba","subitem_text_language":"en"},{"subitem_text_value":"Presently with University of Tsukuba","subitem_text_language":"en"},{"subitem_text_value":"Presently with University of Tsukuba","subitem_text_language":"en"},{"subitem_text_value":"Presently with University of Tsukuba","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/217343/files/IPSJ-CG22185010.pdf","label":"IPSJ-CG22185010.pdf"},"date":[{"dateType":"Available","dateValue":"2024-03-04"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-CG22185010.pdf","filesize":[{"value":"3.4 MB"}],"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":"fe635587-b2d0-41d5-b543-14e6528e3af1","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2022 by the Information Processing Society of Japan"}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"金森, 透有"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"金森, 由博"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"遠藤, 結城"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"三谷, 純"}],"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":"人物の顔画像からの感情推定は，ニューラルネットワークを用いた教師あり学習手法により一定水準の精度に達している．本研究では，入力として顔画像だけでなく顔の特徴点を利用することで，さらなる精度向上を目指す．顔の特徴点のみを入力とした推定結果を，顔画像のみで学習済みのネットワークによる推定結果にマージすることによって精度向上を図るが，単体では前者の精度は後者に劣り，単純に合算しても精度は向上しない．そこで本研究では，顔画像のネットワークの出力は固定し，顔の特徴点のみの結果に対して，マージ時の重みの調整方法を 2 つ提案する．1 つ目は，推定の不確実さを利用する．具体的には，顔の特徴点による感情推定時に得られる各感情カテゴリの確率のうち最大のものを確信度と見なし，重みとして用いる．2 つ目は，顔の特徴点のみの推定結果が顔画像のみの推定結果と異なっている場合に重みを小さくする．以上により，提案手法が顔画像のみを入力としたベースライン手法による推定精度を上回ることを示す．","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"8","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":"2022-03-04","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"10","bibliographicVolumeNumber":"2022-CG-185"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"id":217343,"links":{}}