{"links":{},"metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00191891","sets":["1164:4619:9352:9579"]},"path":["9579"],"owner":"44499","recid":"191891","title":["一枚の線画イラストにおける閉領域の奥行き推定"],"pubdate":{"attribute_name":"公開日","attribute_value":"2018-10-31"},"_buckets":{"deposit":"557ca4af-6d86-4a30-8558-91924978ab4a"},"_deposit":{"id":"191891","pid":{"type":"depid","value":"191891","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"一枚の線画イラストにおける閉領域の奥行き推定","author_link":["444641","444642","444640","444639","444636","444638","444635","444637"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"一枚の線画イラストにおける閉領域の奥行き推定"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"一般セッション3","subitem_subject_scheme":"Other"}]},"item_type_id":"4","publish_date":"2018-10-31","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"筑波大学"},{"subitem_text_value":"筑波大学"},{"subitem_text_value":"筑波大学／現在，豊橋技術科学大学"},{"subitem_text_value":"筑波大学"}]},"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/191891/files/IPSJ-CVIM18214013.pdf","label":"IPSJ-CVIM18214013.pdf"},"date":[{"dateType":"Available","dateValue":"2020-10-31"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-CVIM18214013.pdf","filesize":[{"value":"1.1 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":"20"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"572d6461-6add-4d3b-aa8d-16c15988268d","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2018 by the Information Processing Society of Japan"}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"昆, 将太郎"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"金森, 由博"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"遠藤, 結城"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"三谷, 純"}],"nameIdentifiers":[{}]}]},"item_4_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Shotaro, Kon","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Yoshihiro, Kanamori","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Yuki, Endo","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Jun, Mitani","creatorNameLang":"en"}],"nameIdentifiers":[{}]}]},"item_4_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AA11131797","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":"2188-8701","subitem_source_identifier_type":"ISSN"}]},"item_4_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"与えられた景観画像中の物体の奥行きを推定する研究が，コンピュータビジョンの分野で盛んに行われてきた．自然画像を対象とした奥行き推定の研究は数多く存在するが，アニメやイラストなどの抽象画像の場合，自然画像のような濃淡や模様がなく，手がかりが少ないので奥行きの推定が難しい．本研究の目的は，白地背景に黒い線で描かれた線画の閉領域に対して，互いに隣接する閉領域の間でどちらが手前か奥かを自動で判定することである．本研究では教師あり学習によって線画の領域の局所的な推定を行い，有向グラフを用いることによって大域的な推定を行う．局所的な推定について，イラストによっては境界線の構造が複雑であり，従来の方法では教師あり学習に用いる特徴量の抽出が困難な場合がある．本研究ではそのようなイラストを考慮した特徴量の抽出方法を提案する．さらに，イラストの奥行き推定に適した新たな特徴量を提案し，精度の向上を図る．また，大域的な推定に用いる有向グラフのアルゴリズムについて，サイクルの除去の方法を新たに提案する．","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ビジョンとイメージメディア（CVIM）"}],"bibliographicPageStart":"1","bibliographicIssueDates":{"bibliographicIssueDate":"2018-10-31","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"13","bibliographicVolumeNumber":"2018-CVIM-214"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"updated":"2025-01-20T00:22:07.617395+00:00","created":"2025-01-19T00:57:41.877264+00:00","id":191891}