{"metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00216976","sets":["1164:4619:10826:10881"]},"path":["10881"],"owner":"44499","recid":"216976","title":["コンテンツ適応的な視認性予測モデルに基づく知覚ベースの画像合成"],"pubdate":{"attribute_name":"公開日","attribute_value":"2022-03-03"},"_buckets":{"deposit":"d9379298-4340-4ddc-b811-619adc5361ab"},"_deposit":{"id":"216976","pid":{"type":"depid","value":"216976","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"コンテンツ適応的な視認性予測モデルに基づく知覚ベースの画像合成","author_link":["561213","561212"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"コンテンツ適応的な視認性予測モデルに基づく知覚ベースの画像合成"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"セッション6-B ","subitem_subject_scheme":"Other"}]},"item_type_id":"4","publish_date":"2022-03-03","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"NTTコミュニケーション科学基礎研究所"},{"subitem_text_value":"東京大学生産技術研究所"}]},"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/216976/files/IPSJ-CVIM22229045.pdf","label":"IPSJ-CVIM22229045.pdf"},"date":[{"dateType":"Available","dateValue":"2024-03-03"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-CVIM22229045.pdf","filesize":[{"value":"20.5 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":"280125c8-ac02-49f8-8f89-c73bc6c201fb","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":"吹上, 大樹"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"大石, 岳史"}],"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":"重なり合った画像を表示する際,透過度を設定して半透明表示を行う方法がよく用いられる.しかし,合成後の画像の視認性は物理的な透過度だけではなく画像の特徴や組み合わせに依存して大きく変化してしまう.このため,表示される画像が常に変化し得るインタラクティブなアプリケーション上では視認性を期待する値に保つことが困難となる.この問題を解決する有効な方法として人間の視認性モデルに基づいて画素ごとに透過度を最適化することが考えられる.しかし,画質評価等で用いられる既存モデルは主に閾値付近でのノイズの視認性を予測することを目的としており,合成画像の閾値上の視認性の程度を正しく評価できる保証はない.とりわけ自然画像は画像毎に周波数や色等の特徴分布が大きく異なるため,これに応じて視認性評価時に着目される特徴が変わってくると考えられる.そこで我々は,合成画像の特徴毎の視認性を適応的に重み付けするコンテンツ適応型特徴集約機構を備えた視認性予測モデルを考案した.また,モデルの検証とキャリブレーションのために様々な自然画像を合成した大量の画像を用いて大規模な心理物理学実験を実施し,アブレーション実験を通じて適応的な特徴集約機構が合成画像の視認性予測にとって重要であることを確かめた.さらに,提案モデルに基づいて,ユーザーが視認性に基づいて直感的に画像合成を行える手法を開発し,その有効性を確認した.","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":"2022-03-03","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"45","bibliographicVolumeNumber":"2022-CVIM-229"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"id":216976,"updated":"2025-01-19T15:40:10.060499+00:00","links":{},"created":"2025-01-19T01:17:29.181555+00:00"}