{"links":{},"id":2008648,"metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:02008648","sets":["581:1765244505933:1765246177381"]},"path":["1765246177381"],"owner":"80578","recid":"2008648","title":["画像内の反射成分の干渉下でも検出性能を維持できる画像中のプライバシーリスク検出手法"],"pubdate":{"attribute_name":"PubDate","attribute_value":"2026-03-15"},"_buckets":{"deposit":"be25bbe4-4128-4b5b-86c6-08d82318c4c6"},"_deposit":{"id":"2008648","pid":{"type":"depid","value":"2008648","revision_id":0},"owner":"80578","owners":[80578],"status":"published","created_by":80578},"item_title":"画像内の反射成分の干渉下でも検出性能を維持できる画像中のプライバシーリスク検出手法","author_link":[],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"画像内の反射成分の干渉下でも検出性能を維持できる画像中のプライバシーリスク検出手法","subitem_title_language":"ja"},{"subitem_title":"An Image Privacy Risk Detection that Maintains the Detection Performance under Interference from Reflective Components in the Image","subitem_title_language":"en"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"[特集：若手研究者] プライバシーリスク検出，Single Image Reflection Removal，マルチタスク学習，チャネルアテンション","subitem_subject_scheme":"Other"}]},"item_type_id":"2","publish_date":"2026-03-15","item_2_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"宮崎大学"},{"subitem_text_value":"宮崎大学"},{"subitem_text_value":"宮崎大学"},{"subitem_text_value":"神奈川工科大学"},{"subitem_text_value":"宮崎大学"}]},"item_2_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"University of Miyazaki","subitem_text_language":"en"},{"subitem_text_value":"University of Miyazaki","subitem_text_language":"en"},{"subitem_text_value":"University of Miyazaki","subitem_text_language":"en"},{"subitem_text_value":"Kanagawa Institute of Technology","subitem_text_language":"en"},{"subitem_text_value":"University of Miyazaki","subitem_text_language":"en"}]},"item_language":{"attribute_name":"言語","attribute_value_mlt":[{"subitem_language":"jpn"}]},"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/2008648/files/IPSJ-JNL6703011.pdf","label":"IPSJ-JNL6703011.pdf"},"date":[{"dateType":"Available","dateValue":"2028-03-15"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-JNL6703011.pdf","filesize":[{"value":"2.7 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":"8"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"070d94a9-7a56-41fa-bfd4-1ca9da404b93","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2026 by the Information Processing Society of Japan"}]},"item_2_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"臼崎,翔太郎"}]},{"creatorNames":[{"creatorName":"油田,健太郎"}]},{"creatorNames":[{"creatorName":"山場,久昭"}]},{"creatorNames":[{"creatorName":"朴,美娘"}]},{"creatorNames":[{"creatorName":"岡崎,直宣"}]}]},"item_2_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Shotaro Usuzaki","creatorNameLang":"en"}]},{"creatorNames":[{"creatorName":"Kentaro Aburada","creatorNameLang":"en"}]},{"creatorNames":[{"creatorName":"Hisaaki Yamaba","creatorNameLang":"en"}]},{"creatorNames":[{"creatorName":"Mirang Park","creatorNameLang":"en"}]},{"creatorNames":[{"creatorName":"Naonobu Okazaki","creatorNameLang":"en"}]}]},"item_2_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AN00116647","subitem_source_identifier_type":"NCID"}]},"item_resource_type":{"attribute_name":"資源タイプ","attribute_value_mlt":[{"resourceuri":"http://purl.org/coar/resource_type/c_6501","resourcetype":"journal article"}]},"item_2_publisher_15":{"attribute_name":"公開者","attribute_value_mlt":[{"subitem_publisher":"情報処理学会","subitem_publisher_language":"ja"}]},"item_2_source_id_11":{"attribute_name":"ISSN","attribute_value_mlt":[{"subitem_source_identifier":"1882-7764","subitem_source_identifier_type":"ISSN"}]},"item_2_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"本研究では，SNSでの画像投稿時の利用を想定し，画像内の反射成分による干渉下でも検出性能を維持できる，画像中のプライバシーリスク検出手法を提案する．反射成分とは，画像内において，透過物質越しに撮影した際に透過物質の手前の風景が反射し，本来の撮影対象に重なって映っている成分を指す．反射成分の像が重なって映るため，反射成分を含まない画像に比べてリスクの検出がしにくいことが予想される．本研究では，画像中に反射成分と透過成分が存在することを前提とし，次の3つの工夫を施したモデルを提案する．(1)反射成分の物体検出用の出力を追加する，(2)検出タスクだけでなく反射成分の分離タスクの同時学習を行う，(3)分離タスクの推測結果を検出タスクの補助情報として利用する．実験では，反射成分が存在する疑似的な画像を利用し，提案モデルと類似手法，個別に学習した手法と検出精度を比較した．実験の結果，提案モデルは反射成分が存在する画像でのリスク検出精度を一般的な手法よりも改善できた．検出精度をより高めるには，適切なパラメータ調整や学習方法を検討する必要があることが分かった．","subitem_description_type":"Other"}]},"item_2_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"In this study, we propose a novel image privacy risk detection method that accounts for an image's reflection component. The reflection component refers to the undesired entered component in which objects ahead of a transparent surface (e.g., glass) are reflected and overlapped onto the subject beyond the transparent surface. Since the transmission and reflection components spatially overlap in the image, detecting privacy risks becomes more challenging compared to images without such reflection. Assuming that both reflected and transmitted components coexist in an image, we propose a privacy risk detection model that incorporates the following three design elements: To this end, our approach introduced the following three strategies: (1) extending the output of the detection decoder with additional channels dedicated to reflection components; (2) formulating the problem as a multitask learning that simultaneously optimizes the privacy risk detection task and the reflection removal task; and (3) utilizing the estimated reflection components as auxiliary features for the detection task by channel attention. We conducted experiments using synthetically generated images that include reflection components and evaluated the performance of our proposed method against baseline models, including those trained on each task individually. The results demonstrate that the proposed method achieves superior detection accuracy compared to general approaches, confirming its effectiveness in handling privacy risks by reflection. It became clear that adjusting the appropriate parameters and learning methods were necessary to improve the detection performance.","subitem_description_type":"Other"}]},"item_2_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"604","bibliographic_titles":[{"bibliographic_title":"情報処理学会論文誌"}],"bibliographicPageStart":"588","bibliographicIssueDates":{"bibliographicIssueDate":"2026-03-15","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"3","bibliographicVolumeNumber":"67"}]},"relation_version_is_last":true,"item_2_identifier_registration":{"attribute_name":"ID登録","attribute_value_mlt":[{"subitem_identifier_reg_text":"10.20729/0002008648","subitem_identifier_reg_type":"JaLC"}]},"weko_creator_id":"80578"},"created":"2026-03-09T04:27:50.769476+00:00","updated":"2026-03-15T06:02:27.738937+00:00"}