{"links":{},"id":69556,"metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00069556","sets":["1164:4619:5972:6107"]},"path":["6107"],"owner":"10","recid":"69556","title":["適応的な多変量正規分布による自然画像の事前確率モデル"],"pubdate":{"attribute_name":"公開日","attribute_value":"2010-05-20"},"_buckets":{"deposit":"e4ab8778-ee47-4f19-b351-d7cd793be357"},"_deposit":{"id":"69556","pid":{"type":"depid","value":"69556","revision_id":0},"owners":[10],"status":"published","created_by":10},"item_title":"適応的な多変量正規分布による自然画像の事前確率モデル","author_link":["0","0"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"適応的な多変量正規分布による自然画像の事前確率モデル"},{"subitem_title":"Natural Image prior model using adaptive multi-variate Gaussian distribution","subitem_title_language":"en"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"卒論ダイジェスト１","subitem_subject_scheme":"Other"}]},"item_type_id":"4","publish_date":"2010-05-20","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"東京工業大学制御システム工学科"},{"subitem_text_value":"東京工業大学大学院理工学研究科機械制御システム専攻"},{"subitem_text_value":"東京工業大学大学院理工学研究科機械制御システム専攻"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Department of Control and Systems Engineering, Tokyo Institute of Technology","subitem_text_language":"en"},{"subitem_text_value":"Graduate School of Science and Technology, Tokyo Institute of Technology","subitem_text_language":"en"},{"subitem_text_value":"Graduate School of Science and Technology, Tokyo Institute of Technology","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/69556/files/IPSJ-CVIM10172010.pdf"},"date":[{"dateType":"Available","dateValue":"2012-05-20"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-CVIM10172010.pdf","filesize":[{"value":"3.9 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":"6fc73bd0-84dc-4add-9ba3-678ec3dc7878","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2010 by the Information Processing Society of Japan"}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"山内, 啓大朗"},{"creatorName":"田中, 正行"},{"creatorName":"奥富, 正敏"}],"nameIdentifiers":[{}]}]},"item_4_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Keitaro, Yamauchi","creatorNameLang":"en"},{"creatorName":"Masayuki, Tanaka","creatorNameLang":"en"},{"creatorName":"Masatoshi, Okutomi","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_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"ディジタル画像をマルコフ確率場 (MRF) ととらえて事前確率分布をモデル化する方法が提案されている．多くの研究では，ポテンシャル関数のパラメータが固定された 「均質マルコフ確率場」 によってモデル化されている．本論文は，ポテンシャル関数のパラメータが適応的に推定される 「非均質マルコフ確率場」 を利用した自然画像の事前確率モデルを提案する．提案手法では，画像を低周波成分と高周波成分に分解し，高周波成分を非均質マルコフ確率場によってモデル化する．その際，ポテンシャル関数のパラメータは低周波成分をもとに適応的に推定される．本論文では，マルコフ確率場のポテンシャル関数として多変量正規分布を利用する．そのモデルを利用した最大事後確率推定によりデノイジングを行った．","subitem_description_type":"Other"}]},"item_4_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"Many prior models are proposed which model a digital image by a Markov Random Field (MRF). However, in many applications, only homogeneous MRF which has the potential function with fixed parameters is discussed. This paper proposes a natural image prior model which uses non-homogeneous MRF whose parameters are adaptively designed. In the proposed model, an image is decomposed into low- and high-frequency components. Then the high-frequency component is modeled by the non-homogeneous MRF. The parameters of the potential function are adaptively designed based on the low-frequency component associated to the high frequency component. In this paper, we use a multivariate Gaussian function for the potential function on the MRF. Finally, we use the proposed model for denoising by Maximum a-Posteriori estimation.","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":"2010-05-20","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"10","bibliographicVolumeNumber":"2010-CVIM-172"}]},"relation_version_is_last":true,"weko_creator_id":"10"},"created":"2025-01-18T23:28:59.332020+00:00","updated":"2025-01-21T23:52:42.606934+00:00"}