{"id":102988,"updated":"2025-01-21T10:36:18.494699+00:00","links":{},"created":"2025-01-18T23:48:05.611704+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00102988","sets":["1164:3616:7453:7660"]},"path":["7660"],"owner":"11","recid":"102988","title":["画像情報に基づいたガウス雑音の標準偏差の推定"],"pubdate":{"attribute_name":"公開日","attribute_value":"2014-09-04"},"_buckets":{"deposit":"a325e65d-eee6-4725-8b85-4fcf45748c8a"},"_deposit":{"id":"102988","pid":{"type":"depid","value":"102988","revision_id":0},"owners":[11],"status":"published","created_by":11},"item_title":"画像情報に基づいたガウス雑音の標準偏差の推定","author_link":["0","0"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"画像情報に基づいたガウス雑音の標準偏差の推定"},{"subitem_title":"An Estimate Method of Standard Deviation for Gaussian Noise with Image Information","subitem_title_language":"en"}]},"item_type_id":"4","publish_date":"2014-09-04","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"神奈川工科大学情報学部"},{"subitem_text_value":"神奈川工科大学情報学部"},{"subitem_text_value":"東京都市大学知識工学部"},{"subitem_text_value":"神奈川工科大学情報学部"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Faculty of Informatics, Kanagawa Institute of Technology","subitem_text_language":"en"},{"subitem_text_value":"Faculty of Informatics, Kanagawa Institute of Technology","subitem_text_language":"en"},{"subitem_text_value":"Faculty of Knowledge Engineering, Tokyo City University","subitem_text_language":"en"},{"subitem_text_value":"Faculty of Informatics, Kanagawa 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/102988/files/IPSJ-AVM14086008.pdf"},"date":[{"dateType":"Available","dateValue":"2100-01-01"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-AVM14086008.pdf","filesize":[{"value":"735.6 kB"}],"mimetype":"application/pdf","priceinfo":[{"tax":["include_tax"],"price":"0","billingrole":"27"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"279f9fed-85ee-4278-83c4-1652f8e24a49","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2014 by the Institute of Electronics, Information and Communication Engineers This SIG report is only available to those in membership of the SIG."}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"鈴木, 貴士"},{"creatorName":"辻, 裕之"},{"creatorName":"田口, 亮"},{"creatorName":"木村, 誠聡"}],"nameIdentifiers":[{}]}]},"item_4_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Takashi, Suzuki","creatorNameLang":"en"},{"creatorName":"Hiroyuki, Tsuji","creatorNameLang":"en"},{"creatorName":"Akira, Taguchi","creatorNameLang":"en"},{"creatorName":"Tomoaki, Kimura","creatorNameLang":"en"}],"nameIdentifiers":[{}]}]},"item_4_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AN10438399","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":"データ依存型の雑音除去フィルタでは加法雑音の標準偏差等をフィルタ処理に用いる場合も多い．当然，加法雑音の標準偏差等は未知であるから，劣化画像からそれらを推定する必要がある．ガウス雑音によって劣化した画像から重畳しているガウス雑音の標準偏差を推定する方法として，PCA を用いた方法や MAD を利用した方法などがある．PCA を用いる方法は，推定精度は良いが計算量が非常に多く，MAD を利用する方法は，計算量は少ないものの画像の種類･性質によって推定精度が悪くなる．そこで，本稿では MAD を利用した方法を拡張し，計算量が少なく推定精度が画像の種類・性質に依存せず高くなる方法を提案する．提案法では画像をサブブロツクに分割し，そのブロック毎に推定される標準偏差の値をもとに画像の性質 （画像中のエッジや細部の含有量に対応する） をパラメータ化 （画像性質パラメータ） する．そして推定した画像性質パラメータを用いて重畳している雑音の MAD による標準偏差推定値を補正するための補正係数を導出する．本稿ではその補正係数を画像性質パラメータの一次式で表されること明らかにする．提案法と MAD 値を利用した従来法との比較を 21 種類の標準画像を用いて行った．その結果，従来法の標準偏差推定誤差が 21 画像の平均で 25%であったものが，提案法では 8%まで下がることを明らかにする．","subitem_description_type":"Other"}]},"item_4_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"The standard deviation of Gaussian noise is required for restoration of degradation images. At the moment, the estimating method of Gaussian noise's standard deviation is proposed by PCA or MAD value. However, these methods have the problems, such as a large amount of computation time and estimate's error. Therefore, we proposed the estimate method of Gaussian noise's standard deviation which extended MAD value. The proposed method corrects the estimation value of standard deviation by using liner expression. As a result of applying this proposed method to some degraded images, it confirmed that the standard deviation's error of this proposed method is small than conventional method.","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"6","bibliographic_titles":[{"bibliographic_title":"研究報告オーディオビジュアル複合情報処理（AVM）"}],"bibliographicPageStart":"1","bibliographicIssueDates":{"bibliographicIssueDate":"2014-09-04","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"8","bibliographicVolumeNumber":"2014-AVM-86"}]},"relation_version_is_last":true,"weko_creator_id":"11"}}