{"updated":"2025-01-20T00:43:22.910932+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00191374","sets":["1164:4619:9352:9559"]},"path":["9559"],"owner":"11","recid":"191374","title":["インパルス性雑音除去への深層学習の応用に関する検討"],"pubdate":{"attribute_name":"公開日","attribute_value":"2018-09-13"},"_buckets":{"deposit":"7f319d39-1b61-4c6e-a358-888937035411"},"_deposit":{"id":"191374","pid":{"type":"depid","value":"191374","revision_id":0},"owners":[11],"status":"published","created_by":11},"item_title":"インパルス性雑音除去への深層学習の応用に関する検討","author_link":["441205","441204","441196","441206","441207","441202","441200","441203","441201","441198","441199","441197"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"インパルス性雑音除去への深層学習の応用に関する検討"},{"subitem_title":"A Study on Impulse Noise Removal with Deep Learning","subitem_title_language":"en"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"ディスカッションセッション5","subitem_subject_scheme":"Other"}]},"item_type_id":"4","publish_date":"2018-09-13","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"長野工業高等専門学校"},{"subitem_text_value":"長野工業高等専門学校"},{"subitem_text_value":"長野工業高等専門学校"},{"subitem_text_value":"長野工業高等専門学校"},{"subitem_text_value":"長野工業高等専門学校"},{"subitem_text_value":"信州大学工学部"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"National Institute of Technology, Nagano College","subitem_text_language":"en"},{"subitem_text_value":"National Institute of Technology, Nagano College","subitem_text_language":"en"},{"subitem_text_value":"National Institute of Technology, Nagano College","subitem_text_language":"en"},{"subitem_text_value":"National Institute of Technology, Nagano College","subitem_text_language":"en"},{"subitem_text_value":"National Institute of Technology, Nagano College","subitem_text_language":"en"},{"subitem_text_value":"Faculty of Engineering, Shinshu University","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/191374/files/IPSJ-CVIM18213029.pdf","label":"IPSJ-CVIM18213029.pdf"},"date":[{"dateType":"Available","dateValue":"2020-09-13"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-CVIM18213029.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":"20"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"fdf0674c-5351-4cb9-9a66-8ac5df012474","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":"天利, 安志"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"宮崎, 敬"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"村上, 舜"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"越村, 勇介"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"横山, 靖樹"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"山本, 博章"}],"nameIdentifiers":[{}]}]},"item_4_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Yasushi, Amari","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Takashi, Miyazaki","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Shun, Murakami","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Yusuke, Koshimura","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Yasuki, Yokoyama","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Hiroaki, Yamamoto","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":"近年，デジタルカメラに用いられる CMOS イメージセンサの高解像度化に伴い，受光部の単位面積当たりの入射光量の減少により，光量のわずかな変動がインパルス性雑音の発生に影響する．これまで，MF (メジアンフィルタ) 法などの雑音除去手法によって画質の向上がなされてきた．最近，ガウス性雑音やバースト雑音に対して深層学習を応用した雑音除去方法が提案され，有効性が示されている．本稿では，この深層学習を用いたインパルス性雑音除去方法について検討を行い，その結果を報告する. 特に，損失関数を変えた時および Squeeze-and-Excitation block を用いた時の結果画像の画質への影響を調べた．また，ガウス性雑音に対する有効性を調べた．","subitem_description_type":"Other"}]},"item_4_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"As camera resolution progresses to higher resolution, a slight variation in light amount affects the generation of impulse noises due to decrement in the amount of incident light per unit cell of the light receiving area. So far, image quality has been improved by noise removal methods such as Median Filter (MF). Recently, a noise removal method applying Deep Learning to gaussian noise and burst noise has been proposed, and its effectiveness has been shown. In this paper, we investigate impulse noise removal method with Deep Learning and report the results of removed images using proposed method. In particular, we investigated the effect on the image quality of the result image when changing the loss function and using Squeeze-and-Excitation block. In addition, we examined the effectiveness of the proposed network against gaussian noise.","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":"2018-09-13","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"29","bibliographicVolumeNumber":"2018-CVIM-213"}]},"relation_version_is_last":true,"weko_creator_id":"11"},"created":"2025-01-19T00:57:15.997403+00:00","id":191374,"links":{}}