{"id":212484,"updated":"2025-01-19T17:30:18.053852+00:00","links":{},"created":"2025-01-19T01:13:25.662648+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00212484","sets":["1164:6390:10480:10634"]},"path":["10634"],"owner":"44499","recid":"212484","title":["半教師あり学習を用いた果実画像からのメロン等級判定システムの検討"],"pubdate":{"attribute_name":"公開日","attribute_value":"2021-08-26"},"_buckets":{"deposit":"a97c1d51-182d-4478-8923-56762c65f32f"},"_deposit":{"id":"212484","pid":{"type":"depid","value":"212484","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"半教師あり学習を用いた果実画像からのメロン等級判定システムの検討","author_link":["542233","542231","542232","542230","542229"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"半教師あり学習を用いた果実画像からのメロン等級判定システムの検討"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"農林水産","subitem_subject_scheme":"Other"}]},"item_type_id":"4","publish_date":"2021-08-26","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"静岡大学大学院自然科学系教育部情報科学専攻"},{"subitem_text_value":"静岡大学情報学部"},{"subitem_text_value":"静岡大学情報学部"},{"subitem_text_value":"（株）大和コンピューター"},{"subitem_text_value":"静岡大学学術院情報領域／グリーン科学技術研究所"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Graduate School of Science and Technology, Shizuoka University","subitem_text_language":"en"},{"subitem_text_value":"Faculty of Informatics, Shizuoka University","subitem_text_language":"en"},{"subitem_text_value":"Faculty of Informatics, Shizuoka University","subitem_text_language":"en"},{"subitem_text_value":"DAIWA COMPUTER CO., LTD.","subitem_text_language":"en"},{"subitem_text_value":"College of Informatics, Academic Institute, Shizuoka University / Research Institute of Green Science and 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/212484/files/IPSJ-CDS21032013.pdf","label":"IPSJ-CDS21032013.pdf"},"date":[{"dateType":"Available","dateValue":"2023-08-26"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-CDS21032013.pdf","filesize":[{"value":"1.2 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":"47"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"dd557115-d912-4989-a758-4f584592aecf","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2021 by the Information Processing Society of Japan"}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"小池, 誠"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"平原, 健太郎"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"渡辺, 隆一"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"小川, 晋"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"峰野, 博史"}],"nameIdentifiers":[{}]}]},"item_4_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AA12628327","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":"2188-8604","subitem_source_identifier_type":"ISSN"}]},"item_4_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"高級果物として知られるメロンは，果実の見栄えなど外見の品質が重要視されており，出荷時には形状や色合い，ネットの模様，傷の有無などを加味した等級の選別が行われている．このような外観検査は，経験豊富な生産者による目視確認が一般的であるが，近年の深層学習分野の発展により，外観検査に深層学習による画像認識モデルを適用する研究も注目されている．しかし，深層学習を用いるためには，大量のアノテーションされた画像データを収集する労力が問題となる．そこで，本研究では画像の類似度という尺度に着目し，深層距離学習とパッチ合成画像によるデータ拡張手法と，半教師あり学習を組み合わせることで，少ないラベルありデータから等級判定を行うシステムを検討する．回転テーブルを備えメロン果実の全周画像を取得する撮影部と，撮影した画像から等級を判定するサーバ部から構成される等級判定システムのプロトタイプを構築し，実現性についての基礎検証を実施した．その結果，画像の類似度という距離尺度を基にした等級判定モデルによって，約 60% の精度で等級判定が可能なことを確認した．また，等級判定システムが出力するデータ間の距離と，人間の等級判断との相関について分析することで，距離尺度を用いることの有用性を検討した．","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"8","bibliographic_titles":[{"bibliographic_title":"研究報告コンシューマ・デバイス＆システム（CDS）"}],"bibliographicPageStart":"1","bibliographicIssueDates":{"bibliographicIssueDate":"2021-08-26","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"13","bibliographicVolumeNumber":"2021-CDS-32"}]},"relation_version_is_last":true,"weko_creator_id":"44499"}}