{"updated":"2025-01-20T05:50:01.578640+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00176517","sets":["6164:6805:6807:9016"]},"path":["9016"],"owner":"10","recid":"176517","title":["機械学習を用いたパターン認識による筆者識別"],"pubdate":{"attribute_name":"公開日","attribute_value":"2016-01-08"},"_buckets":{"deposit":"c7e0fdef-e048-4fa6-8a7b-8f1607d80e7e"},"_deposit":{"id":"176517","pid":{"type":"depid","value":"176517","revision_id":0},"owners":[10],"status":"published","created_by":10},"item_title":"機械学習を用いたパターン認識による筆者識別","author_link":["371695","371693","371696","371694"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"機械学習を用いたパターン認識による筆者識別"},{"subitem_title":"Writer Identification by the Pattern Recognition with Machine Learning","subitem_title_language":"en"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"筆跡，機械学習，ニューラルネットワーク，バックプロパゲーション法，画像解析","subitem_subject_scheme":"Other"}]},"item_type_id":"29","publish_date":"2016-01-08","item_language":{"attribute_name":"言語","attribute_value_mlt":[{"subitem_language":"jpn"}]},"item_29_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"九州工業大学情報工学部知能情報工学科"},{"subitem_text_value":"九州工業大学大学院情報工学研究院情報創成工学研究系"}]},"item_29_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Kyushu Institute of Technology","subitem_text_language":"en"},{"subitem_text_value":"Kyushu Institute of Technology","subitem_text_language":"en"}]},"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/176517/files/IPSJ-WPRO2016019.pdf","label":"IPSJ-WPRO2016019.pdf"},"date":[{"dateType":"Available","dateValue":"2016-01-08"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-WPRO2016019.pdf","filesize":[{"value":"630.0 kB"}],"mimetype":"application/pdf","priceinfo":[{"tax":["include_tax"],"price":"0","billingrole":"5"},{"tax":["include_tax"],"price":"0","billingrole":"6"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"809ffbbf-a020-42ee-abe6-71d1df49a56f","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2016 by the Information Processing Society of Japan"}]},"item_29_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"高橋, 真奈茄"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"小出, 洋"}],"nameIdentifiers":[{}]}]},"item_29_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Manaka, Takahashi","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Hiroshi, Koide","creatorNameLang":"en"}],"nameIdentifiers":[{}]}]},"item_resource_type":{"attribute_name":"資源タイプ","attribute_value_mlt":[{"resourceuri":"http://purl.org/coar/resource_type/c_5794","resourcetype":"conference paper"}]},"item_29_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"コンピュータは高度な演算が可能である一方，人物の識別などは不得手とされている．このような識別における課題の一つとして，筆跡の筆者識別が挙げられる．本稿では，機械学習を用いたアプローチからコンピュータによる効果的な筆跡の筆者識別手法を提案し，視覚情報に基づく判断論理形成についての考察を行う．提案手法では，筆跡画像を幾何学的に解析し，階層型ニューラルネットワークを用いたパターン認識によって筆者を識別する．階層型ニューラルネットワークを用いることで，より柔軟な筆者識別を目指す．また，提案手法を実装し，実装したシステムによる筆者識別実験と，改良したシステムによる処理時間計測実験を実施した．筆者識別実験では，最良で78%の識別精度を得られた．処理時間計測実験では，処理速度が8.6倍に向上した．","subitem_description_type":"Other"}]},"item_29_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"Although computers process a lot of tasks efficiently, they are weak in some problems like human recognition. One of these problems is a writer identification. In this manuscript, the authors propose an efficient pattern recognition method to identify a writer by using machine learning. The authors also give consideration to a logic to decide a author based on sight information. In The proposed method, makes an analyze of handwriting images geometrically first. And it identify a writer by using a pattern recognition with multi layer neural networks finally. Aim more flexible writer identification with using multi layer neural network. The authors implement the proposed methods on a multicore machine. And authors conduct experiments to evaluate the proposed method, and processing speed. The proposed method recognized a writer with 78 percent precision and the authors improved the processing speed of about 8.6 times.","subitem_description_type":"Other"}]},"item_29_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"142","bibliographic_titles":[{"bibliographic_title":"第57回プログラミング･シンポジウム予稿集"}],"bibliographicPageStart":"133","bibliographicIssueDates":{"bibliographicIssueDate":"2016-01-08","bibliographicIssueDateType":"Issued"},"bibliographicVolumeNumber":"2016"}]},"relation_version_is_last":true,"weko_creator_id":"10"},"created":"2025-01-19T00:46:09.540649+00:00","id":176517,"links":{}}