{"updated":"2025-01-21T12:47:10.370773+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00097678","sets":["6164:6165:6210:7367"]},"path":["7367"],"owner":"11","recid":"97678","title":["将棋を対象とした画像情報を用いた自動局面認識手法"],"pubdate":{"attribute_name":"公開日","attribute_value":"2007-11-09"},"_buckets":{"deposit":"58ec5af4-bcd8-4e6d-94d0-7d8c809ab2c8"},"_deposit":{"id":"97678","pid":{"type":"depid","value":"97678","revision_id":0},"owners":[11],"status":"published","created_by":11},"item_title":"将棋を対象とした画像情報を用いた自動局面認識手法","author_link":["0","0"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"将棋を対象とした画像情報を用いた自動局面認識手法"},{"subitem_title":"Automatic position recognition method using image information in shogi","subitem_title_language":"en"}]},"item_type_id":"18","publish_date":"2007-11-09","item_language":{"attribute_name":"言語","attribute_value_mlt":[{"subitem_language":"jpn"}]},"item_18_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"東京大学大学院工学系研究科"},{"subitem_text_value":"東京大学大学院新領域創成科学研究科"},{"subitem_text_value":"東京大学大学院工学系研究科／東京大学大学院新領域創成科学研究科"}]},"item_18_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Graduate School of Engineering, The University of Tokyo","subitem_text_language":"en"},{"subitem_text_value":"Graduate School of Frontier Sciences, The University of Tokyo","subitem_text_language":"en"},{"subitem_text_value":"Graduate School of Engineering, The University of Tokyo / Graduate School of Frontier Sciences, The University of Tokyo","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/97678/files/IPSJ-GPWS2007030.pdf"},"date":[{"dateType":"Available","dateValue":"2007-11-09"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-GPWS2007030.pdf","filesize":[{"value":"3.7 MB"}],"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":"d7475a3c-33cd-4438-83bb-6a60ef2c2ef5","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2007 by the Information Processing Society of Japan"}]},"item_18_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"栗田, 哲平"},{"creatorName":"三輪, 誠"},{"creatorName":"近山, 隆"}],"nameIdentifiers":[{}]}]},"item_18_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Kurita, Teppei","creatorNameLang":"en"},{"creatorName":"Miwa, Makoto","creatorNameLang":"en"},{"creatorName":"Chikayama, Takashi","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_18_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"将棋における画像情報を用いた精度の高い局面の自動認識は，現実の対極での棋譜の効率的取得およびユーザ支援をするにあたって重要な処理である．精度の高い自動認識をするためには，その時の状況に因ってパラメータを変え，ロバストに将棋盤の認識と局面状況の認識を行う必要がある．本研究では将棋を対象とし盤の桝目の認識と，差分情報を用いた局面の自動認識を精度高く行う事を目的としている．駒の動きは事前に得ておいた訓練例を用いて決定木を構成し分類を行い，打った駒は初期盤面の駒情報を訓練例とし逐次最小最適化法を用いた Support Vector Machine による分類によって，その種類の判断を行った．結果として，今回の実験例では 640 × 480 の解像度を持つカメラからの画像情報を用いて，桝目の認識はパラメータを調整しないで 97.0%，桝目属性の分類に 99.7%，打った駒の判断を 100%の正解率で分類を行う事が出来た．","subitem_description_type":"Other"}]},"item_18_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"Automatic position recognition with high accuracy is a critical process for automatic capture of game records in shogi. For high accuracy recognition, recognition of shogi board and game situation is desirable without parameter adjustment. In this paper, we recognize a shogi board and its position situation based on image dierence information. The action of pieces is recognized using decision tree with training data. Pushed pieces is classied using Sequential Minimal Optimization with rst position informations of board. As experimental results, board position was recognized with the accuracy of about 97.0%, the cells were classied with the accuracy of 99.7%, and placed pieces were classied with the accuracy of 100%.","subitem_description_type":"Other"}]},"item_18_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"179","bibliographic_titles":[{"bibliographic_title":"ゲームプログラミングワークショップ2007論文集"}],"bibliographicPageStart":"172","bibliographicIssueDates":{"bibliographicIssueDate":"2007-11-09","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"12","bibliographicVolumeNumber":"2007"}]},"relation_version_is_last":true,"weko_creator_id":"11"},"created":"2025-01-18T23:44:08.564125+00:00","id":97678,"links":{}}