{"updated":"2025-01-23T00:18:41.879450+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00015510","sets":["581:859:866"]},"path":["866"],"owner":"1","recid":"15510","title":["ネオコグニトロンの原理を用いた手書き数字認識　－マイクロコンピュータによるシステム－"],"pubdate":{"attribute_name":"公開日","attribute_value":"1987-06-15"},"_buckets":{"deposit":"bc8e992b-d179-455e-ba67-e12a3f8d647f"},"_deposit":{"id":"15510","pid":{"type":"depid","value":"15510","revision_id":0},"owners":[1],"status":"published","created_by":1},"item_title":"ネオコグニトロンの原理を用いた手書き数字認識　－マイクロコンピュータによるシステム－","author_link":["0","0"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"ネオコグニトロンの原理を用いた手書き数字認識　－マイクロコンピュータによるシステム－"},{"subitem_title":"Handwritten Numeral Recognition by the Algorithm of the Neocognitron -An Experimental System Using a Microcomputer-","subitem_title_language":"en"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"論文","subitem_subject_scheme":"Other"}]},"item_type_id":"2","publish_date":"1987-06-15","item_2_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"NHK放送技術研究所視覚情報研究部"},{"subitem_text_value":"NHK放送技術研究所視覚情報研究部"},{"subitem_text_value":"NHK放送技術研究所視覚情報研究部"},{"subitem_text_value":"早稲田大学理工学部電子通信学科"}]},"item_2_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Visual Science Research Division, NHK Science and Technical Research Laboratories","subitem_text_language":"en"},{"subitem_text_value":"Visual Science Research Division, NHK Science and Technical Research Laboratories","subitem_text_language":"en"},{"subitem_text_value":"Visual Science Research Division, NHK Science and Technical Research Laboratories","subitem_text_language":"en"},{"subitem_text_value":"Department of Electronics and Communication Engineering, School of Science and Engineering, Waseda University","subitem_text_language":"en"}]},"item_language":{"attribute_name":"言語","attribute_value_mlt":[{"subitem_language":"jpn"}]},"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/15510/files/IPSJ-JNL2806010.pdf"},"date":[{"dateType":"Available","dateValue":"1989-06-15"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-JNL2806010.pdf","filesize":[{"value":"736.6 kB"}],"mimetype":"application/pdf","priceinfo":[{"tax":["include_tax"],"price":"660","billingrole":"5"},{"tax":["include_tax"],"price":"330","billingrole":"6"},{"tax":["include_tax"],"price":"0","billingrole":"8"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"22090f45-1900-458e-9c73-abc92e32f508","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 1987 by the Information Processing Society of Japan"}]},"item_2_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"福島, 邦彦"},{"creatorName":"三宅, 誠"},{"creatorName":"伊藤, 崇之"},{"creatorName":"河野, 隆志"}],"nameIdentifiers":[{}]}]},"item_2_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Kunihiko, Fukushima","creatorNameLang":"en"},{"creatorName":"Sei, Miyake","creatorNameLang":"en"},{"creatorName":"Takayuki, Ito","creatorNameLang":"en"},{"creatorName":"Takashi, Kouno","creatorNameLang":"en"}],"nameIdentifiers":[{}]}]},"item_2_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AN00116647","subitem_source_identifier_type":"NCID"}]},"item_resource_type":{"attribute_name":"資源タイプ","attribute_value_mlt":[{"resourceuri":"http://purl.org/coar/resource_type/c_6501","resourcetype":"journal article"}]},"item_2_source_id_11":{"attribute_name":"ISSN","attribute_value_mlt":[{"subitem_source_identifier":"1882-7764","subitem_source_identifier_type":"ISSN"}]},"item_2_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"従来のパターン認識は入力パターンの変形や位置ずれの影響を避けるために まず入力パターンの位置や大きさの正規化を行った後に特徴抽出や識別を行う方式が多かった.これに対して 筆者らは先に 生物の視覚神経系を参考にして 高度のパターン認識能力と学習能力を持つ神経回路モデル\"ネオコグニトロン\"を提案した.ネオコグニトロンは 入力パターンの変形が位置ずれ ノイズなどに強いパターン認識能力を示す.生物の神経系をヒントにしているため その反応特性は人間に似ており 人間が似ていると感じるものはネオコグニトロンも似ていると判断する.しかも学習能力を持っているので あらかじめ学習させておけば どのようなパターンでも認識させることができる.すでにわれわれは ネオコグニトロンによる手書き数字認識システムをミニコンピュータで実現しているが 今回は ネオコグニトロンの演算量がどの程度かを一般の技術者に直感的にわかってもらうため 広く普及しているマイクロコンピュータを用いてシステムを構成した.プログラムは できるだけ高速に動作させるために種々の工夫をこらして作成した.このシステムがマイクロコンピュータでも実現可能であるということは その演算量がそれほど膨大なものではなく 専用のハードウェアを用いれば 実用になる速度で働くシステムを製作できることを示している.","subitem_description_type":"Other"}]},"item_2_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"635","bibliographic_titles":[{"bibliographic_title":"情報処理学会論文誌"}],"bibliographicPageStart":"627","bibliographicIssueDates":{"bibliographicIssueDate":"1987-06-15","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"6","bibliographicVolumeNumber":"28"}]},"relation_version_is_last":true,"item_2_alternative_title_2":{"attribute_name":"その他タイトル","attribute_value_mlt":[{"subitem_alternative_title":"画像情報処理"}]},"weko_creator_id":"1"},"created":"2025-01-18T22:49:02.327122+00:00","id":15510,"links":{}}