{"links":{},"id":53380,"metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00053380","sets":["1164:4619:4721:4722"]},"path":["4722"],"owner":"1","recid":"53380","title":["輪郭とエッジの一致尺度に基づく高速な再帰的閾値決定法"],"pubdate":{"attribute_name":"公開日","attribute_value":"1992-11-19"},"_buckets":{"deposit":"eb8d7161-9033-4cd1-8355-a9036321d949"},"_deposit":{"id":"53380","pid":{"type":"depid","value":"53380","revision_id":0},"owners":[1],"status":"published","created_by":1},"item_title":"輪郭とエッジの一致尺度に基づく高速な再帰的閾値決定法","author_link":["0","0"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"輪郭とエッジの一致尺度に基づく高速な再帰的閾値決定法"},{"subitem_title":"High Speed Algorithm for Recursive Threshold Selection Based on Edge and Contour Evaluation","subitem_title_language":"en"}]},"item_type_id":"4","publish_date":"1992-11-19","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"横浜国立大学工学部"},{"subitem_text_value":"横浜国立大学工学部"},{"subitem_text_value":"横浜国立大学工学部"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Yokohama National University","subitem_text_language":"en"},{"subitem_text_value":"Yokohama National University","subitem_text_language":"en"},{"subitem_text_value":"Yokohama National 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/53380/files/IPSJ-CVIM92080021.pdf"},"date":[{"dateType":"Available","dateValue":"1994-11-19"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-CVIM92080021.pdf","filesize":[{"value":"1.1 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":"b17e2b6c-cb96-4bfe-ae10-0e7acf8bc467","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 1992 by the Information Processing Society of Japan"}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"河村, 真"},{"creatorName":"後藤, 敏行"},{"creatorName":"関口, 隆"}],"nameIdentifiers":[{}]}]},"item_4_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Makoto, Kawamura","creatorNameLang":"en"},{"creatorName":"Toshiyuki, Gotoh","creatorNameLang":"en"},{"creatorName":"Takashi, Sekiguchi","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_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"輪郭とエッジの一致尺度は二値化の閾値決定に有効であるが、これを多段階閾値選択に拡張しようとする場合、第一の閾値処理により生成された輪郭が第二の閾値評価に影響を及ぼすという問題がある。本論文ではこの問題を回避し、再帰処理により高速に閾値を決定できる高速手法を提案する。閾値Tで二値化した時の輪郭が、最大値フィルタ処理画像濃度がT以上かつ最小値フィルタ処理画像濃度がT未満であることを利用し、再帰の各段階で各濃度に対する輪郭上のエッジの割合を推定、これに基づいて閾値を濃度レベル数の二乗のオーダーで決定することが可能になった。","subitem_description_type":"Other"}]},"item_4_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"This paper describes a high speed algorithm for recursive thresholds selection based on edge and contour evaluation. First we discuss the problem of extending the conventional method to a multiple thresholds selection. Then we discuss the condition of a pixel(x, y) which is on the contour of the image binarized by threshold T : Max(x, y)≧T and Min(x, y)