[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-127461-en":3,"doc-seo-127461-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},127461,962084925290,"Ophelia","https://ap-avatar.wpscdn.com/davatar_085a072bc5b1113ac321206ff7593b45",8,"Research & Report","Deriving Orthographic Data from Classical Japanese Texts with Machine Learning Methods - Abstract","The project applies advanced machine-learning and computer-vision techniques to extract orthographic data from classical Japanese manuscript images, focusing on jibo 字母—the Chinese-character matrices underlying cursive hiragana. Inspired by NDLkotenOCR and KuroNet, it targets automation of jibo data generation to enable large-scale orthographic analysis and scribal attribution. Existing OCR tools omit jibo identification, limiting orthographic research. The planned pipeline supports batch recognition, frequency tabulation, and public-facing scholarly use for linguistic and historical insights.","Deriving Orthographic Data from Classical Japanese Texts with Machine  \nLearning Methods  \nHerman Chau / Michael R. Zeng / Paul S. Atkins (University of Washington, Seattle)  \nAbstract: This project applies advanced machine-learning techniques to extract orthographic data—specifically jibo 字母, the Chinese character matrices underlying cursive Japanese hiragana—from classical Japanese manuscripts. Inspired by the National Diet Library’s NDLkotenOCR and the Center for Open Data in the Humanities’ (CODH) KuroNet, our aim is to automate the generation of jibo data from manuscript images. This automation enables large-scale orthographic analysis and scribal attribution, which has traditionally required extensive manual effort. By integrating modern computer vision techniques, we seek to create a robust pipeline that identifies jibo to facilitate deeper linguistic and historical insights into classical Japanese texts.  \nKeywords: orthography, calligraphy, hiragana  \n概要：このプロジェクトでは、高度な機械学習技術を用いて、古典日本語の写本から表記データ(すなわち、ひらがなの基盤となる漢字「字母」 )を抽出する.国立国会図書館のNDLkotenOCR や、人文学オープンデータ共同利用センター（CODH）の KuroNet に触発され、写本画像から字母データを自動生成する仕組みを構築する.この自動化により、従来は膨大な手作業を要していた大規模な表記分析や筆者の特定が可能になる.最新のコンピュータビジョン技術を統合することで、字母を識別する堅牢なパイプラインを実現し、古典日本語テキストに対する言語的 ・ 歴史的理解を深める.  \nキーワード：表記、字母、ひらがな  \n1. Introduction  \nThis project applies advanced machine-learning techniques to extract orthographic data—specifically jibo 字母, the Chinese character matrices underlying cursive Japanese hiragana—from classical Japanese manuscripts. Inspired by the National Diet Library’s NDLkotenOCR and the Center for Open Data in the Humanities’ (CODH) KuroNet, our aim is to automate the generation of jibo data from manuscript images [1,2] . This automation enables large-scale orthographic analysis and scribal attribution, which have traditionally required extensive manual effort. By integrating modern computer vision techniques, we seek to create a robust pipeline that identifies jibo to facilitate deeper linguistic and historical insights into classical Japanese texts.  \n2. Background and Previous Work  \nThe writing system known as hiragana represents the sounds of the Japanese language using phonetic symbols that are highly cursivized forms of Chinese characters with similar pronunciations (e.g., the phonetic symbol あ A is derived from the character安 AN meaning ‘safety’) . Modern hiragana represents each sound with one and only one character (e.g., the sound A is always represented by あ) but, until the twentieth century, hiragana was polygraphic: each sound could be represented by multiple characters (e.g., the sound A could be represented also by cursivized versions of the characters 阿,亜,悪, or愛) and the  \nchoice of which to use appears to have been largely a question of personal preference. The historian of Japanese calligraphy Komatsu Shigemi (1925-2010) was the first scholar to demonstrate that statistical analysis of jibo ‘character matrices,’ the Chinese characters from which premodern scribes derived their hiragana symbols, could be used to identify the scribe of a manuscript [3] .  \nAlthough Komatsu’s method was innovative and his findings convincing, he did not apply modern statistical techniques of his analysis and therefore did not provide basic information, such as the probability that the results could have been obtained by chance. However, Komatsu’s method has been refined by and is being used to great effect by Professor Saitō Tetsuya of Shukutoku University in Japan. He has published a suite of articles categorizing texts by time period or scribe using statistical analysis of jibo orthographic data [e.g., 4,5] .  \nRecent work by Atkins and Zeng (under review) applies contemporary statistical techniques to the Ogura shikishi 小倉色紙, a famous corpus of some fifty poems attributed to the hand of the medieval Japanese poet Fujiwara no Teika 藤原定家(1162- 1241), revealing that none were likely inscribed by him. These findings underscore the potential of jibo analysis for historical","cbCaitxAsYI2xWQy","https://ap.wps.com/l/cbCaitxAsYI2xWQy","pdf",4015948,1,6,"English","en",105,"# Introduction\n# Background and Previous Work\n# Objective","[{\"question\":\"What is the main goal of this project?\",\"answer\":\"To automatically generate jibo orthographic data from classical Japanese manuscript images using machine learning and computer vision.\"},{\"question\":\"Why are existing OCR tools insufficient for this research?\",\"answer\":\"Tools like Miwo and NDLkotenOCR bypass jibo identification, preventing accurate orthographic research based on jibo analysis.\"},{\"question\":\"How will the project support scholarly analysis after extraction?\",\"answer\":\"It will enable batch recognition, tabulation of jibo frequencies, and visualization of relative frequencies to compare with known scribal patterns.\"}]","Deriving Orthographic Data from Classical Japanese Texts with Machine Learning Methods - Abstract | PDF",1785939030,15,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"deriving-orthographic-data-from-classical-japanese-texts-with-machine-learning-methods-abstract","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/deriving-orthographic-data-from-classical-japanese-texts-with-machine-learning-methods-abstract/127461/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-05",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What is the main goal of this project?","Question",{"text":75,"@type":76},"To automatically generate jibo orthographic data from classical Japanese manuscript images using machine learning and computer vision.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"Why are existing OCR tools insufficient for this research?",{"text":80,"@type":76},"Tools like Miwo and NDLkotenOCR bypass jibo identification, preventing accurate orthographic research based on jibo analysis.",{"name":82,"@type":73,"acceptedAnswer":83},"How will the project support scholarly analysis after extraction?",{"text":84,"@type":76},"It will enable batch recognition, tabulation of jibo frequencies, and visualization of relative frequencies to compare with known scribal patterns.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,114,119,122,127,130,134],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":21,"doc_module":4,"doc_module_name":46,"category_name":111,"show_sort_weight":112,"slug":113},"Technology",50,"technology",{"id":115,"doc_module":4,"doc_module_name":46,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]