"Collapsed" calligraphy, part 2

« previous post | next post »

New article by Nyri Bakkalian in Unseen Japan (9/17/22):

"New App Promises Greater Convenience in Reading Old Japanese Cursive:

Kuzushiji, the 'crushed letters' found in historical Japanese documents, have long been the bane of scholars. A new app may change all that."

The author bemoans:

During my graduate education in Japanese history, interpreting handwritten primary source material from the 19th century and earlier was one of my greatest challenges. Typeset historic documents exist, especially in my period of focus during the Bakumatsu-Meiji transition. But the further back in time one’s research focus is situated, the rarer these documents become. There is a plethora of handwritten documents, written in historic cursive, but learning how to read them is a significant investment of time and resources beyond the means of most people who might otherwise have the inclination to learn.

It seems like a miracle, a dream come true, that an app could assist one in deciphering and parsing all of those wiggles and squiggles of historic cursive.

On 13 September, Tokyo-based printing company Toppan Inc. [VHM:  a firm so well known that even a China specialist like myself is familiar with it] announced the next stage in the development of their new kuzushiji software. Called Fuminoha Zemi, it is an AI-driven OCR (optical character recognition) service. Toppan has been developing its kuzushiji OCR technology with the help of a number of research organizations since 2015. It was based off the Bunsho Gazō System, a character recognition database developed by Professor Terasawa Kengo of Hakodate Mirai University that gathered examples of a given character– say, a hiragana に or a kanji 阿– across different digitized documents.

When a user takes a snapshot of a kuzushiji document, the Fuminoha system analyzes the characters and superimposes a typeset equivalent for ease of reading and further analysis. This can be exported into plain text, PDF, and HTML formats, for greater convenience of reading.

Of course, converting the kuzushiji cursive into typewritten forms doesn't mean that one can read the texts because they are composed in earlier and more formal stages and styles, but after having a typographically clear version of the document one can use dictionaries, grammars, and other research tools (including electronic and digital software to analyze and interpret it.

Fuminoha is not alone in the field of kuzushiji transcription relying on OCR and AI models:

…a competitor app, called Miwo, …has similar functionality and has been available for download since August 2021. Miwo was made by the Center for Open Data in the Humanities, part of the Japanese Research Organization of Information and Systems. It was trained on two recognition models, both of them derived from the National Institute of Japanese Literature’s Kuzushiji Dataset. 

More details about Fuminoha may be found here.  More information about Miwo is available here.

Finally, I was surprised that my own university has extensive resources doing research on kuzushiji, for which see this library website.


Selected readings


[Thanks to Mark Swofford]

1 Comment

  1. Philip Taylor said,

    September 20, 2022 @ 5:49 am

    Very useful information — my colleagues in the Hellenic Institute will liaise with the development team to see if some collaboration might be possible : we wish to use technology such as this to assist scholars in reading early Greek abbreviations, ligatures, monokondyliae, etc.


RSS feed for comments on this post