skip to Main Content

Resources for Japan Scholars: Kuronet Character Recognition Platform

Kuronet Character recognition Platform

kuronet datasetCreated by researchers at Japan’s Centre for Open Data in the Humanities (CODH), KuroNet helps users to decipher historical texts written in classical Japanese script. It uses artificial intelligence to machine-read images of historical texts uploaded by users and convert them into contemporary Japanese. The model was trained on an extensive dataset compiled by CODH which contains over 4000 character classes and a million character images from 44 books printed in the Edo period (around the 17th to 19th centuries).

Related Links


For enquiries or to suggest a resource, please contact the Japanese Studies department via

Main image: Sourced from Centre for Open Data in the Humanities’ Kuzushiji Dataset (Source)

Back To Top