ROIS-DS Center for Open Data in the Humanities (CODH) is developing humanities research in the era of open science. Our work includes 'data-driven humanities' to analyze humanities resources, using state-of-the-art technology from computer science and statistics, and 'big data in the humanities' utilizing datasets created from humanities research for trans-disciplinary research. [Read more..]
>> List of News (in Japanese)
X (Twitter) - Timeline / Facebook / YouTube / Github
Pre-Modern Japanese Text, owned by National Institute of Japanese Literature, is released image and text data as open data. In addition, some text has description, transcription, and tagging data.
Cooking books in the period of Edo, included in Dataset of Pre-Modern Japanese Text were curated to create recipe datasets through the process of transcription, translation to modern Japanese, and structuring into the recipe format.
As a by-product of transcription on Dataset of Pre-Modern Japanese Text (PMJT), shapes and coordinates of old Japanese characters (Kuzushiji) were compiled to create another dataset for training to make machines and humans smarter.
Adapted from Kuzushiji Dataset, KMNIST dataset is a drop-in replacement for MNIST dataset. We provide three types of datasets, namely Kuzushiji-MNIST、Kuzushiji-49、Kuzushiji-Kanji, for different purposes.
The project aims at making research infrastructure for art history research by collecting facial expressions for style compartive study from Japanese Emaki (illustrated scroll), or potentially from work of art across the globe.
Introduce methodologies of machine learning and data science to Ukiyo-e research, and construct a new digital research infrastructure on Japanese culture.
Edo shopping guide is derived from "Edo Kaimono Hitori Annai" published in the Edo Period by cropping advertisement from books and adding the name of merchants with their business, address and the logo to create a visual database of merchants in and around the city of Edo.
Edo Sightseeing Guide is derived from tourism guides published in the Edo Period by cropping illustration from books and adding names, keywords and geographic information to create a visual tourism guide of Edo.
Edo Maps Beta is a project to construct geographic information infrastructure for the urban space of Edo City by extracting place names from Edo Kiriezu and econstructing information from old documents from the Edo Period.
Geoshape repository is a data repository for sharing the geographic shape of a geographic entity. It includes "Historical Municipal Boundaries Dataset Beta Version" about the historical change of municipal boundaries since 1920 and "Village Boundaries Dataset" of 2015.
Seal Script Dataset is a machine learning-friendly dataset of "Tensho" character images cropped from old dictionaries of characters from Japan and China to be used for the interpretation of seals.
Based on the results of digitization of magazines published in the early to mid-Meiji period (modern magazines), we release machine learning datasets for OCR and develop OCR software (Kindai-OCR).
I want to read the kuzushiji material! But I can't read them! "miwo" is an app that helps such people. Just take a picture of the material with the camera, press a button, and the AI will convert the kuzushiji into modern characters. Welcome to the world of kuzushiji documents.
Multi-character (one-page) Kuzushiji recognition service is developed using AI (machine learning). A service for IIIF (International Image Interoperability Framework) images is also released to transcribe kuzushiji images across the world.
Soan is a service that allows users to input modern Japanese text to generate and share kuzushiji images. The software and service enables anyone to digitally typeset old movable type (kokatsuji) from "Sagabon," which are one of the most beautiful books in the history of Japanese publishing.
Historical big data is a project for the seamless analysis of environment and society from the past to the present by structuring various records written by humans.
On November 9, 1867, the restoration of imperial rule symbolized the end of Edo Period. 150 years have passed since then, and now is the time to revive the information space of Edo, using open data about the 260 years of Edo period, and taking advantage of the state-of-the-art technologysuch as artificial intelligence (AI).
To create a vantage point for the various data about the Edo as a city or the Edo as a period, we create a data portal for structuring and integrating data on the historical Edo in response to the needs of present people.
The project aims at analyzing comprehensively the collection of "Bukan" books, which is the best seller through the 200 years of Edo period, and constructing core information platform about Edo period in terms of human and geospatial information about Daimyo (lords) and Shogunate government.
Read two images, overlay them, and emphasize the difference. A service useful for "spot the difference" on images with partial difference, such as the collation of images between different versions of woodblock-printed books.
We develop a platform for assigning identifiers to place names and sharing gazetteers.
By integrating geographic information science (GIS) and natural language processing (NLP), we develop a geo-tagging system for automatically transforming text to maps.
A research database on North China Railway Company by linking company's promotional stock photographs with its transportation network, and studying the activities of the company from the theme and location of photographs.
Memorygraph is a camera app that supports same-composition photography. We use now-and-then photography, before-and-after photography, fixed-point photography, and pilgrimage photography for cultural heritage, tourism, and recovery from disasters.
Digital humanities research project about creating digital archives of cultural heritage based on collaboration between informatics and humanities.
The usage of IIIF (International Image Interoperability Framework) for image delivery in large-scale image databases ranging from humanities to natural sciences, with a long-term goal to contributing to international communities.
Focusing on the concept of "curation," we build a next generation IIIF platform that is open and user-driven.
An open-source IIIF image viewer that takes advantage of IIIF Image API and IIIF Presentation API and implements our proposed specifications such as Curation API, Timeline API and Cursor API.
An IIIF viewer that can be embedded in a Web page derived from IIIF Curation Viewer.
A IIIF Search tool for searching curations created by IIIF Curation Viewer and publishing new curations by re-editing.
A management tool for curations created by IIIF Curation Viewer.
An editing tool for curations created by IIIF Curation Viewer.
A playing tool for curations created by IIIF Curation Viewer.
A whiteboard tool for organizing curations created by IIIF Curation Viewer.
An OCR text editing tool derived from IIIF Curation Viewer.
A flask web application for storing JSON documents; with some special functions for JSON-LD.
A flask web application that crawls Activity Streams for IIIF Canvases and offers a search API.
A flask web application for IIIF resource usage analytics with regard to IIIF Curations.
Scripts for installing IIIF Curation Platform on a Docker environment.
JavaScript-based visual differencing tool.
JavaScript-based visual differencing tool for an image sequence.
OCR system for modern Japanese documents trained on the modern magazine dataset.
