Skip to main content
News and events
The Canonizer demonstrates how well canonicity can be classified based on the text of a novel.
View a hundred years' worth of newspapers within a minute: the KB visualized its digitized newspapers.
Ot & Sien dataset
Data for the development of the automatic visual object recognition tools in children’s books.
Assisted keyword assignment using Annif
Annif can be used to make cataloging more efficient by suggesting authors and keywords.
Delpher demo: pandemics through time (Dutch)
Delpher demo was produced to inspire ideas on how to showcase digital heritage collections.
Historical newspapers OCR ground-truth
A dataset consisting of 2000 pages historical newspaper groundtruth, OCR and images.
Narralyzer finds and visualises characters in texts and the relationships between them.
The CHRONIC dataset consists of metadata for 313K classified newspaper images using computer vision.
The SIAMESET dataset consists of images and metadata of advertisements from two Dutch newspapers.
Tool to identify visual trends in advertisements in Dutch historical newspapers.
Tool for extracting topics, keywords and their co-occurence patterns from a Dutch corpus.
The Genre classifier predicts the genre of a Dutch newspaper article, using plain text as input.
The KBK-1M Dataset is a collection of 1,603,396 images and accompanying captions from 1922 – 1994
Simple API to access KB collections using Python.
ALTO Edit is a simple browser-based post correction tool for ALTO XML files.
The Scansion generator is a tool developed to detect meter in Dutch poetry.
DBNL ngram viewer
An ngram viewer counting terms and phrases in the Digital Library of Dutch Literature (DBNL).
Newspaper ngram viewer
The PoliticalMashup ngram viewer visualises the frequency of a phrase in Delpher newspapers.