Train Your Own OCR/HTR Models with Kraken, part 2

Learn about Kraken’s segmentation model and the process of training our own custom segmentation models for layout analysis tasks. Continue reading Train Your Own OCR/HTR Models with Kraken, part 2

Current approaches on Automatic Recognition of Ethiopic script

The script used by the Christian cultures of Ethiopia is ancient, developing from the Sabaean script in the first centuries … Continue reading Current approaches on Automatic Recognition of Ethiopic script

OCR of historical printing in Bengali using segmentation and recognition models trained in Kraken from an annotated dataset of Bengali texts published between 1860 and 1940. Continue reading eScriptorium: Digital Text Production for Urdu, Hindi, and Bengali Print, part 3

This is a guest post by Sarah Blake LaRose. As a scholar of biblical studies who is blind, I often … Continue reading Accessibility of Texts and Tools in Ancient Studies: Reframing the Discussion

In part 1 of this series, I provided a quick introduction to eScriptorium and the workflow associated with it. This … Continue reading eScriptorium: Digital Text Production for Urdu, Hindi, and Bengali Print, part 2

As promised previously, in this post I am leading you in a deep dive into a major digital archive I … Continue reading The Toyo Bunko Archive: a source of joy and torment

State-of-the-art OCR engines use trainable models to perform two consecutive tasks that produce machine-actionable transcriptions. They first segment the position … Continue reading eScriptorium: Digital Text Production for Urdu, Hindi, and Bengali Print, part 1

All scholars engaged in the study of the Japanese diaspora can profit from the treasure trove of resources on the … Continue reading The Japanese Diaspora in Digital Sources: The Hoji Shinbun Digital Collection

Most people involved in Japanese studies with access to a smartphone or tablet will be aware of the kuzushiji (cursive … Continue reading Practicing Reading Cursive Japanese with Miwo