Vestigia Scriptorium
Articles
Prepare Ground Truth, train HTR models and evaluate historical manuscript transcriptions. Practical guides for Transkribus, eScriptorium and Kraken.
Training HTR models for historical manuscript recognition
Handwritten Text Recognition (HTR) is a technology designed to automatically recognize handwritten text from digital document images. Unlike classic OCR, which has historically focused mainly on printed documents, HTR has to work with significantly greater variability of characters, words and entire scribal styles. The same letter can have many forms in a manuscript, and its appearance varies not only between individual scribes, but also according to the surrounding characters, the writing instrument used, the period of creation of the document or the physical condition of the original.
Read article HTR · 02Practical guide: how to train your first HTR model
Creating your own Handwritten Text Recognition (HTR) model does not require programming or machine learning knowledge. The basic principle is that we present the system with a sufficient number of images of lines of handwriting together with their correct transcription. This pair – the image of the document and its verified transcription – forms the so-called Ground Truth (GT), i.e. the reference data from which the model learns.
Read article HTR · 03Practical example: creating an HTR model for an archival volume
Let's imagine that we have a digitized 300-page land register. The book was created over several decades and contains entries by several scribes. The goal is not to create a diplomatic edition of the entire source, but to obtain a sufficiently high-quality automatic transcription in which it will be possible to search for names of persons, place names, farmstead numbers and other data.
Read article HTR · 04Preparing a test environment for working with HTR
Before we start creating our own Ground Truth and training the HTR model, it is advisable to prepare a separate testing environment in which we can safely experiment with digitized documents, models and individual tool settings.
Read article