TRANSKRIBUS

Ефективност на генерични модели HTR за историческа кирилица и глаголица: Сравнение на средства

Performance of Generic HTR Models on Historical Cyrillic and Glagolitic: Comparison of Engines


Serbian Early Printed Books from Venice: Creating Models for Automatic Text Recognition Using Transkribus

Владимир Р. Поломац. Сръбски старопечатни книги от Венеция: cъздаване на модели за автоматично текстово разпознаване чрез Transkribus

  • Summary/Abstract

    The paper describes the process of creating a model for the automatic rec- ognition of Serbian Church Slavonic printed books from Venice (from Božidar and Vincenzo Vuković’s printery) by using the Transkribus software platform, based on the principles of artificial intelligence and machine learning. By using the example of Prayer Book (Euchologion) (1538–1540) from Božidar Vuković’s printery, it has been shown that a successful model for the automatic recognition of individual books (with around 5% of unrecognized characters) can also be trained on the material consisting of approximately 4000 words, and that the increased amount of training material (in our case around 38000 words) leads to the improvement of the model and reduced error rate (between 1–2% of unrecognized characters). The most notable result of the paper is manifested through the creation of a generic model for the automatic text recognition of Serbian Church Slavonic books from Božidar and Vincenzo Vuković’s printery. The ini- tial version of the generic model (called Dionisio 1.0. by the Božidar Vuković’s Italian pseudonym – Dionisio della Vecchia) is the first resource for the automatic recognition of the Serbian medieval Cyrillic script, publicly available to all users of the Transkribus software platform (see https://readcoop.eu/model/dionisio-1-0/).


Using Handwritten Text Recognition (HTR) Tools to Transcribe Historical Multilingual Lexica

Използване на приложения за разпознаване на ръкописни текстове (HTR) при транскрибиране на многоезични исторически лексикони

  • Summary/Abstract
    The paper discusses some results obtained as part of an ongoing project at the Slavic Institute of Heidelberg University to produce automatic transcriptions of an early 18th century trilingual printed dictionary (Fedor Polikarpov’s Leksikon trejazyčnyj) and, on a preliminary basis, of a 17th century trilingual manuscript (Epifanij Slavineckii’s working copy of his Greek–Slavic–Latin dictionary) using the handwritten text recognition (HTR) platforms Transkribus and eScriptorium. It is argued that there are considerable advantages to employing such tools in terms of the simplification and acceleration of work on multilingual edition projects. Moreover, a comparison of our experience working with Transkribus and eScriptorium is given, along with an overview of the practical benefits and challenges of working with each of these platforms.

Using Handwritten Text Recognition on bilingual Evenki-Russian manuscripts of Konstantin Rychkov

Използване на инструменти за разпознаване на ръкописни текстове (HTR) върху двуезични евенкско-руски ръкописи от колекцията на Константин Ричков

  • Summary/Abstract

    We report on applying Handwritten Text Recognition (HTR) to manuscripts from the archive of Konstantin Rychkov preserved at IOM RAS, St. Petersburg, within the INEL project. Folklore texts in Evenki (Tungusic) were collected in Western Siberia in 1910s. We used services provided by the Transkribus platform. The necessary step of Layout Analysis proved to be time-consuming due to the organization of the parallel Evenki- Russian text on the page without following a strict separation line. HTR models have been trained successively on different amounts of data up to 521 pages. The best Character Error Rate attained on validation data for the largest dataset is 4.50% for models trained on all characters. The distribution of errors is non-uniform: most errors are due to just a few problematic issues, especially diacritics such as the accent marking stress. It is written high above the line and frequently cut off from the line images at the preprocessing stage. After excluding the stress mark from training data and recognition, the lowest CER dropped to 2.90%. We compared two recognition engines, HTR+ and PyLaia. The HTR+ model trained without stress marks made less errors in letters, while PyLaia performed better with respect to diacritics.


Recognizing Handwritten Text in Slavic Manuscripts: a Neural-Network Approach Using Transkribus


Subscribe to TRANSKRIBUS