Analyzing the Influence of Hyperparameters on the Efficiency of an OCR Model for Pre-Reform Handwritten Texts

Описание

Тип публикации: статья из журнала

Год издания: 2025

Идентификатор DOI: 10.1134/S0361768825700069

Аннотация: This paper considers the influence of hyperparameters on the efficiency of models for optical handwriting recognition of pre-reform texts by the example of 19th-century handwritten reports of Yenisei province governors. The comparative analysis of model configurations with different architectural components, including normalizationПоказать полностьюmodules, feature extraction blocks, and predictors, is carried out. Particular attention is paid to the role of input image resolution and hidden layer size in achieving the optimal tradeoff between prediction accuracy and computational cost. The results allow us to identify key parameters for the development of optical character recognition systems adapted to historical texts with nonstandard orthography and complex structure. Directions for further research include the evaluation of synthetic methods to expand training data and the analysis of alternative architectures, e.g., transformers.

Ссылки на полный текст

Издание

Журнал: Programming and Computer Software

Выпуск журнала: Т. 51, 3

Номера страниц: 173-180

ISSN журнала: 03617688

Место издания: Москва

Издатель: Pleiades Publishing, Ltd.

Персоны

  • Sherstnev P.A. (Artificial Intelligence Center, Siberian Federal University)
  • Kozhin K.D. (Artificial Intelligence Center, Siberian Federal University)
  • Pyataeva A.V. (Artificial Intelligence Center, Siberian Federal University)

Вхождение в базы данных