Improving Handwritten Cyrillic OCR by Font-based Synthetic Text Generator

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F49777513%3A23520%2F23%3A43969586" target="_blank" >RIV/49777513:23520/23:43969586 - isvavai.cz</a>

Výsledek na webu

<a href="https://link.springer.com/chapter/10.1007/978-3-031-50320-7_8" target="_blank" >https://link.springer.com/chapter/10.1007/978-3-031-50320-7_8</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/978-3-031-50320-7_8" target="_blank" >10.1007/978-3-031-50320-7_8</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Improving Handwritten Cyrillic OCR by Font-based Synthetic Text Generator

Popis výsledku v původním jazyce

In this paper, we propose a straight-forward and effective Font-based Synthetic Text Generator (FbSTG) to alleviate the need for annotated data required for not just Cyrillic handwritten text recognition. Unlike standard GAN-based methods, the FbSTG does not have to be trained to learn new characters and styles; all it needs is the fonts, the text, and sampled page backgrounds. In order to show the benefits of the newly proposed method, we train and test two different OCR systems (Tesseract, and TrOCR) on the Handwritten Kazakh and Russian dataset (HKR) both with and without synthetic data. Besides, we evaluate both systems&apos; performance on a private NKVD dataset containing historical documents from Ukraine with a high amount of out-of-vocabulary (OoV) words representing an extremely challenging task for current state-of-the-art methods. We decreased the CER and WER significantly by adding the synthetic data with the TrOCR-Base-384 model on both datasets. More precisely, we reduced the relative error in terms of CER / WER on (i) HKR-Test1 with OoV samples by around 20% / 10%, and (ii) NKVD dataset by 24% CER and 8% WER. The FbSTG code is available at: https://github.com/mhlzcu/doc_gen.

Název v anglickém jazyce

Improving Handwritten Cyrillic OCR by Font-based Synthetic Text Generator

Popis výsledku anglicky

In this paper, we propose a straight-forward and effective Font-based Synthetic Text Generator (FbSTG) to alleviate the need for annotated data required for not just Cyrillic handwritten text recognition. Unlike standard GAN-based methods, the FbSTG does not have to be trained to learn new characters and styles; all it needs is the fonts, the text, and sampled page backgrounds. In order to show the benefits of the newly proposed method, we train and test two different OCR systems (Tesseract, and TrOCR) on the Handwritten Kazakh and Russian dataset (HKR) both with and without synthetic data. Besides, we evaluate both systems&apos; performance on a private NKVD dataset containing historical documents from Ukraine with a high amount of out-of-vocabulary (OoV) words representing an extremely challenging task for current state-of-the-art methods. We decreased the CER and WER significantly by adding the synthetic data with the TrOCR-Base-384 model on both datasets. More precisely, we reduced the relative error in terms of CER / WER on (i) HKR-Test1 with OoV samples by around 20% / 10%, and (ii) NKVD dataset by 24% CER and 8% WER. The FbSTG code is available at: https://github.com/mhlzcu/doc_gen.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

20205 - Automation and control systems

Projekt

Výsledek vznikl pri realizaci vícero projektů. Více informací v záložce Projekty.

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2023

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

Lecture Notes in Computer Science

ISBN

978-3-031-50319-1

ISSN

0302-9743

e-ISSN

1611-3349

Počet stran výsledku

14

Strana od-do

102-115

Název nakladatele

Springer

Místo vydání

Cham

Místo konání akce

Prague, Czech Republic

Datum konání akce

3. 9. 2023

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—