OCR Improvements for Images of Multi-page Historical Documents

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F49777513%3A23520%2F21%3A43962457" target="_blank" >RIV/49777513:23520/21:43962457 - isvavai.cz</a>

Výsledek na webu

<a href="https://link.springer.com/chapter/10.1007%2F978-3-030-87802-3_21" target="_blank" >https://link.springer.com/chapter/10.1007%2F978-3-030-87802-3_21</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/978-3-030-87802-3_21" target="_blank" >10.1007/978-3-030-87802-3_21</a>

Jazyk výsledku

angličtina

Název v původním jazyce

OCR Improvements for Images of Multi-page Historical Documents

Popis výsledku v původním jazyce

This work presents a pipeline for processing digitally scanned documents, reading their textual content, and storing it in a dataset for the purpose of information retrieval. The pipeline is able to handle images of various quality, whether they were obtained by a digital scanner or camera. The image can contain multiple pages in any layout, but an approximate upright orientation is assumed. The pipeline uses Faster R-CNN to detect individual pages. These are then processed by a deskew algorithm to correct the orientation, and finally read by the Tesseract OCR system that has been retrained on a large set of synthetic images and a small set of annotated real-world documents. By applying the pipeline, we were able to increase the word recall to 60.56% which is an absolute gain of 19.19% from the baseline solution that uses only Tesseract OCR. A demo of the proposed pipeline can be found at https://archivkgb.zcu.cz/.

Název v anglickém jazyce

OCR Improvements for Images of Multi-page Historical Documents

Popis výsledku anglicky

This work presents a pipeline for processing digitally scanned documents, reading their textual content, and storing it in a dataset for the purpose of information retrieval. The pipeline is able to handle images of various quality, whether they were obtained by a digital scanner or camera. The image can contain multiple pages in any layout, but an approximate upright orientation is assumed. The pipeline uses Faster R-CNN to detect individual pages. These are then processed by a deskew algorithm to correct the orientation, and finally read by the Tesseract OCR system that has been retrained on a large set of synthetic images and a small set of annotated real-world documents. By applying the pipeline, we were able to increase the word recall to 60.56% which is an absolute gain of 19.19% from the baseline solution that uses only Tesseract OCR. A demo of the proposed pipeline can be found at https://archivkgb.zcu.cz/.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

20205 - Automation and control systems

Projekt

<a href="/cs/project/DG20P02OVV018" target="_blank" >DG20P02OVV018: Digitální archiv dokumentů NKVD/KGB vztahujících se k Československu</a><br>

Návaznosti

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

Rok uplatnění

2021

Kód důvěrnosti údajů

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

Název statě ve sborníku

23rd International Conference, SPECOM 2021, St. Petersburg, Russia, September 27–30, 2021, Proceedings

ISBN

978-3-030-87801-6

ISSN

0302-9743

e-ISSN

1611-3349

Počet stran výsledku

12

Strana od-do

226-237

Název nakladatele

Springer

Místo vydání

Cham

Místo konání akce

St. Petersburg, Russia

Datum konání akce

27. 9. 2021

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—