Institutional Repository of Vilnius University
Lentelių atpažinimas spausdintuose dokumentuose /
Abstract
dc:descriptionTable Recognition in the Printed Documents There are many different table templates and it is impossible to recognize them all with a single tool. Although the tool would be able to detect tables, it would do unreliably. Tools that are designed to recognize the structure of a single table work much more efficiently and make much fewer mistakes. In this work, one table structure is chosen. The selected structure does not have all edges - it has only horizontal lines. Algorithm was developed with the “OpenCV” tool that did not require a lot of data to train. The cells of the discovered table are given to the optical character recognition tool “Tesseract”, which converts image of the cell into text. The recognized text from the table is placed in an “Excel” file.
Degree
thesis:*- Grantor dc:publisher
- Institutional Repository of Vilnius University
- Year dc:date
- 2020
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Ščerba, Elžbieta,
- Contributors dc:contributor
-
- Valaitis, Vytautas
Rights
dc:rights- Statement dc:rights
-
- info:eu-repo/semantics/openAccess
- Language dc:language
- lit
Identifiers
dc:identifier.*- Repository record dc:identifier
- https://repository.vu.lt/VU:ELABAETD81705047&prefLang=en_US