Back to search

Institutional Repository of Vilnius University

Dokumentų analizė ir atpažinimas /

Abstract

dc:description

Document digitization systems, which are dealing with various types of documents, use universal methods thus are not as effective as those which are designed to digitalise only one type. Simple, yet sufficient methods can be used when specific document characteristics are taken into consideration. In this thesis digitalization of invoices and receipts is analysed. Modified “XY-cut” algorithm is suggested for segmentation, classification is simplified by performing comparison of array representations of document layout binary trees, retrieved information is formatted and validated using pipelines. “JSON” is used to represent digitalization results. Suggested algorithms and methods are more effective and more reliable than those used in complex document digitization systems.

Degree

thesis:*
Grantor dc:publisher
Institutional Repository of Vilnius University
Year dc:date
2016

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Jurgelionis, Edvinas,
Contributors dc:contributor
  • Peldžius, Stasys

Rights

dc:rights
Statement dc:rights
  • info:eu-repo/semantics/openAccess
Language dc:language
lit

Identifiers

dc:identifier.*

Chain of custody

source
Harvested from
Vilnius University
Base URL
epublications.vu.lt/oai
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
related terms
citation

Jurgelionis, Edvinas,. Dokumentų analizė ir atpažinimas /. Institutional Repository of Vilnius University, 2016. https://repository.vu.lt/VU:ELABAETD23222279&prefLang=en_US