Publication Details
Vizuální segmentace elektronických dokumentů
document modelling, page segmentation, information extraction, document structure
Document segmentation deals with the discovery of the visual layout of documents and its representation. This knowledge allows to improve the results of existing document processing methods that are usually based on processing the text content only, such as document indexing and retrieval, classification, information extraction, etc. Currently, there exist several approaches to the document segmentation. However, they are usually limited to a particular type of documents or a particular application. In this paper, we propose a new method that solves some limiting features of the existing methods and furthermore, we show how this method can be used in the information extraction area.
@INPROCEEDINGS{FITPUB8268, author = "Radek Burget", title = "Vizu\'{a}ln\'{i} segmentace elektronick\'{y}ch dokument\r{u}", pages = "155--166", booktitle = "Znalosti 2007", year = 2007, location = "Ostrava, CZ", publisher = "V\v{S}B - Technical University of Ostrava", ISBN = "978-80248-1279-3", language = "czech", url = "https://www.fit.vut.cz/research/publication/8268" }