by Johann Wieser
Abstract:
An important step in the analysis of printed documents is the segmentation and classification of blocks into categories such as photographs, titles, paragraphs, etc. This report presents an approach to enhance and combine two commonly used methods, a merging bottom up approach and a cutting top down approach, to segment pages of a newspaper. The planned procedure for an implementation of a layoutanalysis system as a preprocessing module for a commercial product is described.
Reference:
Layoutanalysis, Finding Text, Titles, and Photographs in Digital Images of Newspaper Pages (Johann Wieser), Technical report, PRIP, TU Wien, 1993.
Bibtex Entry:
@TechReport{TR018,
author = "Johann Wieser",
institution = "PRIP, TU Wien",
month = feb,
number = "PRIP-TR-018",
title = "Layoutanalysis, {F}inding {T}ext, {T}itles, and
{P}hotographs in {D}igital {I}mages of {N}ewspaper
{P}ages",
year = "1993",
url = "https://www.prip.tuwien.ac.at/pripfiles/trs/tr18.pdf",
abstract = "An important step in the analysis of printed
documents is the segmentation and classification of
blocks into categories such as photographs, titles,
paragraphs, etc. This report presents an approach to
enhance and combine two commonly used methods, a
merging bottom up approach and a cutting top down
approach, to segment pages of a newspaper. The
planned procedure for an implementation of a
layoutanalysis system as a preprocessing module for
a commercial product is described.",
}