Detail publikace

Web Page Element Classification Based on Visual Features

BURGET, R. BURGETOVÁ, I.

Originální název

Web Page Element Classification Based on Visual Features

Typ

článek ve sborníku mimo WoS a Scopus

Jazyk

angličtina

Originální abstrakt

When applying the traditional data mining methods to World Wide Web documents, the typical problem is that a normal web page contains a variety of information of different kinds in addition to its main content. This additional information such as navigation, advertisement or copyright notices negatively influences the results of the data mining methods as for example the content classification. In this paper, we present a method of interesting area detection in a web page. This method is inspired by an assumed human reader approach to this task. First, basic visual blocks are detected in the page and subsequently, the purpose of these blocks is guessed based on their visual appearance. We describe a page segmentation method used for the visual block detection, we propose a way of the block classification based on the visual features and finally, we provide an experimental evaluation of the method on real-world data.

Klíčová slova

page segmentation, preprocessing, classification, visual features, visual blocks

Autoři

BURGET, R.; BURGETOVÁ, I.

Rok RIV

2009

Vydáno

1. 4. 2009

Nakladatel

IEEE Computer Society

Místo

Dong Hoi

ISBN

978-0-7695-3580-7

Kniha

1st Asian Conference on Intelligent Information and Database Systems ACIIDS 2009

Strany od

67

Strany do

72

Strany počet

6

BibTex

@inproceedings{BUT33776,
  author="Radek {Burget} and Ivana {Burgetová}",
  title="Web Page Element Classification Based on Visual Features",
  booktitle="1st Asian Conference on Intelligent Information and Database Systems ACIIDS 2009",
  year="2009",
  pages="67--72",
  publisher="IEEE Computer Society",
  address="Dong Hoi",
  isbn="978-0-7695-3580-7"
}