Faculty of Information Technology, BUT

Publication Details

Automatic annotation of online articles based on visual feature classification

BURGET Radek and BURGETOVÁ Ivana. Automatic annotation of online articles based on visual feature classification. International Journal of Intelligent Information and Database System, vol. 5, no. 4, pp. 338-360. ISSN 1751-5858.
Czech title
Automatická anotace elektronicky publikovaných článků založená na klasifikaci vizuálních vlastností
Type
journal article
Language
english
Authors
Keywords
automatic annotation, online articles, page segmentation; document preprocessing, visual features, visual analysis, data mining, classification
Abstract
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.
Published
2011
Pages
338-360
Journal
International Journal of Intelligent Information and Database System, vol. 5, no. 4, ISSN 1751-5858
Publisher
Inderscience Publishers
BibTeX
@ARTICLE{FITPUB9692,
   author = "Radek Burget and Ivana Burgetov\'{a}",
   title = "Automatic annotation of online articles based on visual feature classification",
   pages = "338--360",
   journal = "International Journal of Intelligent Information and Database System",
   volume = 5,
   number = 4,
   year = 2011,
   ISSN = "1751-5858",
   language = "english",
   url = "https://www.fit.vut.cz/research/publication/9692"
}
Back to top