Content-based indexing of visual information in the web pages Online publication date: Fri, 31-Jul-2015
by Ali Benafia; Ramdane Maamri; Zaidi Sahnoun; Sara Benafia
International Journal of Reasoning-based Intelligent Systems (IJRIS), Vol. 7, No. 1/2, 2015
Abstract: As the World Wide Web has grown, the methods for indexing have changed considerably. It is in this context that we present in this paper a novel approach to the indexing of web pages. In general, a web page contains multiple objects at once; some objects have a specific stain for static and dynamic page design. Others are more important and relevant in terms of information as regards the page content. In order to identify this informative part, we developed a novel approach for cleaning superfluous objects and then have kept the image and textual part in the web page. Once the images and texts are identified in page, we have established a link between the text and the visual characteristics of image to build a bridge over the semantic gap. To do this, we then explore the possibilities of integration of visual and textual features. The proposed approach is tested on a large corpus and the results are compared with the human expert indexing.
Online publication date: Fri, 31-Jul-2015
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Reasoning-based Intelligent Systems (IJRIS):
Login with your Inderscience username and password:
Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.
If you still need assistance, please email firstname.lastname@example.org