By Topic

Characterizing objectionable image content (pornography and nude images) of specific Web segments: Chile as a case study

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$33 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

5 Author(s)
J. Ruiz-del-Solar ; Dept. of Electr. Eng., Chile Univ., Chile ; V. Castaneda ; R. Verschae ; R. Baeza-Yates
more authors

In this paper we perform a characterization of the objectionable image content (pornography and nude images) of the Chilean Web (.cl domain). This characterization is based on a novel objectionable image filtering system that detects porno and nude images. In an automated process we examine all .cl Web sites, and download a large number of the available images. Then, we analyze the images' contents and we detect human-skin blobs. Afterwards, special features are derived from these skin blobs (size, orientation, position, solidity, eccentricity, etc.). Finally, a statistical classifier is employed for classifying the images in three classes: normal, porno and nude. In addition to these, we characterize the three classes by their faces content. We present statistics of use to anyone concerned with the objectionable image content of the Web in Chile. We believe that the described methodology can be employed for carrying out similar studies in other segments of the Web, and also for the automatic discovering of new pornographic sites.

Published in:

Third Latin American Web Congress (LA-WEB'2005)

Date of Conference:

31 Oct.-2 Nov. 2005