Image Rating System for Filtering Web Pages with Inappropriate Contents
نویسندگان
چکیده
We have developed a prototype system with image discrimination for the filtering and rating of web pages displaying inappropriate content. We used the SafetyOnline rating standard for the system. The rating standard defines five categories having five levels. The system rates web pages and classifies them into five levels of inappropriateness for each category according to the rating standard. The filtering process is different from the rating process. To enable the filtering of web pages, a user pre-selects a level of inappropriateness in each category in advance and the system filters out web pages whose the level of inappropriateness is higher than the level specified by the user. In the rating process, the system classifies web pages into five levels of inappropriateness for each category. The system performs both image and text classification to filter web page content. In this paper, we focused on image classification. We developed a method that enables the system to rate an image by integrating results of discriminating the image a t all levels based on the Bayesian theory. The system also rates and fiiters a certain web page by integrating the results of images attached to the web page. We examined the process of image discrimination for the filtering of inappropriate content and the process of image classification for the rating of that.
منابع مشابه
Use of Semantic Similarity and Web Usage Mining to Alleviate the Drawbacks of User-Based Collaborative Filtering Recommender Systems
One of the most famous methods for recommendation is user-based Collaborative Filtering (CF). This system compares active user’s items rating with historical rating records of other users to find similar users and recommending items which seems interesting to these similar users and have not been rated by the active user. As a way of computing recommendations, the ultimate goal of the user-ba...
متن کاملSection-Based Filtering and Its Application to SearchFilter
Demands for automatic filtering of restrictive contents on the WWW are growing continuously as the accessibility of the web is rapidly expanding. Most information filtering technologies aim at site-filtering or page-filtering, which are often inconvenient since other pages of the same site or other sections in the same page may still be appropriate for the reviewer. In this paper, a new framewo...
متن کاملAn Integrated Approach to Rating and Filtering Web Content
In this poster, we will illustrate an integrated approach to Web filtering, whose main features are flexible filtering policies taking into account both users’ characteristics and resource content, the specification of an ontology for the filtering domain, and the support for the main filtering strategies currently available. Our approach has been implemented in two prototypes, which address th...
متن کاملPrioritize the ordering of URL queue in Focused crawler
The enormous growth of the World Wide Web in recent years has made it necessary to perform resource discovery efficiently. For a crawler it is not an simple task to download the domain specific web pages. This unfocused approach often shows undesired results. Therefore, several new ideas have been proposed, among them a key technique is focused crawling which is able to crawl particular topical...
متن کاملPerformance Enhancement in Collaborative Filtering Technique by Removing Shilling Effect
Web page content mining is traditional searching of Web pages with the help of content, while Search results mining is a further search of pages found from a previous search. Web content mining has an approach that is shilling effect in which rating can be done and gives improper results. In this work we proposed an algorithm which gives appropriate values than shilling effects. Keywords, web m...
متن کامل