A Novel Web Page Filtering System by Combining Texts and Images

Abstract

Abstract

Mining browsing behaviors for objectionable content filtering

“…Motion information has been associated with image features in detecting pornographic video content (Jansohn et al., ). Hybrid text and image analysis has also been used to train the classifier for pornography filtering (Chen et al., ; Polpinij et al., ). In addition to content features, analysis of linking structures through hyperlinks has been used to filter Internet pornography (Chau & Chen, ; Ho & Watters, ).…”

“…Controlling access to the Internet through filtering has been recognized as a mandatory response to address the issue of content inappropriate for children. Traditional filtering techniques regard objectionable access identification as a categorization problem through content analysis (Caulkins, Ding, Duncan, Krishnan, & Nyberg, 2006;Chau & Chen, 2008;Chen, Wu, Zhu, & Hu, 2006;Deselaers, Pimenidis, & Hey, 2008;Eickhoff et al, 2010Eickhoff et al, , 2011Hammami, Chahir, & Chen, 2006;Ho & Watters, 2004;Jansohn, Ulges, & Breuel, 2009;Lee, Luh, & Yang, 2008;Lee, Hui, & Fong, 2002, 2003, 2005Lin, Jan, Lin, & Lai, 2006;Polpinij, Sibunruang, Paungpronpitag, Chamchong, & Chotthanom, 2008;Wu, Zuo, Hu, Zhu, & Li, 2008;Zhang, Qin, & Yan, 2006;Zhu, Wu, Cheng, & Wu, 2004;Zuo, Hu, & Wu, 2010), that is, crawling the content of URLs and analyzing the texts, images, video clips, and films by machine learning to distinguish normal web pages from objectionable ones. Unlike the case in most previous studies, which have focused on the content of web pages for objectionable access filtering, we look for insights into users' web surfing behaviors in clickthrough data.…”

“…Approach Targets Resnick & Miller, 1996 Self-rating labeling HTML metadata Caulkins et al, 2006;Lee et al, 2002Lee et al, , 2003Lee et al, , 2005Lin et al, 2006 Intelligent content analysis Texts Texts and titles Zhang et al, 2006 Texts and URLs Chen et al, 2006;Polpinij et al, 2008 Text and images Chau & Chen, 2008;Ho & Watters, 2004 Texts and hyperlinks Hammami et al, 2006;Eickhoff et al, 2010Eickhoff et al, , 2011 Texts, images, and hyperlinks Deselaers et al, 2008;Wu et al, 2008;Zhu et al, 2004;Zuo et al, 2010Images Jansohn et al, 2009 Images and videos Lee & Chen, 2011a, 2011bSzummer & Craswell, 2008 Behavioral mining Query logs content, such as texts, images, videos, and hyperlinks, to learn the classifiers for objectionable-content categorization. In recent years, a behavioral mining approach has been proposed to explore users' search intents by query logs for objectionable-accesses filtering.…”

Web Content Filtration Using Different Web Mining Techniques in Educational System: An Overview

“…In this method divide and concur, navie bayes, knearest neighbour algorithms are used. [5] In this paper Hui Li,Fei cai and Zhifang Liao have done work on a filter which is used to block unwanted messages and allow user to have direct control on the message posted on the wall of online social networking sites. Inference algorithm is used to infer the new information from the filtering rules to increase the efficiency of the filtering process.…”

Mining search intents for collaborative cyberporn filtering

“…They attempt to analyze texts, images, video clips, and films on web pages to understand the context in which the discriminative features appear and make a classification decision. Several numerical algorithms, including neural networks (Lee et al, 2002, 2003, 2005), statistical text analysis (Caulkins et al, 2006; Lee & Luh, 2008; Lee, Luh, & Yang, 2008), pattern‐recognition techniques (Deselaers, Pimenidis, & Hey, 2008; Lee, Kuo, Chung, & Chen, 2007), and hybrid feature analysis (Chen, Wu, Zhu, & Hu, 2006; Hammami, Chahir, & Chen, 2006; Polpinij, Sibunruang, Paungpronpitag, Chamchong, & Chotthanom, 2008) have been used to train the classifier for pornography filtering. Features from skin pixels were usually adopted for pornographic‐image recognition (Wu, Zuo, Hu, Zhu, & Li, 2008; Zhu, Wu, Cheng, & Wu, 2004; Zuo, Hu, & Wu, 2010).…”