Detection of Porn on World Wide Web in order to Prevent Abuse against Kids in India

 Scrapbooking

 4 views
of 3
All materials on our website are shared by users. If you have any questions about copyright issues, please report us to resolve them. We are always happy to assist you.
Description
Detection of Porn on World Wide Web in order to Prevent Abuse against Kids in India
Share
Tags
Transcript
  IJRIT International Journal of Research in Information Technology, Volume 1, Issue 1, January 2013, Pg. 1-3 1Dr. P. Tsang et al , IJRIT International Journal of International Journal of International Journal of International Journal of Research in Information Technology (IJRITResearch in Information Technology (IJRITResearch in Information Technology (IJRITResearch in Information Technology (IJRIT))))www.ijrit.comwww.ijrit.comwww.ijrit.comwww.ijrit.com  ISSN 2001-5569   Detection of Porn on World Wide Web in order toPrevent Abuse against Kids in India Dr. Patrick Tsang 1 , Mohammad Zainuddin 2   1 School of Computer ScienceLinnaeus University (LNU), Sweden   drptsang@yahoo.se  2 Research Scholar, SecunderabadHyderabad, Andhra Pradesh, INDIA Zain.xenon@gmail.com  Abstract This paper explores the sensitive issue of pornography and discusses an automated system for detection of nude contentin the video which is browsed on internet. Pornography issue is neglected in our country (India) due to its sensitivetopic and due to this problem it has now become the reason for crimes against children in huge numbers. Hence, todecrease the impact of porn among kids, this research paper carries out discussion on a computer system which has theability to detect adult content in a video browsed on net and prevent child abuse to some extent.  Keywords: Pornographic detection, Judgment Criteria, Audio Based Classification. 1. Introduction The word “porn” comes from a Greek word called “pornographos” which means explicit portrayal of sexual activities. Pornography may use a variety of media, including images, videos, books, magazines,animations and even video games. The minds of immature children are mainly corrupted by these adultcontents on internet which are available free on pornographic websites. Hence, to prevent children fromthese adult contents existing methods are not sufficient.In India children account for a forty two percent of the country’s population, have long been the victims of some of the most brutal sexual crimes. This issue is always on top most priority for law enforcementagencies since the beginning of digital trafficking of child pornography [1] [2].Therefore, a much more brilliant system is required to detect porn on internet with abilities to prevent kidsfrom viewing explicit sexual contents on World Wide Web. 2. Importance of Research Major objective of this research is to develop new methods of video interrogation to detect as pornographic.New method includes skin detection, audio detection and pixel detection in order to judge whether a videois pornographic or not.Accuracy of detection of video is the primary objective of this research in order to prevent India fromcommitting crimes against children.  IJRIT International Journal of Research in Information Technology, Volume 1, Issue 1, January 2013, Pg. 1-3 2Dr. P. Tsang et al , IJRIT 3. Review of Existing Methods Many researchers have contributed by developing different algorithms to detect adult images and videos.Most of the work related to pornography detection [3] is based on images. Forsyth et al. [4] proposed abody plan that detected different parts of the body by their geometric constraints for detecting the nakedpeople. Their system marks skin - like pixels using combined color and texture properties. These skinregions are then fed to a grouper used for grouping human figure using geometric constrains. Lv and Yangapplied change in optical flow volume to extract important key frames and later used skin color detectionmethod to detect objectionable scene in video. Porn video is detected based on motion features usingHMM. Feature vectors are extracted by calculating the direction and magnitude after obtaining motionvectors from compressed MPEG video. These motion vectors are fed to Hidden Markov Model forclassification of 6 actions. Skin color is one of important cues for pornographic video’s detection.Hence, Existing methods are not sufficient to block adult content from reaching children. 4. Proposed System Our proposed system consists of three filtering stages. They are:I.   Keywords based FilteringII.   Skin Pixel FilteringIII.   Audio based FilteringFig. 1 Pornographic Video Detection System 4.1 Keywords based Filtering As we know, there are many keywords through which a person can search and get adult material frominternet. In keywords based filtering, we are using these keywords to detect pornographic content byfiltering out the keywords which can take a person to a porn media or website.Some of the keywords which resemble a porn content are sex, porn, intercourse etc. There are many suchkeywords which we are filtering in our proposed system in detecting adult explicit content in a video.  IJRIT International Journal of Research in Information Technology, Volume 1, Issue 1, January 2013, Pg. 1-3 3Dr. P. Tsang et al , IJRIT 4.2 Skin Pixel Filtering Based upon the pixels of the human skin in a video, we can detect whether a video is pornographic or not.In this filtering, we are carrying out a matching technique to match the private parts of human bodies sothat detection of nudity is easier. For this purpose, we are considering pixels below the abdomen to match 4.3 Audio based Filtering The last and final level of filtering is audio filtering. In this phase, we are extracting audio from the videoand looking for the audio patches whether it contains audio which resemble a sexual activity or not. Thepatches which show us the inclusion of adult content can be Groans, Moans, Screams, etc. 5. Conclusion Proposed Porn Detection System is more suitable for porn detection in modern internet world and moreaccurate than previous systems. Hence, to overcome child abuse in India and other countries, computationalautomatic systems should be entertained to stop crimes related to porn. References [1] Burgess, Ann Wolbert, and Marieanne Lindeqvist Clark, eds. Child pornography and sex rings .Lexington: Lexington Books, 1984.   [2] Quayle, Ethel. Child pornography: An internet crime . Routledge, 2003.   [3] Agbinya, Johnson I., et al. "Automatic online porn detection and tracking." Proc. 12th IEEE Int. Conf.on Telecommunications . 2007.   [4] Quinn, James F., and Craig J. Forsyth. “Describing sexual behavior in the era of the Internet: Atypology for empirical research.”  Deviant Behavior  26.3 (2005): 191-207.
Related Search
We Need Your Support
Thank you for visiting our website and your interest in our free products and services. We are nonprofit website to share and download documents. To the running of this website, we need your help to support us.

Thanks to everyone for your continued support.

No, Thanks