Safe V chat

A system for obscene content detection in online video chat services

Yu Li Liang, Xinyu Xing, Hanqiang Cheng, Jianxun Dang, Sui Huang, Richard Han, Xue Liu, Qin Lv, Shivakant Mishra

Research output: Contribution to journalArticle

Abstract

Online video chat services such as Chatroulette, Omegle, and vChatter that randomly match pairs of users in video chat sessions are quickly becoming very popular, with over a million users per month in the case of Chatroulette. A key problem encountered in such systems is the presence of flashers and obscene content. This problem is especially acute given the presence of underage minors in such systems. This article presents SafeVchat, a novel solution to the problem of flasher detection that employs an array of image detection algorithms. A key contribution of the article concerns how the results of the individual detectors are fused together into an overall decision classifying a user as misbehaving or not, based on Dempster- Shafer theory. The article introduces a novel, motion-based skin detection method that achieves significantly higher recall and better precision. The proposed methods have been evaluated over real-world data and image traces obtained from Chatroulette.com. SafeVchat has been deployed in Chatroulette. A combination of SafeVchat with human moderation has resulted in banning as many as 50,000 inappropriate users per day on Chatoulette. Furthermore, offensive content on Chatoulette has dropped significantly from 33.08% (before SafeVchat installation) to 3.49% (after SafeVchat installation).

Original languageEnglish (US)
Article number2499927
JournalACM Transactions on Internet Technology
Volume12
Issue number4
DOIs
StatePublished - Jan 1 2013

Fingerprint

Skin
Detectors

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications

Cite this

Liang, Yu Li ; Xing, Xinyu ; Cheng, Hanqiang ; Dang, Jianxun ; Huang, Sui ; Han, Richard ; Liu, Xue ; Lv, Qin ; Mishra, Shivakant. / Safe V chat : A system for obscene content detection in online video chat services. In: ACM Transactions on Internet Technology. 2013 ; Vol. 12, No. 4.
@article{225c8b076a4f480ab49e8df452c0531b,
title = "Safe V chat: A system for obscene content detection in online video chat services",
abstract = "Online video chat services such as Chatroulette, Omegle, and vChatter that randomly match pairs of users in video chat sessions are quickly becoming very popular, with over a million users per month in the case of Chatroulette. A key problem encountered in such systems is the presence of flashers and obscene content. This problem is especially acute given the presence of underage minors in such systems. This article presents SafeVchat, a novel solution to the problem of flasher detection that employs an array of image detection algorithms. A key contribution of the article concerns how the results of the individual detectors are fused together into an overall decision classifying a user as misbehaving or not, based on Dempster- Shafer theory. The article introduces a novel, motion-based skin detection method that achieves significantly higher recall and better precision. The proposed methods have been evaluated over real-world data and image traces obtained from Chatroulette.com. SafeVchat has been deployed in Chatroulette. A combination of SafeVchat with human moderation has resulted in banning as many as 50,000 inappropriate users per day on Chatoulette. Furthermore, offensive content on Chatoulette has dropped significantly from 33.08{\%} (before SafeVchat installation) to 3.49{\%} (after SafeVchat installation).",
author = "Liang, {Yu Li} and Xinyu Xing and Hanqiang Cheng and Jianxun Dang and Sui Huang and Richard Han and Xue Liu and Qin Lv and Shivakant Mishra",
year = "2013",
month = "1",
day = "1",
doi = "10.1145/2499926.2499927",
language = "English (US)",
volume = "12",
journal = "ACM Transactions on Internet Technology",
issn = "1533-5399",
publisher = "Association for Computing Machinery (ACM)",
number = "4",

}

Safe V chat : A system for obscene content detection in online video chat services. / Liang, Yu Li; Xing, Xinyu; Cheng, Hanqiang; Dang, Jianxun; Huang, Sui; Han, Richard; Liu, Xue; Lv, Qin; Mishra, Shivakant.

In: ACM Transactions on Internet Technology, Vol. 12, No. 4, 2499927, 01.01.2013.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Safe V chat

T2 - A system for obscene content detection in online video chat services

AU - Liang, Yu Li

AU - Xing, Xinyu

AU - Cheng, Hanqiang

AU - Dang, Jianxun

AU - Huang, Sui

AU - Han, Richard

AU - Liu, Xue

AU - Lv, Qin

AU - Mishra, Shivakant

PY - 2013/1/1

Y1 - 2013/1/1

N2 - Online video chat services such as Chatroulette, Omegle, and vChatter that randomly match pairs of users in video chat sessions are quickly becoming very popular, with over a million users per month in the case of Chatroulette. A key problem encountered in such systems is the presence of flashers and obscene content. This problem is especially acute given the presence of underage minors in such systems. This article presents SafeVchat, a novel solution to the problem of flasher detection that employs an array of image detection algorithms. A key contribution of the article concerns how the results of the individual detectors are fused together into an overall decision classifying a user as misbehaving or not, based on Dempster- Shafer theory. The article introduces a novel, motion-based skin detection method that achieves significantly higher recall and better precision. The proposed methods have been evaluated over real-world data and image traces obtained from Chatroulette.com. SafeVchat has been deployed in Chatroulette. A combination of SafeVchat with human moderation has resulted in banning as many as 50,000 inappropriate users per day on Chatoulette. Furthermore, offensive content on Chatoulette has dropped significantly from 33.08% (before SafeVchat installation) to 3.49% (after SafeVchat installation).

AB - Online video chat services such as Chatroulette, Omegle, and vChatter that randomly match pairs of users in video chat sessions are quickly becoming very popular, with over a million users per month in the case of Chatroulette. A key problem encountered in such systems is the presence of flashers and obscene content. This problem is especially acute given the presence of underage minors in such systems. This article presents SafeVchat, a novel solution to the problem of flasher detection that employs an array of image detection algorithms. A key contribution of the article concerns how the results of the individual detectors are fused together into an overall decision classifying a user as misbehaving or not, based on Dempster- Shafer theory. The article introduces a novel, motion-based skin detection method that achieves significantly higher recall and better precision. The proposed methods have been evaluated over real-world data and image traces obtained from Chatroulette.com. SafeVchat has been deployed in Chatroulette. A combination of SafeVchat with human moderation has resulted in banning as many as 50,000 inappropriate users per day on Chatoulette. Furthermore, offensive content on Chatoulette has dropped significantly from 33.08% (before SafeVchat installation) to 3.49% (after SafeVchat installation).

UR - http://www.scopus.com/inward/record.url?scp=84896962606&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84896962606&partnerID=8YFLogxK

U2 - 10.1145/2499926.2499927

DO - 10.1145/2499926.2499927

M3 - Article

VL - 12

JO - ACM Transactions on Internet Technology

JF - ACM Transactions on Internet Technology

SN - 1533-5399

IS - 4

M1 - 2499927

ER -