Featured Articles

Apple announces its Apple Watch

Apple announces its Apple Watch

Apple has finally unveiled its eagerly awaited smartwatch and surprisingly it has dropped the "i" from the brand, calling it simply…

More...
Skylake 14nm announced

Skylake 14nm announced

Kirk B. Skaugen, Senior Vice President General Manager, PC Client Group has showcased Skylake, Intel’s second generation 14nm architecture.

More...
Apple officially announces 4.7-inch iPhone 6 and 5.5-inch iPhone 6 Plus

Apple officially announces 4.7-inch iPhone 6 and 5.5-inch iPhone 6 Plus

The day has finally come and it appears that most rumors were actually spot on as Apple has now officially unveiled…

More...
CEO: Intel on target for 40m tablets

CEO: Intel on target for 40m tablets

Intel CEO Brian Krzanich just kicked off the IDF 2014 keynote and it started with a phone avatar, some Katy Perry…

More...
Aerocool Dead Silence reviewed

Aerocool Dead Silence reviewed

Aerocool is well known for its gamer cases with aggressive styling. However, the Dead Silence chassis offers consumers a new choice,…

More...
Frontpage Slideshow | Copyright © 2006-2010 orks, a business unit of Nuevvo Webware Ltd.
Thursday, 20 January 2011 13:54

Boffins develop way of spotting flashers

Written by Nick Farell
y_exclamation

Hitech software to keep everything in your pants
Boffins fed up with people getting their kit off on chat sites have developed a new algorithm that will allow sites to nip the nudity in the bud.

Video chat services such as Chatroulette which randomly link the webcams of people who visit the site have been doing well but it has been plagued by people who want to show their genitals. Of course these are usually sad gits, but the cry has gone up “what about the children” who need to be protected from the sight of other people's genitals.

Now Xinyu Xing at the University of Colorado at Boulder and a few pals have come up with a "flasher detection" algorithm that spots the offenders, allowing them to be kicked out. Spotting flashers is harder than it might appear particularly when you have 20,000 users on the site at any time.

Another approach is to use existing algorithms designed to detect pornographic content. Exactly how these algorithms work isn't entirely clear, but they appear to look for skin content in images. But this does not work very well because videos are often poorly lit making it hard to distinguish skin from yellowy-white walls in the background.

Xing and his chums have come up with a new algorithm, called SafevChat. It analyses the images using several different criteria and then fuses the results before deciding whether the image is acceptable or not.

One of the tricks is to see that the skin is moving. It uses face, eye and nose detectors to distinguish facial from non-facial skin.Chatroulette began using it on its website earlier this month.

There will probably be those who feel that the lack of genitals on the site make it suffer a bit.


Last modified on Thursday, 20 January 2011 14:19

Nick Farell

E-mail: This e-mail address is being protected from spambots. You need JavaScript enabled to view it
blog comments powered by Disqus

 

Facebook activity

Latest Commented Articles

Recent Comments