Featured Articles

AMD Never Settle Forever bundle hits 200-series cards

AMD Never Settle Forever bundle hits 200-series cards

AMD’s Never Settle bundles have been around for a while and the community response has been extremely positive. When AMD launched…

More...
AMD shipping Beema APUs

AMD shipping Beema APUs

According to Lisa Su, SVP & GM, Global Business Units at AMD, Beema notebook parts have started shipping to manufacturers last…

More...
IHS teardown reveals Galaxy S5 BOM

IHS teardown reveals Galaxy S5 BOM

Research firm IHS got hold of Samsung’s new flagship smartphone and took it apart to the last bolt to figure out…

More...
Galaxy S5, HTC One M8 available selling well

Galaxy S5, HTC One M8 available selling well

Samsung’s Galaxy S5 has finally gone on sale and it can be yours for €699, which is quite a lot of…

More...
KFA2 GTX 780 Ti Hall Of Fame reviewed

KFA2 GTX 780 Ti Hall Of Fame reviewed

KFA2 gained a lot of overclocking experience with the GTX 780 Hall of Fame (HOF), which we had a chance to…

More...
Frontpage Slideshow | Copyright © 2006-2010 orks, a business unit of Nuevvo Webware Ltd.
Monday, 19 March 2007 20:22

Fraunhofer Institut detects faces

Written by Sanjin Rados

Image

CEBIT 2007: Are Cebit visitors happy ?

 

Fraunhofer Institute is very well known name. They developed MP3 format (short from MPEG1 Audio Layer 3) and they are doing continuously research in many fields. Fraunhofer booth at Cebit has some interesting technologies.


One of them is Real Time Face Detection software that can be used for rapid detection of arbitrary amount of frontal faces within a still images or a video stream. The algorithm is capable of working with monochrome and colour images of arbitrary size. It has C++ interface and is also available as an SDK for Windows and Linux platform for both 32 and 64 bit. 

 

 Image

 It seems that visitors are happy today

 

Multiple faces can be found simultaneously, and we saw it in work. The software can detect if you are  Angry, Happy, Sad, Surprised, Male or Female, with open or closed Mouth. The cutting-edge system is based on high-performing features and statistical classificator trained with over 10,000 sample images.

 

Image

 

We learned that there is a possibility to make an interface in java and use it like Facefinder in mobile phones. That way the phone should be able to recognise owners face and there will be no need for a PIN. 

There are many fields for implementing the face recognition technology, from security and biometric face recognition, teleconference and multimedia systems, to man-machine interfaces.

 

Image

 

On the boot we also saw one small ultracompact multiformat CMOS HDTV camera. It is all-in-one camera with a 2/3 inch single chip CMOS sensor. It can capture 1080i/p HD video and has sensitivity of f5.6 at 2000lux with signal/noise ratio >62db. Quantisation processing is 16 bit and thanks to small dimensions and weight of only 200 gramms it is very usable. Racing cars will have one of these cameras. All in all it looks cool. 

 

Image

 

Image 

Last modified on Monday, 19 March 2007 23:30

Sanjin Rados

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

To be able to post comments please log-in with Disqus

 

Facebook activity

Latest Commented Articles

Recent Comments