Chances are, you’ve seen at least one or two TV shows in which the police examine news footage shot at several different crime scenes, and recognize the same person’s face showing up repeatedly in the crowds of onlookers ... the ol’ “criminal returning to the scenes of their crimes” scenario. Realistically, it’s pretty hard to believe that one person could look through all that footage, and remember all those faces. It turns out that a computer could do it, however, as scientists at Indiana’s University of Notre Dame have illustrated with their “Questionable Observer Detector," or QuOD.
Japan’s Hitachi Kokusai Electric has developed a surveillance system that can automatically detect a face in either a provided photo or video footage, then search for that same face in other video provided by networked cameras. While such facial recognition systems have been seen before, this one is able to compare the target face against others at an astounding rate of 36 million faces per second.
Some day in the not-too-distant future, you may be on a service like Chatroulette, and suddenly find yourself matched up with a person who looks exactly like Angelina Jolie. Well, chances are it won’t really be her. Instead, it will likely be someone using the descendant of a system put together by Arturo Castro. Using a combination of existing software, the Barcelona digital artist has demonstrated how a variety of famous faces can be mapped onto his own, moving with it in real time. While Castro’s system isn’t likely to fool anyone – in its present version – it’s an unsettling indication of what could be possible with just a little more finessing.
When studying wild animals such as gorillas and chimpanzees, it's not uncommon to use photo or video traps - unmanned cameras that are triggered to capture images when creatures pass in front of them. Scientists can then retrieve the cameras and review the footage, to get an estimate of the numbers of a certain species within a given area, and to see what those animals have been up to. One of the problems with this approach, however, is that it's often hard to tell one animal from another - are you looking at several shots of several different apes, or is it the same individual every time? German scientists are developing wild primate-devoted facial recognition software, in order to answer such questions.
Binghamton University computer scientist Lijun Yin thinks that using a computer should be a comfortable and intuitive experience, like talking to a friend. As anyone who has ever yelled “Why did you go and do that
?” at their PC or Mac will know, however, using a computer is currently sometimes more like talking to an overly-literal government bureaucrat who just doesn’t get you
. Thanks to Yin’s work with things like emotion recognition, however, that might be on its way to becoming a thing of the past.
technology is now pretty common in digital cameras, but has also found its way into things like taps
, door locks
and even ice cream machines
. Recently, researchers from the University of Manchester developed software that allows mobile phones to detect faces too. Unlike some devices that simply identify faces, however, phones equipped with this software will be able to continuously track faces in real time.
capabilities of modern cameras means photographers no longer have to go through the boring task of jotting down the location of a picture on the back of photos. Unfortunately, interference when taking pictures indoors or even outside amongst a forest of skyscrapers can render the geotagging feature inoperative. The latest model to join Casio’s EXILIM
Hi-Zoom lineup, the EX-H20G, overcomes this problem by using a Hybrid GPS system that combines GPS with a three-way accelerometer and direction sensor to track a user’s last known satellite-acquired position against map data stored in the camera’s memory. It then checks every 10 minutes until it can reconnect to a satellite signal.
has announced the new SELPHY CP800 Compact Photo Printer, which will replace the SELPHY CP780. The CP800 features a tilt LCD screen, built-in voice guidance, and dye sublimation technology, which produces smooth and glossy prints that are reportedly similar in quality and look to traditional lab photos. Prints are dry and ready for handling the second they leave the printer, and a special over-coating provides protection from spills and splashes.
While it's not as high-tech as the built-in Wi-Fi featured on the recently announced ST80 camera
, Samung's inclusion of a flip-out USB connector on its PL90 model is still a welcome addition. The new point-and-shoot – which takes 12.2 megapixel stills, 640x480 movies and packs some clever face detection functionality – joins the HMX-E10 pocket sized camcorder and new Dual View
models in the company's latest raft of releases.
Hand a child an ice cream you'll generally be rewarded with a beaming smile, but with this new interactive vending machine, it's the smile that gets rewarded – with a free ice cream. Created for Unilever, the world’s biggest ice cream manufacturer, the first ever smile-activated ice cream vending machine combines face-recognition technology to measure a person’s grin and take a photo that can be uploaded to Facebook thanks to the machine’s built-in 3G capability.