Recognition

If you watch a handwriting expert authenticate a signature, they will talk about echoes of the process of signing one's name – darker or lighter lines reveal pressure variations, the shape of the loops reveals the shaking of the hand, and the flow of the ink shows if the signature was laid down without hesitation. These echoes of the act of writing make a signature far more revealing than a simple squiggle on paper. Now researchers from the Fraunhofer Institute for Computer Graphics Research (IGD) have created a credit card that contains a thorough description of these signature traits, which can be used for instant authentication.  Read More

If you’re one of the many people who hate poking at the tiny virtual keys on smartphone keyboards, then you might like the experimental “airwriting” glove system created by a team of computer scientists at Germany’s Karlsruhe Institute of Technology. When the glove’s wearer draws letters in the air with their hand, the system can identify which letters are being drawn. Those letters are converted into digital text, which could then be input into an email, text message, or any other type of mobile app.  Read More

Do you ever get the creep feeling that store mannequins are ... watching you? Well, that feeling may now be justified. Italian display form company Almax has recently introduced its EyeSee line of mannequins, that are equipped with cameras and microprocessors in their heads.  Read More

Nuance Communications has updated its leading speech-to-text application Dragon Dictate for Mac to version 3, and Gizmag goes hands-on to investigate whether it can finally offer software-based dictation which is both practical and appealing, when compared to manual typing.  Read More

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.  Read More

Facial recognition might be all the rage in giving computer systems the ability to ascertain the identity of individuals - what with most people having different facial features and all. But a team from the Hasso Plattner Institute in Potsdam, Germany, has taken a different approach to identify users of touch-based tabletop computers like Microsoft's Surface. Instead of focusing on the face, the team has looked in the opposite direction to develop a system known as Bootstrapper which distinguishes between users based on their footwear.  Read More

Who needs face detection when your car can know who's sitting in it based on their rear-end? A group of Japanese researchers at the Advanced Institute of Industrial Technology (AIIT) have developed a car seat that can identify drivers while they're sitting down. The way the technology works is pretty simple. The seat is retrofitted with 360 different sensors. Those sensors take into account things like your weight, the highest value of pressure on the seat, and where you come in contact with the seat. The idea is that we all sit in car seats relatively the same way each time, so the seat should be able to tell who is sitting in it, ensuring that the person is the owner of the car rather than a car thief.  Read More

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.  Read More

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.  Read More