Imagine a world without crime, where state-of-the art technology helps identifying suspicious individuals even before they do something naughty. A bit like Minority Report but without creepy psychics floating in swimming pools. A world where smartphones and technologies used for video game consoles are more efficient in busting perpetrators than your typical donut-munching cop. Sounds futuristic? Well, you will be surprised, but some of these apparently wild ideas have already found their fervent supporters. One of them is Singapore's Ministry of Home Affairs. 

To be more specific, Singapore’s Ministry of Home Affairs (MHA) has been exploring the use of Kinect to push the boundaries of border control and public safety. Kinect’s unique depth sensors can register information that optical cameras cannot, for instance whether someone is hiding behind tinted windows in a car. Little wonder that MHA is contemplating using Kinect to defend borders and protect public safety. MHA believes that Kinect can be used to protect citizens, given its ability to pick up potential threats with its full-body 3D motion capture, facial recognition, and voice recognition capabilities. In terms of perimeter protection, Kinect has the power to build a virtual fence around critical borders, detecting unusual border crossings, identifying if someone is hiding in a corner, or carrying a weapon.

Texting, calling, busting perps

However ingenious it seems, the idea to identify perps with help of facial recognition technology is not a new one. With the snap of an iPhone camera, one police department is already identifying suspects on the go. Using an app called MORIS (Mobile Offender Recognition and Identification System), the police department in Brockton, Massachusetts is matching photos of suspects with a database in development by statewide sheriff’s departments. The app allows officers to identify suspects through facial recognition, iris biometrics and fingerprints. Conveniently, all of these functions are combined in one device. Police officers in Chicago, Illinois can remotely access video shot from any of the city’s 24,000 closed-circuit television cameras, and they are already using that ability to lay their hands on suspects who thought they could outwit surveillance. Forces of law and order in the Windy City recently issued their first arrest stemming from the use of space-age facial-recognition technology coupled with thousands of cameras that collect live video in real-time at all hours of the day. The With a hefty grant of $5.4 million dedicated to the program, it is now possible to update an already impressive range of city-licensed surveillance cameras to run in tandem with NeoFace, a high-tech analysis program used by various governments and law enforcement agencies around the globe to grab biometric data off of an image and match it to another.

The way you talk, the way you walk

While traditional biometrics scanners can be easily deceived by high-quality photos, Kinect with its advanced sensors and near-IR technology helps to see past the forgery and raise the alarm in real time. Improved biometrics can be a powerful tool in crime prevention, but so is a new multifactor biometric system from FST21 that identifies known approved people as they walk up to a building or access point. FST21, which recently won an award from the security industry association ASIS for its In Motion Identification system, combines multiple technologies with as many as eight different identification schemes to achieve 99.7 percent accuracy, even when up to 100 people are approaching an entrance simultaneously. FST21 combines facial recognition techniques with height, gait, length of limbs, voice characteristics, and other physical identifiers with behavioral characteristics such as how you walk, where you enter from, what time you typically arrive, etc. The system, which uses high-definition cameras in places of standard CCTV cameras, connects the footage to an onsite electronic brain that learns your behavior automatically. Guards can optionally watch footage in real time as the system identifies known personnel, who are visually tagged onscreen with their names in green if “known good” and red if “known bad,” and also highlights unknown individuals.

Sources: http://www.microsoft.com; http://www.cultofmac.com; http://beforeitsnews.com; http://venturebeat.com