Scientists develop touch-based identity recognition software for smartphones

According to a new report, US-based scientist Cheng Bo and his colleagues at the Illinois Institute of Technology have developed advance touch sensitive software that would make a smartphone smart enough to identify the smartphone owner on the basis of their touch gestures like swipe or even taps on screen. A PTI report suggests that this new software named as Silent-Sense has demonstrated 99 percent accuracy in tests conducted by these US-based scientists and could soon be used as a user identity-related feature on future smartphones.

The tech will mainly work on the users’ touch behavior on the display of a touchscreen smartphone and will thus use phone’s built-in sensors to process. It will first track a user’s fingertip size, finger-pressure on screen, duration of a tap, as well as finger position while one will be using the device. And then by applying some pre-fed, software algorithm on these unique gestures the smartphone will record this information to create a unique identity for the user. And once that will be done, the phone will get locked automatically if it finds an alien usage pattern that does not match with the recorded one.

To further ensure the software’s accuracy, scientists have enabled smartphone’s accelerometer and gyroscope, as well as walking speed to make the tech more efficient even when the user is on the move.

Reportedly, the test was conducted on 100 smartphones users and could recognize a user within 10 taps on the screen, and an average of 2.3 touches to identify a user in almost 98 percent of the time. The software is not able to function while using apps and mobile games, however the report suggest that it does start working on more data-sensitive applications like email or SMS.


Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Google+ photo

You are commenting using your Google+ account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )


Connecting to %s