Sensing Movement on Smartphone Devices to Assess User Interaction for Face Verification

Unlocking and protecting smartphone devices has

become easier with the introduction of biometric face verification,

as it has the promise of a secure and quick authentication solution

to prevent unauthorised access. However, there are still many

challenges for this biometric modality in a mobile context, where

the user’s posture and capture device are not constrained. This

research proposes a method to assess user interaction by analysing

sensor data collected in the background of smartphone devices

during verification sample capture. From accelerometer data, we

have extracted magnitude variations and angular acceleration for

pitch, roll, and yaw (angles around the x-axis, y-axis, and z-axis of

the smartphone respectively) as features to describe the amplitude

and number of movements during a facial image capture process.

Results obtained from this experiment demonstrate that it can be

possible to ensure good sample quality and high biometric

performance by applying an appropriate threshold that will

regulate the amplitude on variations of the smartphone

movements during facial image capture. Moreover, the results

suggest that better quality images are obtained when users spend

more time positioning the smartphone before taking an image.