Spoof detection using proximity sensors
Computer-implemented methods and systems for liveness analysis using proximity sensors are described. Reflective strength readings from a proximity sensor, such as an infrared proximity sensor incorporated in a mobile device, are received. A liveness measure is determined based on the one or more readings and a reflection threshold, and, based on the liveness measure, a determination is made whether a target in range of the proximity sensor is likely to be a live human.
1. A computer-implemented method comprising:
receiving one or more reflective strength readings from a proximity sensor of a device;
determining a distance between the device and a target in range of the proximity sensor;
normalizing the one or more reflective strength readings according to the determined distance to determine a reflection threshold;
determining a liveness measure based on the one or more readings and the reflection threshold; and
determining whether the target is likely to be a live human based at least in part on the liveness measure.
2. The method of claim 1 , wherein the proximity sensor comprises a photoelectric sensor, a capacitive sensor, or an acoustic sensor.
3. The method of claim 1 , wherein the device comprises a mobile device having an image sensor.
4. The method of claim 1 , wherein determining a distance between the device and a target in range of the proximity sensor comprises:
receiving one or more images of at least a portion of a face of the target; and
determining the distance based on the received one or more images.
5. The method of claim 4 , wherein the distance is determined based on an interocular distance in the one or more images.
6. The method of claim 1 , wherein determining a distance between the device and a target in range of the proximity sensor comprises:
emitting a signal from the device; and
determining the distance based on a round-trip delay of the signal.
7. The method of claim 6 , wherein the signal comprises a high-frequency ping emitted from an earpiece or speaker of the device.
8. The method of claim 1 , further comprising accepting the target if the target is determined likely to be a live human, and rejecting the target if the target is determined unlikely to be a live human.
9. The method of claim 8 , further comprising:
identifying a false rejection of the target; and
adjusting the reflection threshold based on the identification.
10. The method of claim 1 , wherein the proximity sensor comprises an infrared sensor, and wherein determining the liveness measure comprises evaluating whether the one or more reflective strength readings are representative of a strength of reflection of infrared light from human skin or tissue as compared to a strength of reflection of infrared light from a spoof.
11. A system comprising:
at least one processor; and
at least one memory storing computer-executable instructions that, when executed, configure the at least one processor to perform operations comprising:
receiving one or more reflective strength readings from a proximity sensor of a device;
determining a distance between the device and a target in range of the proximity sensor;
normalizing the one or more reflective strength readings according to the determined distance to determine a reflection threshold;
determining a liveness measure based on the one or more readings and the reflection threshold; and
determining whether the target is likely to be a live human based at least in part on the liveness measure.
12. The system of claim 11 , wherein the proximity sensor comprises a photoelectric sensor, a capacitive sensor, or an acoustic sensor.
13. The system of claim 11 , wherein the device comprises a mobile device having an image sensor.
14. The system of claim 11 , wherein determining a distance between the device and a target in range of the proximity sensor comprises:
receiving one or more images of at least a portion of a face of the target; and
determining the distance based on the received one or more images.
15. The system of claim 14 , wherein the distance is determined based on an interocular distance in the one or more images.
16. The system of claim 11 , wherein determining a distance between the device and a target in range of the proximity sensor comprises:
emitting a signal from the device; and
determining the distance based on a round-trip delay of the signal.
17. The system of claim 16 , wherein the signal comprises a high-frequency ping emitted from an earpiece or speaker of the device.
18. The system of claim 11 , wherein the operations further comprise accepting the target if the target is determined likely to be a live human, and rejecting the target if the target is determined unlikely to be a live human.
19. The system of claim 18 , wherein the operations further comprise:
identifying a false rejection of the target; and
adjusting the reflection threshold based on the identification.
20. The system of claim 11 , wherein the proximity sensor comprises an infrared sensor, and wherein determining the liveness measure comprises evaluating whether the one or more reflective strength readings are representative of a strength of reflection of infrared light from human skin or tissue as compared to a strength of reflection of infrared light from a spoof.