Automated spoofing transformation

1. A computer-implemented method comprising:

causing, by one or more processing devices, a first display device to display one or more calibration patterns;

obtaining, by the one or more processing devices, one or more first images displayed on the first display device, each of the one or more first images including a corresponding calibration pattern of the one or more calibration patterns,

wherein the one or more first images are captured by an image capture device disposed at a non-zero capture angle with respect to the first display device;

determining, by the one or more processing devices, based on the one or more first images, a transformation to be applied to account for the non-zero capture angle;

obtaining, by the one or more processing devices, a second image of a human user;

applying, by the one or more processing devices, the transformation to the second image to generate a transformed spoof representation of the human user for capture by the image capture device being held at the non-zero capture angle with respect to the first display device;

causing, by the one or more processing devices, the first display device to display the transformed spoof representation;

obtaining, by the one or more processing devices, a third image of the transformed spoof representation displayed on the display device and captured by the image capture device; and

testing, by the one or more processing device, the third image in a biometric authentication process.

2. The computer-implemented method of claim 1 , wherein the transformation causes the transformed spoof representation to appear to be the second image, from a perspective of the image capture device being held at the non-zero capture angle with respect to the first display device.

3. The computer-implemented method of claim 1 , wherein determining the transformation comprises determining a transformation matrix.

4. The computer-implemented method of claim 1 , wherein the transformation causes an apparent capture angle of the image capture device with respect to the first display device to be less than an actual capture angle of the image capture device with respect to the first display device.

5. The computer-implemented method of claim 1 , comprising identifying, by the one or more processing devices, a correspondence between a feature included in the one or more first images and a corresponding calibration pattern of the one or more calibration patterns.

6. The computer-implemented method of claim 1 , wherein causing the first display device to display the one or more calibration patterns comprises causing the first display device to display a plurality of calibration patterns in sequence.

7. The computer-implemented method of claim 1 , comprising determining, by the one or more processing devices, based on the one or more first images, boundaries of a field of view of the image capture device.

8. The computer-implemented method of claim 1 , wherein determining the transformation comprises determining a mapping between a field of view of the image capture device and locations on the first display device.

9. The computer-implemented method of claim 8 , wherein the mapping is between one or more corners of the field of view and one or more corresponding locations on the first display device.

10. The computer-implemented method of claim 1 , comprising causing, by the one or more processing devices, movement of the image capture device with respect to the first display device based on the one or more first images.

11. A system comprising:

a first display device;

an image capture device; and

a computer system configured to perform operations comprising:

causing the first display device to display one or more calibration patterns;

obtaining one or more first images displayed on the first display device, each of the one or more first images including a corresponding calibration pattern of the one or more calibration patterns,

wherein the one or more first images are captured by the image capture device disposed at a non-zero capture angle with respect to the first display device;

determining, based on the one or more first images, a transformation to be applied to account for the non-zero capture angle;

obtaining a second image of a human user;

applying the transformation to the second image to generate a transformed spoof representation of the human user for capture by the image capture device being held at the non-zero capture angle with respect to the first display device;

causing the first display device to display the transformed spoof representation;

obtaining a third image of the transformed spoof representation displayed on the display device and captured by the image capture device; and

testing the third image in a biometric authentication process.

12. The system of claim 11 , wherein the transformation causes the transformed spoof representation to appear to be the second image, from a perspective of the image capture device being held at the non-zero capture angle with respect to the first display device.

13. The system of claim 11 , wherein determining the transformation comprises determining a transformation matrix.

14. The system of claim 11 , wherein the transformation causes an apparent capture angle of the image capture device with respect to the first display device to be less than an actual capture angle of the image capture device with respect to the first display device.

15. The system of claim 11 , wherein the operations comprise identifying a correspondence between a feature included in the one or more first images and a corresponding calibration pattern of the one or more calibration patterns.

16. The system of claim 11 , wherein causing the first display device to display the one or more calibration patterns comprises causing the first display device to display a plurality of calibration patterns in sequence.

17. The system of claim 11 , comprising determining, based on the one or more first images, boundaries of a field of view of the image capture device.

18. The system of claim 11 , wherein determining the transformation comprises determining a mapping between a field of view of the image capture device and locations on the first display device.

19. The system of claim 18 , wherein the mapping is between one or more corners of the field of view and one or more corresponding locations on the first display device.

20. A non-transitory, computer-readable storage medium storing one or more instructions that, when executed by a computer system, cause the computer system to perform operations comprising:

causing a first display device to display one or more calibration patterns;

obtaining one or more first images displayed on the first display device, each of the one or more first images including a corresponding calibration pattern of the one or more calibration patterns,

wherein the one or more first images are captured by an image capture device disposed at a non-zero capture angle with respect to the first display device;

determining, based on the one or more first images, a transformation to be applied to account for the non-zero capture angle;

obtaining a second image of a human user;

applying the transformation to the second image to generate a transformed spoof representation of the human user for capture by the image capture device being held at the non-zero capture angle with respect to the first display device;

causing the first display device to display the transformed spoof representation;

obtaining a third image of the transformed spoof representation displayed on the display device and captured by the image capture device; and

testing the third image in a biometric authentication process.