SYSTEM AND METHOD FOR PASSIVE LIVE PERSON VERIFICATION USING REAL-TIME EYE REFLECTION

• US 20140169642A1
• Filed: 12/17/2012
• Published: 06/19/2014
• Est. Priority Date: 12/17/2012
• Status: Active Grant

• Current Assignee: Qualcomm, Inc.
• Original Assignee: Qualcomm, Inc.
• Inventors: Law, Henry Hing, Kwong, Tung Chuen, Chan, Benjamin Koon Pan, Yu, Wilson Hung, Zhou, Yugang
• Granted Patent: US 9,058,519 B2
• Time in Patent Office: Days
• US Class Current: 382/117
• CPC Class Codes: G06V 40/18 Eye characteristics, e.g. of the iris
• CPC Class Codes: G06V 40/40 Spoof detection, e.g. liveness detection

Abstract

Systems, methods, and apparatus for detecting a live human face in an image are disclosed. The methods, systems, and apparatus are capable of capturing an image of a verification pattern that has been reflected from a defined region of interest of a user'"'"'s eye. The captured image can be compared to the emitted verification pattern to determine whether the captured reflection matches the emitted pattern and is within the region of interest to verify a live user of an electronic device.

Claims

1. A method for authenticating a user of a device, comprising:

defining a region of interest corresponding to a user'"'"'s eye;

calibrating a background pixel range of the region of interest of the user'"'"'s eye;

emitting a verification pattern from a display of the device;

capturing a reflected image of the verification pattern from the region of interest of the user'"'"'s eye; and

verifying a live user by comparing the captured reflected image to an expected pixel pattern.

2. The method of claim 1, wherein calibrating a background pixel range of the region of interest of the user'"'"'s eye is conducted with a display light turned off.

3. The method of claim 1, wherein verifying the live user comprises comparing captured pixel values of the reflected image with a background pixel value for each pixel in the region of interest.

4. The method of claim 1, wherein defining a region of interest corresponding to a user'"'"'s eye comprises determining the location of a user'"'"'s eye on the user'"'"'s face.

5. The method of claim 4, wherein defining a region of interest corresponding to a user'"'"'s eye comprises locating a region encompassing a user'"'"'s pupil, the region defined by an upper boundary, a lower boundary, a left boundary, and a right boundary.

6. The method of claim 1, wherein the verification pattern comprises a random pattern.

7. The method of claim 1, wherein the verification pattern comprises a display light turned on and off in a random pattern.

8. The method of claim 1, wherein the verification pattern is a static black and white image displayed on the display.

9. The method of claim 1, wherein the verification pattern is a static color image displayed on the display.

10. The method of claim 1, wherein the verification pattern is a moving image displayed on the display.

11. The method of claim 10, wherein the moving image is a black and white image.

12. The method of claim 10, wherein the moving image is a color image.

13. The method of claim 6, wherein verifying a live user comprises determining a reflected pattern from cluster sizes of pixels of the reflected image and determining whether the reflected pattern matches the emitted random pattern.

14. The method of claim 8, wherein verifying a live user comprises determining a reflected pattern from cluster sizes of pixels of the reflected image and determining whether the reflected pattern matches the static black and white image displayed on the display.

15. The method of claim 9, wherein verifying a live user comprises determining a reflected pattern from cluster sizes of pixels of the reflected image and determining whether the reflected pattern matches the static color image displayed on the display.

16. The method of claim 11, where verifying a live user comprises determining a reflected pattern from cluster sizes of pixels of the reflected image and determining whether the reflected pattern matches the moving black and white image.

17. The method of claim 12, where verifying a live user comprises determining a reflected pattern from cluster sizes of pixels of the reflected image and determining whether the reflected pattern matches the moving color image.

18. A system for improving verification of passive recognition of a user'"'"'s face by a device, comprising:

an image sensor connected to a display device; and

a control module configured to;

define a region of interest corresponding to a user'"'"'s eye;

calibrate a background pixel range of the region of interest of the user'"'"'s eye;

emit a random pattern of light from the device;

capture a reflection of the random pattern reflected from the region of interest of the user'"'"'s eye; and

verify a live user by comparing the captured reflected image to an expected pixel pattern.

19. The system of claim 18, wherein the control module is configured to define a region of interest corresponding to a user'"'"'s eye by determining the locations of a user'"'"'s eye on the user'"'"'s face.

20. The system of claim 19, wherein the control module is configured to define a region of interest corresponding to a user'"'"'s eye by locating a region encompassing a user'"'"'s pupil, the region defined by an upper boundary, a lower boundary, a left boundary, and a right boundary.

21. The system of claim 18, wherein the control module is configured to verify a live user by determining a reflected pattern from cluster sizes of pixels of the reflected image and determining whether the reflected pattern matches the emitted random pattern.

22. A system for improving verification of passive recognition of a user'"'"'s face by a device, comprising:

a camera connected to a display device; and

a control module configured to;

define a region of interest corresponding to a user'"'"'s eye;

calibrate a background pixel range of the region of interest of the user'"'"'s eye;

display a verification pattern on a display of the device;

capture a reflected image of the verification pattern from the region of interest of a user'"'"'s eye; and

verify a live user by comparing the captured reflected image to an expected pixel pattern.

23. The system of claim 22, wherein the control module is configured to define a region of interest corresponding to a user'"'"'s eye by determining the locations of a user'"'"'s eye on the user'"'"'s face.

24. The system of claim 23, wherein the control module is configured to define a region of interest corresponding to a user'"'"'s eye by locating a region encompassing a user'"'"'s pupil, the region defined by an upper boundary, a lower boundary, a left boundary, and a right boundary.

25. The system of claim 22, wherein the verification pattern is a random pattern.

26. The system of claim 22, wherein the verification pattern is a static black and white image displayed on the display.

27. The system of claim 22, wherein the verification pattern is a static color image displayed on the display.

28. The system of claim 22, wherein the verification pattern is a moving image displayed on the display.

29. The system of claim 28, wherein the moving image is a black and white image.

30. The system of claim 28, wherein the moving image is a color image.

31. The system of claim 26, wherein the control module is configured to verify a live user by determining a reflected pattern from cluster sizes of pixels of the reflected image and determining whether the reflected pattern matches the static black and white image displayed on the display.

32. The system of claim 27, wherein the control module is configured to verify a live user by determining a reflected pattern from cluster sizes of pixels of the reflected image and determining whether the reflected pattern matches the static color image displayed on the display.

33. The system of claim 29, wherein the control module is configured to verify a live user by determining a reflected pattern from cluster sizes of pixels of the reflected image and determining whether the reflected pattern matches the moving black and white image displayed on the display.

34. The system of claim 30, wherein the control module is configured to verify a live user by determining a reflected pattern from cluster sizes of pixels of the reflected image and determining whether the reflected pattern matches the moving color image displayed on the display.

35. An apparatus for improving verification of passive recognition of a user'"'"'s face by a device, comprising:

a processor;

a memory, operably coupled to the processor;

a display, operably coupled to the processor;

an imaging sensor operably coupled to the processor;

a calibration module configured to define a region of interest corresponding to a user'"'"'s eye and calibrate a background pixel range of the region of interest of the user'"'"'s eye;

a pattern generating module configured to generate and emit a verification pattern from a display of the device;

an image capture module configured to capture a reflected image of the verification pattern from the region of interest of the user'"'"'s eye; and

a verification module configured to compare the captured reflected image to an expected pixel pattern.

36. The apparatus of claim 35, wherein the verification pattern comprises a display light turned on and off in a random pattern.

37. The apparatus of claim 35 further comprising a user verification module configured to notify the user of a live person verification event.

38. The apparatus of claim 36, wherein the verification module is configured to verify a live user by determining a reflected pattern from cluster sizes of pixels of the reflected image and determining whether the reflected pattern matches the emitted random pattern.

39. A device for improving verification of passive recognition of a user'"'"'s face by a device, comprising:

an imaging sensor configured to capture an image of a user'"'"'s eye;

means for defining a region of interest of the user'"'"'s eye;

means for calibrating a background pixel region of interest of the user'"'"'s eye with the device light off;

means for displaying a random verification pattern on the display;

means for capturing a reflection of the verification pattern reflected from the region of interest of a user'"'"'s eye; and

means for verifying a live user by comparing a captured pixel value with a background pixel value for each pixel in the region of interest.

40. A non-transitory computer readable medium, storing instructions that when executed by a processor, cause the processor to perform the method of:

defining a region of interest corresponding to a user'"'"'s eye;

calibrating a background pixel range of the region of interest of the user'"'"'s eye with a device light off;

emitting a random verification pattern from the device;

capturing a reflection of the verification pattern reflected from the region of interest of a user'"'"'s eye; and

verifying a live user by comparing a captured pixel value with a background pixel value for each pixel in the region of interest.