Apparatus and methods for detecting the presence of a human eye

• US 7,801,335 B2
• Filed: 11/13/2006
• Issued: 09/21/2010
• Est. Priority Date: 11/11/2005
• Status: Active Grant

• Current Assignee: EyeLock LLC (VOXX International Corporation)
• Original Assignee: Global Rainmakers, Inc.
• Inventors: Hoyos, Hector T., Hanna, Keith J.
• Primary Examiner(s): Le; Brian Q
• Assistant Examiner(s): Park; Edward
• Application Number:
  US11/559,381
• Publication Number:
  US 20070110285A1
• Time in Patent Office: 1,408 Days
• Field of Search: 382/115, 382/116, 382/117, 382/118
• US Class Current: 382/117
• CPC Class Codes: G06V 40/19 Sensors therefor
• CPC Class Codes: G06V 40/40 Spoof detection, e.g. liveness detection
• CPC Class Codes: G06V 40/45 Detection of the body part being alive

Abstract

Apparatus and methods for determining whether a live, human eye is presented for iris-based recognition. An image is presented on a computer screen and reflected back from the eye. The reflected image is captured and processed to determine whether the reflection was consistent with a human eye.

Claims

1. A method of detecting a living human eye comprising the steps of:

presenting a first image on a display, wherein the display is oriented to face a user;

positioning at least one camera proximate the display, wherein the at least one camera is oriented to face the user so that light emitted by the display as the first image is reflected by the user and captured by the at least one camera;

obtaining a second image through the at least one camera; and

using a computing device to perform;

determining whether at least a portion of the second image includes a representation of the first image on the display reflected by a curved surface consistent with a human eye, wherein the step of positioning the at least one camera proximate the display comprises positioning the at least one camera 75 to 500 mm from the user and wherein the step of determining whether the at least the portion of the second image includes the representation of the first image on the display reflected by the curved surface consistent with a human eye comprises determining whether the representation of the first image is 12.5 to 166.7 times smaller than that of a reflection off a flat surface.

2. The method of detecting a human eye of claim 1, wherein the step of determining whether the at least a portion of the second image includes the representation of the first image on the display reflected by the curved surface consistent with the human eye comprises determining whether the representation of the first image is equal to a human-eye magnification level and wherein the human-eye reduction in magnification level compared to a reflection off a flat surface is determined by dividing a distance from the display to the user by 3 to 6 millimeters.

3. The method of detecting a human eye of claim 1, wherein the step of determining whether the at least the portion of the second image includes the representation of the first image on the display reflected by the curved surface consistent with the human eye comprises determining whether the representation of the first image is at least ten times smaller than the first image.

4. The method of detecting a human eye of claim 1, wherein the step of determining whether the at least the portion of the second image includes the representation of the first image on the display reflected by an ellipsoidal surface with an eccentricity of 0.5 and a radius of curvature at the apex of the surface of 7.8 mm.

5. The method of detecting a human eye of claim 1, wherein the step of determining whether the at least the portion of the second image includes the representation of the first image on the display reflected by the curved surface consistent with the human eye comprises determining whether the representation of the first image has a magnification at the center of the representation that is smaller than a magnification in areas surrounding the center of the representation.

6. The method of detecting a human eye of claim 1, further comprising the step of isolating a portion of the second image containing a representation of a human iris, wherein the subsequent step of comparing is performed on the portion of the second image containing the representation of the human iris.

7. The method of detecting a human eye of claim 1, wherein the step of determining whether the at least the portion of the second image includes the representation of the first image on the display reflected by the curved surface consistent with the human eye comprises searching the second image for a warped version of the first image.

8. The method of detecting a human eye of claim 1, wherein the step of presenting the first image on the display comprises presenting a checkered pattern having a plurality of black and white squares;

and wherein the step of determining whether the at least the portion of the second image includes the representation of the first image on the display reflected by the curved surface consistent with the human eye comprises searching the second image for a deformed checkered pattern.

9. The method of detecting a human eye of claim 1, wherein the step of positioning the at least one camera proximate the display comprises placing the camera on the display.

10. The method of detecting a human eye of claim 9, further comprising the step of providing a computer operationally coupled with the display and the at least one camera, wherein the step of determining whether the at least the portion of the second image includes the representation of the first image on the display reflected by a curved surface consistent with the human eye is performed by the computer.

11. The method of detecting a human eye of claim 10, further comprising the step of establishing a network connection with a remote computer wherein the step of determining whether the at least a portion of the second image includes a representation of the first image on the display reflected by a curved surface consistent with the human eye is performed by the remote computer.

12. The method of detecting a human eye of claim 1, further comprising the step of detecting a skin area in the second image and determining whether the reflection of light from the skin area is consistent with human skin.

13. A method of detecting a living human eye comprising the steps of:

presenting a first image on a display, wherein the display is oriented to face a user;

positioning at least one camera proximate the display, wherein the at least one camera is oriented to face the user so that light emitted by the display as the first image is reflected by the user and captured by the at least one camera;

obtaining a second image through the at least one camera; and

using a computing device to perform;

determining whether at least a portion of the second image includes a representation of the first image on the display reflected by a curved surface consistent with a human eye,

presenting a third image on the display, wherein the third image is different than the first image; and

obtaining a fourth image through the at least one camera, and wherein

the step of determining whether at least a portion of the second image includes the representation of the first image further comprises determining a difference between the fourth image and the second image to produce a difference image, identifying a portion of the difference image containing a difference between a reflection of the first image and the third image, wherein a human eye is detected when the portion of the difference image is consistent with a reflection formed by a curved surface.

14. The method of detecting a human eye of claim 13, wherein the first image comprises a first checkered pattern and the third image comprises a second checkered pattern having an arrangement of checkered squares different than the first checkered pattern.

15. The method of detecting a human eye of claim 13, further comprising the step of aligning the second image and the fourth image prior to determining the difference between the fourth image and the second image.

16. The method of detecting a human eye of claim 13, wherein the step of identifying the portion of the difference image containing the difference between the reflection of the first image and the third image comprises identifying the portion of the difference image having an area of greatest difference between the second image and the fourth image.

17. The method of detecting a human eye of claim 13, further comprising the step of

determining an image reflection size reduction compared to the reflection off a flat surface of the portion of the difference image containing the difference between the reflection of the first image and the third image.

18. The method of detecting a human eye of claim 13, wherein a human eye is detected when a ratio between an image size and the image reflection size is greater than 10 to 1.

19. The method of detecting a human eye of claim 13, wherein a human eye is detected when a ratio between an image size and the image reflection size is equal to a distance between the computer screen and the user divided by 3 to 6 millimeters.

20. The method of detecting a human eye of claim 13, further comprising the step of detecting a skin area in the second image and determining whether the reflection of light from the skin area is consistent with human skin.

21. A method of detecting a human iris comprising the steps of:

presenting a first image on a display positioned in front of a user;

capturing a first reflection of the first image off of the user through a camera;

presenting a second image on the display positioned in front of the user;

capturing a second reflection of the second image off of the user through the camera;

using a computing device to perform;

comparing the first reflection of the first image with the second reflection of the second image to determine whether the first reflection and the second reflection were formed by a curved surface consistent with a human eye,

wherein the step of comparing the first reflection of the first image with the second reflection of the second image comprises calculating a difference between the first reflection and the second reflection to provide a difference image, identifying a portion of the difference image containing a difference between a reflection of the first image and a reflection of the second image, determining a size of the portion of the difference image wherein a human iris is detected when the ratio of the size of the portion of the difference image to the first and second image is equal to a human-eye magnification level.

22. The method of detecting a human iris of claim 21, wherein the human-eye magnification level is determined by dividing a distance from the display to the user by 3 to 6 millimeters.

23. The method of detecting a human iris of claim 21, further comprising the step of aligning the first reflection and the second reflection prior to determining the difference between the first reflection and the second reflection.

24. The method of detecting a human iris of claim 21, wherein the step of presenting the first image comprises presenting a checkered pattern of two colors and wherein the step of presenting the second image comprises inverting the two colors in the checkered pattern.

25. The method of detecting a human eye of claim 21, further comprising the step of detecting a skin area in the second image and determining whether the reflection of light from the skin area is consistent with human skin.

26. A method of detecting a living human eye comprising the steps of:

presenting one or more displays, wherein the displays are oriented to face a user;

positioning at least one camera proximate the displays, wherein the at least one camera is oriented to face the user so that light emitted by the displays is reflected by the user and captured by the at least one camera as a first image;

obtaining a second image through the at least one camera at a different time than the first image;

detecting a first position of a reflection in the first image and a second position of a reflection in the second image;

using a computing device to perform;

normalizing a positional change of the user in the first image and the second image based upon the first position and the second position, wherein the step of normalizing comprises compensating for motion during the time between the first image and the second image by using at least a translation motion model to detect residual motion of the position of the reflection; and

determining whether a change between at least a portion of the first image and the second image is consistent with reflection by a curved surface consistent with that of a human eye.

27. The method of detecting a human eye of claim 26, further comprising the step of detecting a skin area in the second image and determining whether the reflection of light from the skin area is consistent with human skin.