Iris recognition for a secure facility

• US 7,574,021 B2
• Filed: 09/18/2007
• Issued: 08/11/2009
• Est. Priority Date: 09/18/2006
• Status: Active Grant

• Current Assignee: Princeton Identity Inc.
• Original Assignee: Sarnoff Corporation (SRI International, Inc.)
• Inventors: Matey, James R.
• Primary Examiner(s): TUCKER, WESLEY J
• Application Number:
  US11/857,432
• Publication Number:
  US 20080199054A1
• Time in Patent Office: 693 Days
• Field of Search: 382/117, 382/115
• US Class Current: 382/117
• CPC Class Codes: G06V 40/19 Sensors therefor

Abstract

A method of performing iris recognition from at least one image, comprising: using a plurality of cameras to capture a plurality of images of a subject where at least one of said images contains a region having at least a portion of an iris; and processing at least one of said plurality of images to perform iris recognition; identifying the subject by the iris recognition; determining the security level of the subject from the subject'"'"'s identity; and modifying the display of a computer system in a secure information facility based on the security level of the subject.

Claims

1. A computer implemented method for performing iris recognition from at least one image, comprising:

displaying, at a display of a computer system in a secure information facility, information that is appropriate for a first subject'"'"'s security level;

using a plurality of cameras to capture a plurality of images of a second subject where at least one of said images contains a region having at least a portion of an iris;

processing, with a processor, at least one of said plurality of images to perform iris recognition;

identifying, with the processor, the second subject by the iris recognition;

determining, with the processor, the security level of the second subject from the second subject'"'"'s identity; and

modifying, with the processor, the display based on the security levels of the first and second subjects, wherein only that subset of the displayed information appropriate for the second subiect'"'"'s security level is displayed when the second subject has a different security level than the first subject.

2. The method of claim 1, wherein the information appropriate for the second subject is less than the information appropriate for the first subject.

3. The method of claim 2, further comprising the step of blanking portions of the display that are not appropriate for the for the security level of the second subject.

4. The method of claim 1, wherein the plurality of cameras comprises a plurality of wide field-of-view (WFOV) cameras and a plurality of narrow field-of-view (NFOV) cameras, wherein the step of using a plurality of cameras to capture a plurality of images of a second subject further comprises the steps of:

finding the head, then the face, and then the eyes of the second subject using at least one of the plurality of WFOV cameras to determine a region of interest (ROL); and

localizing the iris of the second subject from the ROI using at least one of the plurality of NFOV cameras.

5. The method of claim 4, further comprising the steps of:

estimating a depth map of the ROI using the processor, and selecting at least one of the plurality of NFOV cameras using the depth map.

6. The method of claim 5, wherein the depth map is estimated using at least one of a stereo camera, an infrared camera, ultrasound, and ladar.

7. The method of claim 1, further comprising the steps of:

setting a lens focus of at least one of the plurality of cameras at a series of depth curtains; and

capturing fine resolution imagery of an iris when at least one of the first subject and the second subject passes through at least one of the depth curtains.

8. A system for performing iris recognition from at least one image, comprising:

a display of a computer system in a secure information facility for displaying, information that is appropriate for a first subject'"'"'s security level;

a plurality of cameras for capturing a plurality of images of a subject where at least one of said images contains a region having at least a portion of an iris; and

a processor;

for processing at least one of said plurality of images to perform iris recognition;

for identifying the second subject by the iris recognition;

for determining the security level of the second subject from the second subject'"'"'s identity; and

for modifying the display based on the security levels of the first and second subjects, wherein only that subset of the displayed information appropriate for the second subject'"'"'s security level is displayed when the second subject has a different security level than the first subject.

9. The system of claim 8, wherein the information appropriate for the second subject is less than the information appropriate for the first subject.

10. The system of claim 9, wherein the processor is further configured for blanking portions of the display that are not appropriate for the for the security level of the second subject.

11. The system of claim 8, wherein the plurality of cameras comprises a plurality of wide field-of-view (WFOV) cameras and a plurality of narrow field-of-view (NFOV) cameras, wherein at least one of the plurality of WFOV cameras is configured for finding the head, then the face, and then the eyes of the second subject to determine a region of interest (ROI);

and wherein at least one of the plurality of NFOV cameras is configured for localizing the iris of the second subject from the ROI.

12. The system of claim 11, wherein the processor is further configured for:

estimating a depth map of the ROI using the processor; and

selecting at least one of the plurality of NFOV camera using the depth map.

13. The system of claim 12, wherein the depth map is estimated using at least one of a stereo camera, an infrared camera, ultrasound, and ladar.

14. The system of claim 8, wherein the processor is further configured for setting a lens focus of at least one of the plurality of cameras at a series of depth curtains;

and wherein at least one of the plurality of cameras is further configured for capturing fine resolution imagery of an iris when at least one of the first subject and the second subject passes through at least one of the depth curtains.

15. A computer-readable medium having stored thereon a plurality of instructions, the plurality of instructions including instructions which, when executed by a processor, cause the processor to perform the steps of a method for performing iris recognition from at least one image, comprising:

displaying, at a display of a computer system in a secure information facility, information that is appropriate for a first subject'"'"'s security level;

using a plurality of cameras to capture a plurality of images of a second subject where at least one of said images contains a region having at least a portion of an iris;

processing at least one of said plurality of images to perform iris recognition;

identifying the second subject by the iris recognition;

determining the security level of the second subject from the second subject'"'"'s identity; and

modifying the display based on the security levels of the first and second subjects, wherein only that subset of the displayed information appropriate for the second subject'"'"'s security level is displayed when the second subject has a different security level than the first subject.

16. The computer-readable medium of claim 15, wherein the information appropriate for the second subject is less than the information appropriate for the first subject.

17. The computer-readable medium of claim 16, further comprising the step of blanking portions of the display that are not appropriate for the for the security level of the second subject.

18. The computer-readable medium of claim 15, wherein the plurality of cameras comprises a plurality of wide field-of-view (WFOV) cameras and a plurality of narrow field-of-view (NFOV) cameras, wherein the step of using a plurality of cameras to capture a plurality of images of a second subject further comprises the steps of:

finding the head, then the face, and then the eyes of the second subject using at least one of the plurality of WFOV cameras to determine a region of interest (ROI); and

localizing the iris of the second subject from the ROI using at least one of the plurality of NFOV cameras.

19. The computer-readable medium of claim 18, further comprising the steps of:

estimating a depth map of the ROI using the processor; and

selecting at least one of the plurality of the NFOV cameras using the depth map.

20. The computer-readable medium of claim 19, wherein the depth map is estimated using at least one of a stereo camera, an infrared camera, ultrasound, and ladar.

21. The computer-readable medium of claim 15, further comprising the steps of:

setting a lens focus of at least one of the plurality of cameras at a series of depth curtains; and

capturing fine resolution imagery of an iris when at least one of the first subject and the second subject passes through at least one of the depth curtains.