Biometrics with spatiospectral spoof detection

• US 7,801,339 B2
• Filed: 07/31/2006
• Issued: 09/21/2010
• Est. Priority Date: 07/31/2006
• Status: Active Grant

• Current Assignee: HID Global Corporation (Assa Abloy AB)
• Original Assignee: Lumidigm Incorporated (Assa Abloy AB)
• Inventors: Rowe, Robert K., Nixon, Kristin A., Sidlauskas, David P.
• Primary Examiner(s): Strege; John B
• Application Number:
  US11/461,253
• Publication Number:
  US 20080025580A1
• Time in Patent Office: 1,513 Days
• Field of Search: 382/115, 382/124, 382/125, 340/5.53, 340/5.83
• US Class Current: 382/124
• CPC Class Codes: G06V 40/1394 using acquisition arrangements

Abstract

Methods and apparatus are described for performing a biometric function on a purported skin site. The site is illuminated under distinct optical conditions and light reflected from the site is received. A feature value for several features is derived from the received light, permitting a comparison to be performed with reference feature values. Whether the purported skin site is a true skin site is determined from the comparison.

Claims

1. A method of performing a biometric function on a purported skin site, the method comprising:

illuminating the purported skin site under a plurality of distinct optical conditions;

receiving spatially distributed multispectral light reflected from the purported skin site;

deriving a feature value for each of a plurality of features from the received light;

performing a comparison of the derived feature value for each of the plurality of features with reference feature values; and

determining whether the purported skin site is a true skin site from the comparison.

2. The method recited in claim 1 wherein deriving the feature value comprises extracting a plurality of images from the received light, each of the images corresponding to an image under one of the plurality of distinct optical conditions.

3. The method recited in claim 2 wherein deriving the feature value further comprises decomposing each of the plurality of images into a plurality of different frequency spatial components.

4. The method recited in claim 3 wherein decomposing each of the plurality of images comprises performing a wavelet decomposition.

5. The method recited in claim 3 wherein deriving the feature value further comprises calculating a ratio of a first of the different spatial frequency components to a second of the different spatial frequency components.

6. The method recited in claim 3 wherein deriving the feature value further comprises calculating an intensity distribution for each of the different spatial frequency components.

7. The method recited in claim 6 wherein at least one of the features is substantially invariant to illumination intensity.

8. The method recited in claim 7 wherein the at least one of the features comprises a ratio of an intensity at a first predetermined percentile of the intensity distribution to an intensity at a second predetermined percentile of the intensity distribution.

9. The method recited in claim 7 wherein at least a second of the features varies with illumination intensity.

10. The method recited in claim 9 wherein:

the at least one of the features comprises a ratio of an intensity at a first predetermined percentile of the intensity distribution to an intensity at a second predetermined percentile of the intensity distribution; and

the at least a second of the features comprises a difference between the intensity at the first predetermined percentile and the intensity at the second predetermined percentile.

11. The method recited in claim 6 wherein at least one of the features varies with illumination intensity.

12. The method recited in claim 1 wherein determining whether the purported skin site is a true skin site comprises determining that the purported skin site is not a true skin site, the method further comprising issuing an alarm to identify the purported skin site as a spoof.

13. The method recited in claim 1 further comprising performing a biometric identification from the received light.

14. A biometric sensor comprising:

an illumination subsystem disposed to illuminate a purported skin site of an individual;

a detection subsystem disposed to receive light reflected from the purported skin site; and

a controller in communication with the illumination subsystem and with the detection subsystem, the controller including;

instructions for illuminating the purported skin site with the illumination subsystem under a plurality of distinct optical conditions during a single illumination session;

instructions for receiving spatially distributed multispectral light reflected from the purported skin site with the detection subsystem;

instructions for deriving a feature value for each of a plurality of features from the received light;

instructions for performing a comparison of the derived feature value for each of the plurality of features with reference feature values; and

determining whether the purported skin site is a true skin site from the comparison.

15. The biometric sensor recited in claim 14 wherein the instructions for deriving the feature value comprises instructions for extracting a plurality of image representations from the received light, each of the image representations corresponding to an image under one of the plurality of distinct optical conditions.

16. The biometric sensor recited in claim 15 wherein the instructions for deriving the feature value further comprise instructions for decomposing each of the plurality of image representations into a plurality of different spatial frequency components.

17. The biometric sensor recited in claim 16 wherein the instructions for decomposing each of the plurality of image representations comprise instructions for performing a wavelet decomposition.

18. The biometric sensor recited in claim 16 wherein the instructions for deriving the feature value further comprise instructions for calculating a ratio of a first of the different spatial frequency components to a second of the different spatial frequency components.

19. The biometric sensor recited in claim 16 wherein the instructions for deriving the feature value further comprise instructions for calculating an intensity distribution for each of the different spatial frequency components.

20. The biometric sensor recited in claim 19 wherein at least one of the features is substantially invariant to illumination intensity.

21. The biometric sensor recited in claim 20 wherein the at least one of the features comprises a ratio of an intensity at a first predetermined percentile of the intensity distribution to an intensity at a second predetermined percentile of the intensity distribution.

22. The biometric sensor recited in claim 20 wherein at least a second of the features varies with illumination intensity.

23. The biometric sensor recited in claim 22 wherein:

the at least one of the features comprises a ratio of an intensity at a first predetermined percentile of the intensity distribution to an intensity at a second predetermined percentile of the intensity distribution; and

the at least a second of the features comprises a difference between the intensity at the first predetermined percentile and the intensity at the second predetermined percentile.

24. The biometric sensor recited in claim 19 wherein at least one of the features varies with illumination intensity.

25. The biometric sensor recited in claim 14 wherein controller determines that the purported skin site is not a true skin site, the controller further comprising instructions for issuing an alarm to identify the purported skin site as a spoof.

26. The biometric sensor recited in claim 14 wherein the controller further comprises instructions for performing a biometric identification from the received light.