Methods for performing biometric recognition of a human eye and corroboration of same

• US 8,260,008 B2
• Filed: 09/21/2010
• Issued: 09/04/2012
• Est. Priority Date: 11/11/2005
• Status: Active Grant

• Current Assignee: EyeLock LLC (VOXX International Corporation)
• Original Assignee: Eyelock Corporation (VOXX International Corporation)
• Inventors: Hanna, Keith J., Hoyos, Hector T.
• Primary Examiner(s): Mehta, Bhavesh
• Assistant Examiner(s): Park, Edward
• Application Number:
  US12/887,106
• Publication Number:
  US 20110007949A1
• Time in Patent Office: 714 Days
• Field of Search: 382/100, 382/103, 382/106, 382/107, 382/115, 382/118, 382/155, 382/231, 235/380, 340 51- 592, 704/246, 704/273, 902/3
• US Class Current: 382/115
• CPC Class Codes: G06F 18/22 Matching criteria, e.g. proximity measures
• CPC Class Codes: G06T 7/20 Analysis of motion motion estimation for coding, decoding, compressing or decompressing digital video signals H04N19/43, H04N19/51
• CPC Class Codes: G06V 10/141 Control of illumination
• CPC Class Codes: G06V 40/161 Detection; Localisation; Normalisation
• CPC Class Codes: G06V 40/165 using facial parts and geometric relationships
• CPC Class Codes: G06V 40/19 Sensors therefor
• CPC Class Codes: G06V 40/197 Matching; Classification
• 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
• CPC Class Codes: G06V 40/70 Multimodal biometrics, e.g. combining information from different biometric modalities
• CPC Class Codes: H04N 23/611 where the recognised objects include parts of the human body

Abstract

A method of biometric recognition is provided. Multiple images of the face or other non-iris image and iris of an individual are acquired. If the multiple images are determined to form an expected sequence of images, the face and iris images are associated together. A single camera preferably acquires both the iris and face images by changing at least one of the zoom, position, or dynamic range of the camera. The dynamic range can be adjusted by at least one of adjusting the gain settings of the camera, adjusting the exposure time, and/or adjusting the illuminator brightness. The expected sequence determination can be made by determining if the accumulated motion vectors of the multiple images is consistent with an expected set of motion vectors and/or ensuring that the iris remains in the field of view of all of the multiple images.

Claims

1. A method of biometric recognition, comprising the steps of:

acquiring, by an image-capturing device, at least one image of a face and at least one image of an iris of an individual;

determining at least one imaging parameter from the images;

comparing the at least one imaging parameter determined from the images to at least one predetermined expected imaging parameter, wherein if the at least one imaging parameter determined from the images is significantly different from the at least one predetermined expected imaging parameter, then it is determined that the images do not form an expected sequence, said comparing step comprising determining if accumulated motion vectors of the images is consistent with an expected set of motion vectors, said comparing step performed at the same time as the acquiring step, wherein if said comparing step detects inconsistent accumulated motion vectors, the acquiring step is ceased and an error message is generated; and

if the images are determined to form an expected sequence, associating the face and iris images together.

2. A method of biometric recognition according to claim 1, wherein if the face and iris images are associated together, further comprising the step of comparing at least one of the iris images to a stored iris image in a database.

3. A method of biometric recognition according to claim 2, wherein said iris image comparing step is performed automatically by a computer.

4. A method of biometric recognition according to claim 2, wherein if the face and iris images are associated together, further comprising the step of comparing at least one of the face images to a stored face image in a database.

5. A method of biometric recognition according to claim 4, wherein said face image comparing step is performed manually by a human.

6. A method of biometric recognition according to claim 1, wherein said acquiring step is performed by a single sensing device.

7. A method of biometric recognition according to claim 6, wherein the single sensing device is a camera and said acquiring step further comprises the step of taking multiple images of a person'"'"'s face.

8. A method of biometric recognition according to claim 7, said acquiring step further comprising the step of changing a midpoint of the camera'"'"'s dynamic range while taking the multiple images of the person'"'"'s face.

9. A method of biometric recognition according to claim 7, said acquiring step further comprising the step of changing the position of the user relative to the camera while taking the multiple images of the person'"'"'s face.

10. A method of biometric recognition according to claim 7, said acquiring step further comprising the step of changing the zoom of the camera while taking the multiple images of the person'"'"'s face.

11. A method of biometric recognition according to claim 7, wherein said image-taking step occurs at a frame rate of at least 0.5 Hz.

12. A method of biometric recognition according to claim 1, wherein said acquiring step is performed until at least one face image suitable for human recognition is acquired and at least one iris image suitable for computer recognition is acquired.

13. A method of biometric recognition according to claim 12, further comprising the step of requiring the acquisition of the at least one suitable face image to occur within a predetermined amount of time of the acquisition of the at least one suitable iris image.

14. A method of biometric recognition according to claim 12, further comprising the step of requiring the acquisition of the at least one suitable face image to occur within a predetermined amount of time of the acquisition of the at least one suitable iris image.

15. A method of biometric recognition, comprising the steps of:

acquiring, by an image-capturing device, at least one image of a face and at least one image of an iris of an individual;

determining at least one imaging parameter from the images;

comparing the at least one imaging parameter determined from the images to at least one predetermined expected imaging parameter, wherein if the at least one imaging parameter determined from the images is significantly different from the at least one predetermined expected imaging parameter, then it is determined that the images do not form an expected sequence, said comparing step comprising ensuring that the iris remains in the field of view of the images, said comparing step performed at the same time as the acquiring step, wherein if said comparing step detects that the iris is not in the field of view of the images, the acquiring step is ceased and an error message is generated; and

if the images are determined to form an expected sequence, associating the face and iris images together.

16. A method of biometric recognition according to claim 15, wherein if the face and iris images are associated together, further comprising the step of comparing at least one of the iris images to a stored iris image in a database.

17. A method of biometric recognition according to claim 16, wherein said iris image comparing step is performed automatically by a computer.

18. A method of biometric recognition according to claim 15, wherein if the face and iris images are associated together, further comprising the step of comparing the at least one face image to a stored face image in a database.

19. A method of biometric recognition according to claim 18, wherein said face image comparing step is performed manually by a human.

20. A method of biometric recognition according to claim 15, wherein said acquiring step is performed by a single sensing device.

21. A method of biometric recognition according to claim 20, wherein the single sensing device is a camera and said acquiring step further comprises the step of taking multiple images of a person'"'"'s face.

22. A method of biometric recognition according to claim 21, said acquiring step further comprising the step of changing a midpoint of the camera'"'"'s dynamic range while taking the multiple images of the person'"'"'s face.

23. A method of biometric recognition according to claim 21, said acquiring step further comprising the step of changing the position of the user relative to the camera while taking the multiple images of the person'"'"'s face.

24. A method of biometric recognition according to claim 21, said acquiring step further comprising the step of changing the zoom of the camera while taking the multiple images of the person'"'"'s face.

25. A method of biometric recognition according to claim 21, wherein said image-taking step occurs at a frame rate of at least 0.5 Hz.

26. A method of biometric recognition according to claim 15, wherein said acquiring step is performed until at least one face image suitable for human recognition is acquired and at least one iris image suitable for computer recognition is acquired.