IRIS DEBLURRING METHOD BASED ON GLOBAL AND LOCAL IRIS IMAGE STATISTICS

• US 20100202667A1
• Filed: 02/06/2009
• Published: 08/12/2010
• Est. Priority Date: 02/06/2009
• Status: Active Grant

• Current Assignee: Robert Bosch GmbH
• Original Assignee: Robert Bosch GmbH
• Inventors: YANG, RUIGANG, REN, LIU, HUANG, XINYU
• Granted Patent: US 8,374,389 B2
• Time in Patent Office: Days
• US Class Current: 382/117
• CPC Class Codes: G06T 2207/30041 Eye; Retina; Ophthalmic
• CPC Class Codes: G06T 5/73 Deblurring; Sharpening
• CPC Class Codes: G06V 40/19 Sensors therefor
• CPC Class Codes: H04N 23/683 performed by a processor, e.g. controlling the readout of an image memory

Abstract

A method of identifying a living being includes using a camera to capture a blurred visual image of an iris of the living being. The blurred visual image is digitally unblurred based on a distribution of eye image gradients in an empirically-collected sample of eye images and characteristics of pupil region. The unblurred image is processed to determine an identity of the living being.

Claims

1. A method of identifying a living being, comprising the steps of:

using a camera to capture a blurred visual image of an iris of the living being;

digitally unblurring the blurred visual image based on a distribution of eye image gradients in an empirically-collected sample of eye images and distributions from characteristics of local regions; and

processing the unblurred image to determine an identity of the living being.

2. The method of claim 1 comprising the further step of computing the distributions from characteristics of local regions from iris images only.

3. The method of claim 1 comprising the further steps of approximating the distribution of eye image gradients as a quadratic piecewise function.

4. The method of claim 1 comprising the further step of forming the distribution of eye image gradients from statistics derived from measurements of a population of eye regions.

5. The method of claim 1 comprising the further steps of:

forming the distributions from characteristics of local regions from characteristics of intensity value of pupil region; and

forming the distribution of eye image gradients from global intensity value statistics derived from measurements of a population of eye regions.

6. The method of claim 5 wherein the distributions from characteristics of intensity value of pupil region include:

distribution from local highlight intensity value of pupil region; and

distribution from local non-highlight intensity value of pupil region.

7. The method of claim 6 comprising the further steps of:

detecting the highlight regions and the non-highlight regions around pupil region in a captured image;

deriving the distribution of the local highlight intensity value from the portion identified as corresponding to the highlight regions; and

deriving the distribution of the local non-highlight intensity value from the portion identified as corresponding to the non-highlight regions.

8. The method of claim 1 wherein the distribution comprises a distribution of iris image gradients.

9. A method of identifying a living being, comprising the steps of:

using a camera to capture a blurred visual image of an iris of the living being;

digitally unblurring the blurred visual image based on;

distributions from intensity value of pupil region; and

distribution from global intensity value statistics derived from measurements of a population of eye regions; and

processing the unblurred image to determine an identity of the living being.

10. The method of claim 9 comprising the further step of modeling the global intensity value statistics as a quadratic piecewise function.

11. The method of claim 9 wherein distributions from characteristics of intensity value of pupil region include:

distribution from local highlight intensity value of pupil region; and

distribution from local non-highlight intensity value of pupil region.

12. The method of claim 11 comprising the further steps of:

detecting the highlight regions and the non-highlight regions around pupil region in a captured image;

deriving the distribution of the local highlight intensity value from the portion identified as corresponding to the highlight regions; and

deriving the distribution of the local non-highlight highlight intensity value from the portion identified as corresponding to the non-highlight regions.

13. The method of claim 9 wherein the processing step includes matching the unblurred image to a stored image of an iris of the living being.

14. The method of claim 9 comprising the further step of estimating a blur kernel, the unblurring step including digitally unblurring the blurred visual image based on the estimated blur kernel.

15. A method of identifying a living being, comprising the steps of:

capturing a blurred visual image of an iris of the living being;

digitally unblurring the blurred visual image based on;

distribution from local highlight intensity value of pupil region;

distribution from local non-highlight intensity value of pupil region; and

distribution of global intensity value statistics derived from measurements of a population of eye regions; and

processing the unblurred image to determine an identity of the living being.

16. The method of claim 15 comprising the further step of modeling the global intensity value statistics as a quadratic piecewise function.

17. The method of claim 16 wherein the quadratic piecewise function consists of two separate continuous functions.

18. The method of claim 15 comprising the further steps of:

detecting the highlight regions and the non-highlight regions around pupil region in a captured image;

deriving the distribution of the local highlight intensity value from the portion identified as corresponding to the highlight regions; and

deriving the distribution of the local non-highlight highlight intensity value from the portion identified as corresponding to the non-highlight regions.

19. The method of claim 15 wherein the processing step includes matching the unblurred image to a stored image of an iris of the living being.

20. The method of claim 15 comprising the further step of estimating a blur kernel, the unblurring step including digitally unblurring the blurred visual image based on the estimated blur kernel.