CROSS-SENSOR IRIS MATCHING

• US 20140313306A1
• Filed: 04/17/2013
• Published: 10/23/2014
• Est. Priority Date: 04/17/2013
• Status: Active Grant

• Current Assignee: Honeywell International Inc.
• Original Assignee: Honeywell International Inc.
• Inventors: Venkatesha, Sharath, McCloskey, Scott
• Granted Patent: US 9,224,042 B2
• Time in Patent Office: Days
• US Class Current: 348/78
• CPC Class Codes: G06V 40/19 Sensors therefor
• CPC Class Codes: G06V 40/193 Preprocessing; Feature extraction
• CPC Class Codes: G06V 40/197 Matching; Classification

Abstract

Methods, devices, and systems for cross-sensor iris matching are described herein. One method includes capturing a first image of an iris using a first sensor, capturing a second image of an iris using a second sensor, and determining whether the iris in the first image matches the iris in the second image based on characteristics of the first sensor and the second sensor and image quality of the first image and the second image.

Claims

1. A method for cross-sensor iris matching, comprising:

capturing a first image of an iris using a first sensor;

capturing a second image of an iris using a second sensor; and

determining whether the iris in the first image matches the iris in the second image based on;

characteristics of the first sensor and the second sensor; and

image quality of the first image and the second image.

2. The method of claim 1, wherein determining whether the iris in the first image matches the iris in the second image includes:

accounting for a difference between the characteristics of the first sensor and the characteristics of the second sensor; and

accounting for a difference between the image quality of the first image and the image quality of the second image.

3. The method of claim 1, wherein the method includes:

normalizing the first image and the second image based on the characteristics of the first sensor and the second sensor; and

determining whether the iris in the first image matches the iris in the second image based on the normalized images.

4. The method of claim 1, wherein the method includes:

matching the iris in the first image and the Iris in the second image for a plurality of frequency bands;

fusing the matched irises for each frequency band using the image quality of the first image and the second image to determine a score fusion for all the frequency bands; and

determining whether the iris in the first image matches the iris in the second image based on the score fusion for all the frequency bands.

5. The method of claim 1, wherein:

the characteristics of the first sensor include a resolution of the first sensor; and

the characteristics of the second sensor include a resolution of the second sensor.

6. The method of claim 1, wherein:

the image quality of the first image includes an amount of blur in the first image and an amount of dilation in the iris in the first image; and

the image quality of the second image includes an amount of blur in the second image and an amount of dilation in the iris in the second image.

7. A computing device for cross-sensor iris matching, comprising:

a memory; and

a processor configured to execute executable instructions stored in the memory to;

account for a difference between characteristics of a first sensor and characteristics of a second sensor;

account for a difference between image quality of a first image of an iris captured using a first sensor and image quality of a second image of an iris captured using a second sensor, and

determine whether the iris in the first image matches the iris in the second image after accounting for the difference between the characteristics of the first and second sensor and the difference between the image quality of the first and second image.

8. The computing device of claim 7, wherein accounting for the difference between characteristics of the first sensor and characteristics of the second sensor includes:

determining a modulation transfer function of the first sensor;

determining a modulation transfer function of the second sensor; and

transforming the first image and the second image such that the transformation corresponds to matching the modulation transfer function of the first sensor and the modulation transfer function of the second sensor.

9. The computing device of claim 8, wherein:

determining the modulation transfer function of the first sensor includes capturing a plurality of images of a calibration target using the first sensor; and

determining the modulation transfer function of the second sensor includes capturing a plurality of images of the calibration target using the second sensor.

10. The computing device of claim 8, wherein transforming the first image and the second image includes blurring and/or sharpening the first image in different frequency bands of the first sensor and/or the second image in corresponding frequency bands of the second sensor.

11. The computing device of claim 8, wherein transforming the first image and the second image includes:

dividing the first image and the second image into a plurality of corresponding frequency bands; and

matching the first image and the second image over a single one of the frequency bands.

12. The computing device of claim 11, wherein transforming the first image and the second image includes:

generating an iris template for each of the frequency bands;

defining a weight for each of the frequency bands; and

matching the set of iris templates of the first image and the set of iris templates of the second image over different frequency bands using a particular defined weight for each of the frequency bands.

13. The computing device of claim 12, wherein the weight for each respective frequency band depends on:

a difference between the modulation transfer function of the first sensor and the modulation transfer function of the second sensor over that respective frequency band; and

image quality metrics, including blur, over that respective frequency band.

14. A system for cross-sensor iris matching, comprising:

a first sensor configured to capture a first image of an iris;

a second sensor configured to capture a second image of an iris; and

a computing device configured to determine whether the iris in the first image matches the iris in the second image based on;

optical characteristics of the first sensor and the second sensor; and

image quality of the first image and the second image.

15. The system of claim 14, wherein the computing device is configured to:

divide the first image and the second image into a plurality of frequency bands;

produce a plurality of iris templates from the first image and the second image for each frequency band; and

determine a plurality of distances between the first image and the second image, wherein each distance corresponds to a different one of the plurality of frequency bands.

16. The system of claim 15, wherein the computing device is configured to determine whether the iris in the first image matches the iris in the second image based on the distances between the first image and the second image.

17. The system of claim 15, wherein the computing device is configured to fuse the distances between the first image and the second image using the image quality of the first image and the second image.

18. The system of claim 17, wherein the computing device is configured to:

determine a weight for each of the frequency bands, wherein the weight for each respective frequency band is based on;

a difference between a modulation transfer function of the first sensor and a modulation transfer function of the second sensor over that respective frequency band; and

the image quality of the first image and second image, including blur, over that respective frequency band; and

fuse the distances between the first image and the second image by merging the weights.

19. The system of claim 15, wherein the computing device is configured to fuse the distances between the first image and the second image using a mixture of local experts method.

20. The system of claim 15, wherein the computing device is configured to apply a weight to the distances between the first image and the second image in different frequency bands, wherein the weight depends on an amount of content in the first image and the second image.