SYSTEM AND METHOD FOR 3D IRIS RECOGNITION

• US 20150347841A1
• Filed: 05/27/2015
• Published: 12/03/2015
• Est. Priority Date: 05/30/2014
• Status: Active Grant

• Current Assignee: Leidos Innovations Technology, Inc.
• Original Assignee: Lockheed Martin Corporation (Martin Marietta Corporation)
• Inventors: MEARS, John C.
• Granted Patent: US 9,934,436 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06V 40/19 Sensors therefor
• CPC Class Codes: G06V 40/193 Preprocessing; Feature extraction
• 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

Aspects of the disclosure provide an iris recognition system. The iris recognition system can include a three-dimensional (3D) sensor that is configured to capture a 3D image of an iris, an iris feature extractor that is configured to generate an iris template based on the 3D image of the iris, and a memory that is configured to store the iris template.

Claims

1. An iris recognition system, comprising:

a three-dimensional (3D) sensor that is configured to capture a 3D image of an iris;

an iris feature extractor that is configured to generate an iris template based on the 3D image of the iris; and

a memory that is configured to store the iris template.

2. The iris recognition system of claim 1, further comprising:

an iris comparator that is configured to compare a query iris template against a stored iris template to generate an iris match score.

3. The iris recognition system of claim 2, further comprising:

an iris database that is configured to store a plurality of iris templates.

4. The iris recognition system of claim 1, wherein the 3D sensor is further configured to capture a 3D image of a face and an iris.

5. The iris recognition system of claim 4, further comprising:

an illuminator that is configured to provide illumination in a visible or infrared light spectral band for the 3D sensor to capture the 3D image of the face and the iris.

6. The iris recognition system of claim 4, wherein the iris feature extractor is further configured to generate an iris image quality score based on the 3D image of the iris, and the iris recognition system further comprising:

an iris database that is configured to store a plurality of iris templates; and

an iris comparator that is configured to compare a query iris template against the stored iris template to generate an iris match score.

7. The iris recognition system of claim 6, further comprising:

a face recognition subsystem that is configured to perform 3D face recognition, the face recognition subsystem includes;

a face feature extractor that is configured to generate a face image quality score based on the 3D image of the face and perform a feature extraction process to generate a face template;

a face database that is configured to store the face template; and

a face comparator that is configured to compare a query face template against a stored face template to generate a face match score.

8. The iris recognition system of claim 7, further comprising:

a fuser that is configured to fuse the iris match score and the face match score to generate a fusion score.

9. The iris recognition system of claim 8, wherein the fuser is configured to use the iris image quality score and the face image quality score to fuse the iris match score and the face match score to generate a quality-based fusion score.

10. The iris recognition system of claim 1, wherein the 3D sensor is a microlens array light field camera (LFC).

11. A method for three-dimensional (3D) iris recognition, comprising:

capturing a 3D image of an iris with a three-dimensional (3D) sensor;

generating an iris template based on the 3D image of the iris; and

storing the iris template.

12. The method of claim 11, further comprising:

generating an iris match score based on a comparison of a query iris template against a stored iris template.

13. The method of claim 11, further comprising:

storing a plurality of iris templates in an iris database.

14. The method of claim 11, further comprising:

capturing a 3D image of a face and an iris using the 3D sensor.

15. The method of claim 14, further comprising:

providing illumination in a visible light spectral band for the 3D sensor to capture the 3D image of the face and the iris.

16. The method of claim 14, further comprising:

storing a plurality of iris templates in an iris database;

generating an iris image quality score based on the 3D image of the iris; and

comparing a query iris template against the stored iris template to generate an iris match score.

17. The method of claim 16, further comprising:

performing a feature extraction process based on the 3D image of the face to generate a face template; and

generating a face image quality score based on the 3D image of the face.

18. The method of claim 17, further comprising:

storing the face template in a face database; and

comparing a query face template against a stored face template to generate a face match score.

19. The method of claim 18, further comprising:

fusing the iris match score and the face match score to generate a fusion score.

20. The method of claim 19, wherein fusing the iris match score and the face match score includes:

using the iris image quality score and the face image quality score to fuse the iris match score and the face match score to generate a quality-based fusion score.