Method of capturing image data for iris code based identification of vertebrates

• US 8,854,446 B2
• Filed: 04/28/2011
• Issued: 10/07/2014
• Est. Priority Date: 04/28/2011
• Status: Active Grant

• Current Assignee: Iristrac LLC, Princeton Identity Inc.
• Original Assignee: Iristrac LLC, SRI International, Inc.
• Inventors: Bergen, James Russell, Naroditsky, Oleg
• Primary Examiner(s): Kim, Hee-Yong
• Application Number:
  US13/096,724
• Publication Number:
  US 20120274756A1
• Time in Patent Office: 1,258 Days
• Field of Search: 348/78
• US Class Current: 348/78
• CPC Class Codes: G06V 40/19 Sensors therefor

Abstract

A method of capturing image data for iris code based identification of vertebrates, including humans, comprises the steps of:

• • recording a digital image of an eye with a camera equipped with at least two light sources that have a fixed spatial relationship to an object lens of the camera;
  • locating the eye in the digital image by detecting a specularity pattern that is created by reflection of light from said at least two light sources at a cornea of the eye; and
  • calculating information on the position of the camera relative to the eye on the basis of said fixed spatial relationship between the light sources and the object lens and on the basis of said specularity pattern.

Claims

1. A method of capturing image data for iris code based identification of vertebrates, including humans, the method comprising the steps of:

recording a digital image of an eye with a camera equipped with at least two light sources that have a fixed spatial relationship to an object lens of the camera;

locating the eye in the digital image by detecting a specularity pattern that is created by reflection of light from said at least two light sources at a cornea of the eye; and

calculating information on the position of the camera relative to the eye on the basis of said fixed spatial relationship between the light sources and the object lens and on the basis of said specularity pattern.

2. The method according to claim 1, wherein said information on the position of the camera includes information on the distance between the camera and the eye.

3. The method according to claim 2, wherein said information on the distance between the camera and the eye is used for scaling the digital image in proportion to the distance between the camera and the eye, such that dimensions of a detail in the image of the eye indicate the corresponding true dimensions of the detail in the real eye.

4. The method according to claim 3, wherein a known dimension of an outer boundary of an iris of the eye of a given species of vertebrates is used for constructing an imaginary iris boundary in the digital image, and said imaginary boundary is used for transforming the digital image into a normalized iris image that is insensitive to variations in a dimension of a pupil of the eye.

5. The method according to claim 1, wherein a point designating a center of the eye is detected in the image, and said information on the position of the camera includes information on a deviation of the camera from a straight line that passes through the center of the eye and is normal to a pupil of the eye, said information being calculated on the basis of an offset between the specularity pattern and the point designating the center of the eye.

6. The method according to claim 5, comprising a step of delineating a pupil boundary in the digital image, said point designating the center of the eye being detected by reference to the pupil boundary.

7. The method according to claim 1, comprising a step of checking whether the position of the camera relative to the eye is within a predetermined range of positions.

8. The method according to claim 7, wherein the digital image is recorded in a video mode, with continued calculation of the actual position of the camera relative to the eye, and the camera is enabled to save the digital image when it is found that the position of the camera is within said predetermined range.

9. A method of creating a binary iris code from image data of an eye of a vertebrate, including humans, using the method of claim 1 for capturing the image data.

10. A data record stored on a non-transitory machine readable storage medium, said data record including a binary iris code obtained with the method according to claim 9.

11. An iris code generation kit comprising a camera equipped with at least two light sources that have a fixed spatial relationship to an object lens of the camera, and software and hardware suitable for carrying out the method according to claim 1.

12. The kit according to claim 11, wherein the camera comprises two light sources disposed symmetrically on opposite sides of the object lens.

13. An identification system for identifying vertebrates, including humans, on the basis of an iris code match, comprising at least one iris code generation kit comprising a camera equipped with at least two light sources that have a fixed spatial relationship to an object lens of the camera, and software and hardware suitable for carrying out the method according to claim 1, and a database storing data records, wherein each data record is stored on a non-transient machine readable data carrier and includes a binary iris code obtained with said method.