Method of normalizing a digital image of an iris of an eye

• US 8,755,607 B2
• Filed: 04/28/2011
• Issued: 06/17/2014
• 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): Repko, Jason M
• Assistant Examiner(s): Potts, Ryan P
• Application Number:
  US13/096,728
• Publication Number:
  US 20120275707A1
• Time in Patent Office: 1,146 Days
• Field of Search: None
• US Class Current: 382/199
• CPC Class Codes: G06V 40/18 Eye characteristics, e.g. of the iris

Abstract

A method of normalizing a digital image of an iris of an eye for the purpose of creating an iris code for identification of vertebrates, including humans, the method comprising the steps of:

• • determining a pupil region in the image as a convex region having a boundary that can only be described by more than five independent parameters;
  • determining, in the image, an outer boundary of the iris; and
  • transforming an image of a ring shaped iris region that surrounds the pupil region into a coordinate system in which each point of the iris region is described by a first coordinate that indicates the position of the point along the boundary of the pupil and a second coordinate that indicates the distance of the point from said boundary, said second coordinate having a constant value when the point is located on the outer boundary of the iris.

Claims

1. A method of normalizing a digital image of an iris of an eye of a vertebrate, including a human vertebrate, for the purpose of creating an iris code for use in the identification of the vertebrate, the method comprising the steps of:

determining a pupil region in the image as a convex region having a boundary that can only be described by more than five independent parameters;

determining, in the image, an outer boundary of the iris; and

transforming an image of a ring shaped iris region that surrounds the pupil region into a coordinate system in which each point of the iris region is described by a first coordinate that indicates the position of the point along the boundary of the pupil and a second coordinate that indicates the distance of the point from said boundary, said second coordinate having a constant value when the point is located on the outer boundary of the iris.

2. The method according to claim 1, wherein said coordinate system is established by drawing a sequence of non-intersecting spokes from the boundary of the pupil to the outer boundary of the iris such that a spoke passes through each pixel of said ring shaped iris region, sequentially numbering the spokes, and setting the first coordinate of each pixel to the spoke number of the spoke passing through the pixel.

3. The method according to claim 2, wherein each spoke is normal to the boundary of the pupil at the point where the spoke meets that boundary.

4. The method according to claim 3, for an eye having an elongated pupil, wherein the outer boundary of the iris is determined by first erecting the spokes on the boundary of the pupil and then connecting outer end points of the spokes, wherein all the spokes have the same length and this length is calculated by:

setting a fixed number that represents, for a given species of vertebrates, a known standard dimension of the outer boundary of the iris in a first direction normal to a second direction of largest elongation of the pupil,

subtracting the dimension of the boundary of the pupil region in said first direction from said fixed number, and

dividing the difference by two.

5. The method according to claim 4, comprising a step of measuring a distance between the eye and a camera with which the digital image is captured, and a step of scaling the intensity 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.

6. The method according to claim 1, for an eye having an elongated pupil, wherein the outer boundary of the iris is determined by placing an oval with a fixed shape and a fixed size into the image such that the oval is centered on the pupil area and has a large axis coinciding with the direction of largest elongation of the pupil.

7. The method according to claim 6, comprising a step of measuring a distance between the eye and a camera with which the digital image is captured, and a step of scaling the intensity 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.

8. The method according to claim 1, wherein the boundary of the pupil region is a polygon approximating a smooth closed curve.

9. A method of creating a binary iris code from image data of an eye of a vertebrate, including a human vertebrate, the method comprising:

normalizing a digital image of an iris of the eye, wherein the normalizing step comprises determining a pupil region in the image as a convex region having a boundary that can only be described by more than five independent parameters, determining an outer boundary of the iris in the image, and transforming an image of a ring shaped iris region that surrounds the pupil region into a coordinate system in which each point of the iris region is described by a first coordinate that indicates the position of the point along the boundary of the pupil and a second coordinate that indicates the distance of the point from said outer boundary, said second coordinate having a constant value when the point is located on the outer boundary of the iris; and

filtering the digital image of the iris to produce the iris code, wherein the iris code is a compressed representation of the digital image.

10. The method according to claim 9, further comprising:

creating a data record in a database, wherein the data record includes the iris code and identification information for the vertebrate.

11. A method of identifying an individual by one of their eyes comprising checking an iris binary code of an eye of the individual against a plurality of binary iris codes in a data record stored on a machine readable data carrier;

wherein the individual is identified when said checking results in at least one pair of matching binary iris codes;

wherein said binary iris code of the eye of said individual was created with the method of creating of claim 10;

wherein said data record includes a plurality of binary iris codes for the same eye, which were obtained by said method of creating; and

wherein said binary iris codes are obtained by normalization procedures that differ in a dimension of the outer boundary of the iris as determined in the image.

12. 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 and software and hardware suitable for carrying out the method according to claim 10, and a database storing data records;

and wherein each data record is stored on a machine readable data carrier and includes a binary iris code obtained with said method.

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 and software and hardware suitable for carrying out the method according to claim 10, and a database storing data records on a machine readable data carrier;

wherein said data record includes a binary iris code obtained with said method;

wherein the data record includes a plurality of binary iris codes for the same eye; and

wherein said binary iris codes are obtained by normalization procedures that differ in a dimension of the outer boundary of the iris as determined in the image.

14. The method according to claim 9 further comprising:

repeating the normalizing step for a plurality of values of the outer boundaries of the iris.

15. A kit for creating a binary iris code from image data of an eye of a vertebrate, including a human vertebrate, comprising:

a camera, wherein the camera generates a digital image of an iris of the eye; and

a processing module, wherein the module creates the iris code from the digital image according to the method of claim 9.