System and method for animal identification using IRIS images

• US 8,189,879 B2
• Filed: 02/13/2009
• Issued: 05/29/2012
• Est. Priority Date: 02/14/2008
• Status: Active Grant

• Current Assignee: Iristrac LLC
• Original Assignee: Iristrac LLC
• Inventors: Cambier, James L.
• Primary Examiner(s): Bhatnagar, Anand
• Application Number:
  US12/370,952
• Publication Number:
  US 20090208064A1
• Time in Patent Office: 1,201 Days
• Field of Search: 382/100, 382/115, 382/117, 382/118, 382209-222, 382/181, 382/190, 382/195, 351/200, 351/206, 340 58- 586, 340/4, 726/2
• US Class Current: 382/117
• CPC Class Codes: G06V 40/193 Preprocessing; Feature extraction

Abstract

A system for animal identification includes: an image capture apparatus for obtaining an image of an eye of an animal including a pupil region and an iris region; and a template generation apparatus. The template generation apparatus is for: extracting a set of pixel data from the image, the set of pixel data representing an upper region of interest of the iris region above the pupil region and a lower region of interest of the iris region below the pupil region, the upper region of interest and the lower region of interest have parallel side boundaries that are spaced apart a distance that is substantially independent of a degree of dilation of the pupil region; and transforming the set of pixel data representing the upper region of interest and the lower region of interest into a template of the upper region of interest and the lower region of interest.

Claims

1. A method for animal identification, comprising:

obtaining an image of an eye of an animal including a pupil region and an iris region;

extracting a set of pixel data from the image, the set of pixel data representing a region of interest of the iris region of the eye; and

transforming the set of pixel data representing the region of interest of the iris region of the eye into a template of the region of interest of the iris region of the eye, the template for use in identifying the animal;

generating a plurality of comparison templates by;

applying a plurality of scale factors to the set of pixel data representing the region of interest of the iris region of the eye to generate a plurality of re-sampled sets of pixel data representing the region of interest of the iris region of the eye; and

generating a comparison template from each of the plurality of re-sampled sets of pixel data representing the region of interest of the iris region of the eye;

determining a match score value for each comparison template by comparing each comparison template to a previously enrolled template of an eye of a previously identified animal; and

determining whether the eye of the animal matches the eye of the previously identified animal by comparing at least one of the match score values to a match threshold value.

2. The method of claim 1, wherein the image of the eye includes a pupil having an irregular boundary, and wherein the method further comprises:

determining the irregular boundary of the pupil;

constructing a convex hull of the irregular boundary of the pupil; and

using the convex hull of the irregular boundary of the pupil as a boundary of the pupil region in all subsequent operations.

3. The method of claim 2, further comprising performing successive image morphological closing operations on an area within the boundary of the pupil region until an Euler number representation of the pupil region is equal to one to eliminate internal holes in the pupil region.

4. The method of claim 1, wherein transforming the set of pixel data comprises:

processing the set of pixel data from the image using log-Gabor wavelets in a complex transformation to produce phase information for each pixel of the set of pixel data; and

encoding the phase information for each pixel of the set of pixel data as a two bit value for each pixel to produce a template that provides a compact representation of iris texture features.

5. The method of claim 1, further comprising:

detecting, if present, areas not to be used for matching purposes in each of the plurality of re-sampled sets of pixel data;

generating a comparison mask image of the areas not to be used for matching purposes from each of the plurality of re-sampled sets of pixel data; and

using each comparison mask image and a previously enrolled mask image of the eye of the previously identified animal to select elements of each comparison template and the previously enrolled template that will contribute to the match score value.

6. A system for animal identification, comprising:

an image capture apparatus for obtaining an image of an eye of an animal including a pupil region and an iris region; and

a template generation apparatus for;

extracting a set of pixel data from the image, the set of pixel data representing a region of interest of the iris region of the eye; and

transforming the set of pixel data representing the region of interest of the iris region of the eye into a template of the region of interest of the iris region of the eye, the template for use in identifying the animal;

an enrollment database in communication with the template generation apparatus for;

receiving from the template generation apparatus the template of the region of interest of the iris region of the eye; and

storing the template of the region of interest of the iris region of the eye along with information that includes an identifier for the animal; and

a variable-scale matching apparatus in communication with the template generation apparatus and the enrollment database for;

generating a plurality of comparison templates by;

applying a plurality of scale factors to the set of pixel data representing the region of interest of the iris region of the eye to generate a plurality of re-sampled sets of pixel data representing the region of interest of the iris region of the eye; and

generating a comparison template from each of the plurality of re-sampled sets of pixel data representing the region of interest of the iris region of the eye;

determining a match score value for each comparison template by comparing each comparison template to a previously enrolled template of an eye of a previously identified animal retrieved from the enrollment database; and

determining whether the eye of the animal matches the eye of the previously identified animal by comparing at least one of the match score values to a match threshold value.

7. The system of claim 6, wherein the image of the eye includes a pupil having an irregular boundary, and wherein the template generation apparatus is further for:

determining the irregular boundary of the pupil;

constructing a convex hull of the irregular boundary of the pupil; and

using the convex hull of the irregular boundary of the pupil as a boundary of the pupil region in all subsequent operations.

8. The system of claim 7, wherein the template generation apparatus is further for performing successive image morphological closing operations on an area within the boundary of the pupil region until an Euler number representation of the pupil region is equal to one to eliminate internal holes in the pupil region.

9. The system of claim 6, wherein the template generation apparatus is further for:

processing the set of pixel data from the image using log-Gabor wavelets in a complex transformation to produce phase information for each pixel of the set of pixel data; and

encoding the phase information for each pixel of the set of pixel data as a two bit value for each pixel to produce a template that provides a compact representation of iris texture features.

10. The system of claim 6, wherein the template generation apparatus is further for:

detecting, if present, areas not to be used for matching purposes in each of the plurality of re-sampled sets of pixel data;

generating a comparison mask image of the areas not to be used for matching purposes from each of the plurality of re-sampled sets of pixel data; and

using each comparison mask image and a previously enrolled mask image of the eye of the previously identified animal to select elements of each comparison template and the previously enrolled template that will contribute to the match score value.

11. A method for animal identification, comprising:

obtaining an image of an eye of an animal including a pupil region and an iris region;

extracting a set of pixel data from the image; and

transforming the set of pixel data into a template, the template for use in identifying the animal;

generating a plurality of comparison templates by;

applying a plurality of scale factors to the set of pixel data to generate a plurality of re-sampled sets of pixel data; and

generating a comparison template from each of the plurality of re-sampled sets of pixel data;

determining a match score value for each comparison template by comparing each comparison template to a previously enrolled template of an eye of a previously identified animal; and

determining whether the eye of the animal matches the eye of the previously identified animal by comparing at least one of the match score values to a match threshold value.

12. The method of claim 11, wherein the image of the eye includes a pupil having an irregular boundary, and wherein the method further comprises:

determining the irregular boundary of the pupil;

constructing a convex hull of the irregular boundary of the pupil; and

using the convex hull of the irregular boundary of the pupil as a boundary of the pupil region in all subsequent operations.

13. The method of claim 12, further comprising performing successive image morphological closing operations on an area within the boundary of the pupil region until an Euler number representation of the pupil region is equal to one to eliminate internal holes in the pupil region.

14. The method of claim 11, wherein transforming the set of pixel data comprises:

processing the set of pixel data from the image using log-Gabor wavelets in a complex transformation to produce phase information for each pixel of the set of pixel data; and

encoding the phase information for each pixel of the set of pixel data as a two bit value for each pixel to produce a template that provides a compact representation of iris texture features.

15. The method of claim 11, further comprising:

detecting, if present, areas not to be used for matching purposes in each of the plurality of re-sampled sets of pixel data;

generating a comparison mask image of the areas not to be used for matching purposes from each of the plurality of re-sampled sets of pixel data; and

using each comparison mask image and a previously enrolled mask image of the eye of the previously identified animal to select elements of each comparison template and the previously enrolled template that will contribute to the match score value.

16. A system for animal identification, comprising:

an image capture apparatus for obtaining an image of an eye of an animal including a pupil region and an iris region; and

a template generation apparatus for;

extracting a set of pixel data from the image; and

transforming the set of pixel data into a template for use in identifying the animal;

an enrollment database in communication with the template generation apparatus for;

receiving from the template generation apparatus the template; and

storing the template along with information that includes an identifier for the animal; and

a variable-scale matching apparatus in communication with the template generation apparatus and the enrollment database for;

generating a plurality of comparison templates by;

applying a plurality of scale factors to the set of pixel data to generate a plurality of re-sampled sets of pixel data; and

generating a comparison template from each of the plurality of re-sampled sets of pixel data;

determining a match score value for each comparison template by comparing each comparison template to a previously enrolled template of an eye of a previously identified animal retrieved from the enrollment database; and

determining whether the eye of the animal matches the eye of the previously identified animal by comparing at least one of the match score values to a match threshold value.

17. The system of claim 16, wherein the image of the eye includes a pupil having an irregular boundary, and wherein the template generation apparatus is further for:

determining the irregular boundary of the pupil;

constructing a convex hull of the irregular boundary of the pupil; and

using the convex hull of the irregular boundary of the pupil as a boundary of the pupil region in all subsequent operations.

18. The system of claim 17, wherein the template generation apparatus is further for performing successive image morphological closing operations on an area within the boundary of the pupil region until an Euler number representation of the pupil region is equal to one to eliminate internal holes in the pupil region.

19. The system of claim 16, wherein the template generation apparatus is further for:

processing the set of pixel data from the image using log-Gabor wavelets in a complex transformation to produce phase information for each pixel of the set of pixel data; and

encoding the phase information for each pixel of the set of pixel data as a two bit value for each pixel to produce a template that provides a compact representation of iris texture features.

20. The system of claim 16, wherein the template generation apparatus is further for:

detecting, if present, areas not to be used for matching purposes in each of the plurality of re-sampled sets of pixel data;

generating a comparison mask image of the areas not to be used for matching purposes from each of the plurality of re-sampled sets of pixel data; and

using each comparison mask image and a previously enrolled mask image of the eye of the previously identified animal to select elements of each comparison template and the previously enrolled template that will contribute to the match score value.