Method and apparatus for providing a robust object finder

• US 7,599,524 B2
• Filed: 04/05/2004
• Issued: 10/06/2009
• Est. Priority Date: 04/04/2003
• Status: Active Grant

• Current Assignee: Princeton Identity Inc.
• Original Assignee: Sarnoff Corporation (SRI International, Inc.)
• Inventors: Wildes, Richard, Camus, Theodore A.
• Primary Examiner(s): Johns; Andrew W
• Assistant Examiner(s): Thomas; Mia M
• Application Number:
  US10/818,307
• Publication Number:
  US 20040197011A1
• Time in Patent Office: 2,010 Days
• Field of Search: None
• US Class Current: 382/117
• CPC Class Codes: G06V 40/18 Eye characteristics, e.g. of the iris

Abstract

A method of quickly and robustly localizing a pair of concentric circular region boundaries in a digital image, such as the pupil and iris boundaries in an image of a human eye is disclosed. Specularities in the image are optionally filled. An object containing concentric regions, e.g., a pupil and iris, is found within the image.

Claims

1. A computer-implemented method of finding an object within an image, comprising:

locating, by an object module, a plurality of candidate objects in the image;

modeling, by a processing module, each candidate object as a first concentric region and a second concentric region;

performing, by the processing module, boundary fitting on the plurality of candidate objects, wherein performing boundary fitting on the plurality of candidate objects further comprises;

configuring a plurality of rays into a rectangular representation for each candidate object and computing for each candidate object a first boundary and a second boundary in order to determine a quality measure of each candidate object, wherein said computing comprises estimating the first boundary from said rectangular representation, said first boundary corresponds to the first concentric region and estimating a second boundary from said rectangular representation, said second boundary corresponds to the second concentric region; and

selecting, by the processing module, the object from the plurality of candidate objects in accordance with the quality measure.

2. The method of claim 1, wherein the plurality of rays radiate from a proposed center of each canidate.

3. The method of claim 2, wherein the plurality of rays represent pixel lines.

4. The method of claim 1, wherein selecting by the processing module the object from the plurality of candidate objects further comprises selecting the candidate object having a maximum quality measure.

5. The method of claim 1 further comprising filling in at least one specularity in the image.

6. The method of claim 1 wherein said performing boundary fitting comprises performing a gradient search on the plurality of candidate objects, using the quality measure, until a local maximum is reached.

7. The method of claim 1, wherein at least one of the first concentric region and second concentric region is modeled as an ellipse.

8. The method of claim 7 wherein said ellipse is a circle.

9. The method of claim 1 further comprising performing pyramid processing on the image in order to reproduce the image in a plurality of resolutions.

10. The method of claim of claim 1, further comprising performing fit optimization on the selected object in a higher resolution image.

11. The method of claim 1 wherein said plurality of rays represent the first concentric region and the second concentric region.

12. The method of claim 1 wherein said plurality of rays comprise a first set of rays and a second set of rays such that the first set of rays represent the first concentric region and the second set of rays represent the second concentric region.

13. A computer-readable medium having stored thereon a plurality of instructions for finding an object within an image, the plurality of instructions including instructions which:

locate a plurality of candidate objects in the image;

model each candidate object as a first concentric region and a second concentric region;

perform boundary fitting on the plurality of candidate objects, wherein performing boundary fitting on the plurality of candidate objects further comprises;

configuring a plurality of rays into a rectangular representation for each candidate object and computing for each candidate object a first boundary and a second boundary in order to determine a quality measure of each candidate object, wherein said computing comprises estimating the first boundary from said rectangular representation, said first boundary corresponds to the first concentric region and estimating a second boundary from said rectangular representation, said second boundary corresponds to the second concentric region; and

select the object from the plurality of candidate objects in accordance with the quality measure.

14. The computer-readable medium of claim 13 wherein said plurality of rays comprise a first set of rays and a second set of rays such that the first set of rays represent the first concentric region and the second set of rays represent the second concentric region.

15. A device for finding an object within an image, comprising:

means for locating a plurality of candidate objects in the image;

means for modeling each candidate object as a first concentric region and a second concentric region;

means for performing boundary fitting on the plurality of candidate objects, wherein means for performing boundary fitting further comprises;

means for configuring a plurality of rays into a rectangular representation for each candidate object; and

means for computing for each candidate a first boundary and a second boundary in order to determine a quality measure of each candidate object, wherein said means for computing further comprises means for estimating the first boundary from said rectangular representation, said first boundary corresponds to the first concentric region and means for estimating a second boundary from said rectangular representation, said second boundary corresponds to the second concentric region; and

means for selecting the object from the plurality of candidate objects in accordance with the quality measure.

16. The device of claim 15 wherein said plurality of rays comprise a first set of rays and a second set of rays such that the first set of rays represent the first concentric region and the second set of rays represent the second concentric region.