Method and apparatus for enrollment and authentication of biometric images

• US 6,993,166 B2
• Filed: 05/03/2004
• Issued: 01/31/2006
• Est. Priority Date: 12/16/2003
• Status: Expired due to Fees

• Current Assignee: Motorola, Inc. (Motorola Solutions, Inc.)
• Original Assignee: Motorola, Inc. (Motorola Solutions, Inc.)
• Inventors: Lo, Peter Z., Bavarian, Behnam
• Primary Examiner(s): Miriam, Daniel
• Assistant Examiner(s): MISTRY, O NEAL RAJAN
• Application Number:
  US10/838,617
• Publication Number:
  US 20050129290A1
• Time in Patent Office: 638 Days
• Field of Search: 382/124, 382/125, 382/115, 382/116, 382/209, 382/218, 382/270, 358/3.22
• US Class Current: 382/124
• CPC Class Codes: G06V 10/993 Evaluation of the quality of the acquired pattern
• CPC Class Codes: G06V 40/1347 Preprocessing; Feature extraction
• CPC Class Codes: G06V 40/168 Feature extraction; Face representation

Abstract

A method for enrolling biometric images including the steps of: a) capturing (310) a plurality of images for a user into a capture folder; b) selecting (318) one of the plurality of images in the capture folder and removing the selected image from the capture folder to an enroll folder; c) comparing (322) the selected image to each of the remaining images in the capture folder to generate a corresponding similarity score for each of the remaining images; d) determining (326) whether any of the corresponding similarity scores are at least equal to a predetermined score threshold, and removing each image having a corresponding similarity score at least equal to the predetermined score threshold from the capture folder to a delete folder (330); and e) determining (334) whether there is at least one image in the capture folder and if so repeating steps b) through d).

Claims

1. A method for enrolling biometric images comprising the steps of:

a) capturing a plurality of images for a user into a capture folder;

b) selecting one of the plurality of images in said capture folder and removing said selected image from the capture folder to an enroll folder;

c) comparing the selected image to each of the remaining images in the capture folder to generate a corresponding similarity score for each of the remaining images;

d) determining whether any of the corresponding similarity scores are at least equal to a predetermined score threshold, and removing each said image having a corresponding similarity score at least equal to the predetermined score threshold from the capture folder to a delete folder; and

e) determining whether there is at least one remaining image in the capture folder and if so selecting one of the remaining images and removing it to the enroll folder and repeating steps c) and d), wherein the enroll folder comprises at least two images that are dissimilar based on the predetermined score threshold, and the images in the enroll folder are used during a verification process.

2. The method of claim 1 further comprising the step of extracting corresponding matching features from each of the images in said capture folder and storing said corresponding matching features in said capture folder with said images.

3. The method of claim 2, wherein said selected image is compared to the remaining images in said capture folder by comparing the matching features of said selected image to the matching features of each of the remaining images in said capture folder.

4. The method of claim 3, wherein said matching features are minutiae, and the corresponding minutiae of said selected image are compared with the corresponding minutiae of each of the remaining images in said capture folder using a minutiae matcher processor.

5. The method of claim 2, wherein each of the images in said enroll folder is stored with its corresponding matching features, and each of the images in said delete folder is stored with its corresponding matching features.

6. The method of claim 1, wherein the selected image is compared with each of the remaining images in said capture folder using a matcher processor.

7. The method of claim 6, wherein said score threshold is a function of at least one characteristic of said matcher processor.

8. The method of claim 7, wherein said score threshold is selected to be at least equal to a minimum threshold for said matcher processor and no greater than a maximum threshold for said matcher processor.

9. The method of claim 8, wherein said minimum threshold is the point of zero false non match rate (FNMR) on a distribution curve for mated images, and said maximum threshold is the point of zero false match rate (FMR) on a distribution curve for non-mated images.

10. The method of claim 9, wherein said score threshold is an equal error rate point between said point of zero FMR and said point of zero FNMR.

11. The method of claim 1, wherein said plurality of images are captured in said capture folder as a function of a predetermined quality threshold.

12. The method of claim 11, wherein said quality threshold is determined based on valid ridge flow direction distribution between rejected prints and accepted prints in a fingerprint identification system.

13. The method of claim 11, wherein said step of capturing said plurality of images into a capture folder comprises the steps of:

i) capturing an image;

ii) determining whether the quality of said captured image is at least equal to said predetermined quality threshold; and

iii) enrolling the captured image in said capture folder its quality is at least equal to said predetermined quality threshold.

14. The method of claim 13, wherein a predetermined number of images are captured into said capture folder.

15. The method of claim 14, wherein steps i) through iii) are repeated until said capture folder includes said predetermined number of images.

16. The method of claim 14, wherein said step of capturing said plurality of images into a capture folder further comprises the steps of:

iv) placing the captured image into a temporary folder if its quality is less than said predetermined quality threshold; and

v) determining whether a predetermined maximum number of capture attempts has been reached and whether said capture folder includes said predetermined number of images, and

returning to step i) if the capture folder does not include said predetermined number of images and said predetermined maximum number of capture attempts has not been reached; and

selecting images from said temporary folder and placing them into said capture folder until said capture folder includes said predetermined number of images if said predetermined maximum number of capture attempts has been reached.

17. The method of claim 1, wherein said method is used for enrolling at least one of the set of:

fingerprint images, palm print images and facial images.

18. A method for determining a verification threshold for a user based on comparing one or more images in a delete folder with a plurality of images in an enroll folder, said delete and enroll folders generated as in claim 1, said method comprising the steps of:

a) selecting one image from said delete folder;

b) comparing said selected image with each image in said enroll folder and generating a corresponding similarity score for each said comparison;

c) selecting the highest similarity score from said corresponding similarity scores;

d) repeating steps a), b) and c) until each image in said delete folder has been compared with each image in said enroll folder;

e) selecting the minimum score of all of the highest similarity scores selected in step c); and

f) determining said user verification threshold as a function of said minimum score, the user verification threshold for comparing an image of the user to the images in the enroll folder during a verification process.

19. The method of claim 18, wherein said user verification threshold is equal to said minimum score.

20. The method of claim 18 further comprising the step of granting or denying the user access to a system based on the user'"'"'s verification threshold.

21. The method of claim 18, wherein the selected image is compared with each of the images in said enroll folder using a matcher processor.

22. The method of claim 21, wherein said user verification threshold is further a function of at least one characteristic of said matcher processor.

23. The method of claim 22, wherein said user verification threshold is selected to be at least equal to a minimum threshold for said matcher processor and no greater than a maximum threshold for said matcher processor.

24. The method of claim 23, wherein said user verification threshold is determined in accordance with an algorithm such that:

said user verification threshold is selected to be said minimum threshold if said minimum score is less than said minimum threshold;

said user verification threshold is selected to be said minimum score if said minimum score is between said minimum threshold and said maximum threshold; and

said user verification threshold is selected to be said maximum threshold if said minimum score is greater than said maximum threshold.

25. A method for enrolling biometric images comprising the steps of:

a) capturing a plurality of images for a user into a capture folder;

b) extracting corresponding matching features from each of the images in said capture folder and storing said corresponding matching features in said capture folder with said images;

c) selecting one of the plurality of images in said capture folder and removing said selected image and its corresponding matching features from the capture folder to an enroll folder;

d) comparing the matching features of the selected image to the matching features of each of the remaining images in the capture folder to generate a corresponding similarity score for each of the remaining images;

e) determining whether any of the corresponding similarity scores are at least equal to a predetermined score threshold and removing each said image, and its corresponding matching features, having a corresponding similarity score at least equal to the predetermined score threshold from the capture folder to a delete folder; and

f) determining whether there is at least one remaining image in the capture folder and if so selecting one of the remaining images and removing it to the enroll folder and repeating steps c) and d), wherein the enroll folder comprises at least two images that are dissimilar based on the predetermined score threshold, and the images in the enroll folder are used during a verification process.

26. A system for biometric image enrollment and verification comprising:

a) means for capturing a plurality of images for a user into a capture folder;

b) means for selecting one of the plurality of images in said capture folder and removing said selected image from the capture folder to an enroll folder;

c) means for comparing the selected image to each of the remaining images in the capture folder to generate a corresponding similarity score for each of the remaining images;

d) means for determining whether any of the corresponding similarity scores are at least equal to a predetermined score threshold, and removing each said image having a corresponding similarity score at least equal to the predetermined score threshold from the capture folder to a delete folder;

e) means for determining whether there is at least one remaining image in the capture folder and if so selecting one of the remaining images and removing it to the enroll folder and repeating steps c) and d), wherein the enroll folder comprises at least two images that are dissimilar based on the predetermined score threshold, and the images in the enroll folder are used during a verification process

f) means for determining a verification threshold for said user based on comparing each image in said delete folder with each image in said enroll folder;

g) means for capturing at least one image from said user for use as a search image;

h) means for comparing said at least one search image to each image in said enroll folder and generating corresponding similarity scores for each of the images in the enroll folder; and

i) means for determining whether at least one corresponding similarity score generated in step h) is at least equal to said user verification threshold and if so granting the user access to a system.

27. The system of claim 26, wherein said system is used for enrollment and verification for at least one of the set of:

fingerprint images, palm print images and facial images.