Biometric authentication technology

• US 9,600,730 B2
• Filed: 10/17/2016
• Issued: 03/21/2017
• Est. Priority Date: 06/07/2011
• Status: Active Grant

• Current Assignee: Accenture Global Services Limited (Accenture PLC)
• Original Assignee: Accenture Global Services Limited (Accenture PLC)
• Inventors: Paul, Sanjoy, Tiwari, Abhinav
• Primary Examiner(s): Rahmjoo, Manuchehr
• Application Number:
  US15/294,897
• Publication Number:
  US 20170032205A1
• Time in Patent Office: 155 Days
• Field of Search: 382/115
• US Class Current: 1/1
• CPC Class Codes: G06F 16/51 Indexing; Data structures therefor; Storage structures
• CPC Class Codes: G06F 21/32 using biometric data, e.g. fingerprints, iris scans or voiceprints
• CPC Class Codes: G06V 40/10 Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
• CPC Class Codes: G06V 40/50 Maintenance of biometric data or enrolment thereof
• CPC Class Codes: G06V 40/70 Multimodal biometrics, e.g. combining information from different biometric modalities

Abstract

Biometric authentication technology, in which biometric data is maintained for a group of people. The biometric data includes sorted similarity scores, where each of the sorted similarity scores is computed to represent similarity between a corresponding biometric image and a reference image. A biometric verification system accesses a biometric image of at least a portion of a person, accesses the reference image, and computes a similarity score that represents similarity between the accessed biometric image and the reference image. The biometric verification system searches the sorted similarity scores included in the biometric data using the computed similarity score and outputs a result based on the searching.

Claims

1. A biometric authentication system comprising:

a data storage system configured to maintain, for a group of multiple, different people, biometric data that includes sorted similarity scores, wherein each similarity score represents a similarity between an image of at least a portion of a corresponding person from the group of multiple, different people and a reference image; and

a biometric enrollment system that includes at least one computer, the biometric enrollment system configured to;

receive a particular image of at least a portion of a particular person;

compute a particular similarity score that represents similarity between the particular image and the reference image used in computing the similarity scores for each person in the group of multiple, different people;

determine, from the similarity scores stored in the data storage system for the reference image, a first similarity score that has a value greater than the particular similarity score without any other similarity scores from the similarity scores stored in the data storage system for the reference image having values between the first similarity score and the particular similarity score;

determine, from the similarity scores stored in the data storage system for the reference image, a second similarity score that has a value less than the particular similarity score without any other similarity scores from the similarity scores stored in the data storage system for the reference image having values between the first similarity score and the second similarity score; and

determine a location in the data storage system at which to store biometric data for the particular person using the first similarity score, the second similarity score, and the particular similarity score as an index in the data storage system; and

store, in the data storage system, the biometric data for the particular person at the location in the data storage system.

2. The biometric authentication system of claim 1, wherein the biometric enrollment system is configured to store, in the data storage system, the biometric data for the particular person at the location in the data storage system by linking the biometric data for the particular person with the particular similarity score.

3. The biometric authentication system of claim 2, wherein the biometric enrollment system is configured to link the biometric data for the particular person with the particular similarity score using a unique identifier for the particular person.

4. The biometric authentication system of claim 1, wherein the biometric enrollment system is configured to store, in the data storage system, the biometric data for the particular person at the location in the data storage system by storing, in the data storage system, the particular image for the particular person at the location in the data storage system.

5. The biometric authentication system of claim 1, wherein the biometric enrollment system is configured to store, in the data storage system, the biometric data for the particular person at the location in the data storage system by storing, in the data storage system, blob data descriptive of the particular image for the particular person at the location in the data storage system.

6. The biometric authentication system of claim 1, wherein the biometric enrollment system is configured to store, in the data storage system, the biometric data for the particular person at the location in the data storage system by storing, in the data storage system, fingerprint data for the particular person or iris data for the particular person at the location in the data storage system.

7. The biometric authentication system of claim 1, wherein:

the biometric enrollment system is configured to;

determine a particular type of biometric data for the particular image from a group of multiple, different biometric types; and

select a particular image as the reference image that has the particular type of biometric data; and

the biometric enrollment system is configured to compute the particular similarity score that represents similarity between the particular image and the reference image used in computing the similarity scores for each person in the group of multiple, different people by computing the particular similarity score that represents similarity between the particular image of the particular type of biometric data and the reference image of the particular type of biometric data.

8. The biometric authentication system of claim 1, wherein the data storage system is configured to maintain, for each person in the group of multiple, different people, an entry in a table that identifies the biometric data for the person.

9. The biometric authentication system of claim 1, wherein the data storage system is configured to maintain, for each person in the group of multiple, different people, an object in an object oriented database that identifies the biometric data for the person.

10. The biometric authentication system of claim 1, wherein the data storage system is configured to maintain, for each person in the group of multiple, different people, an Extensible Mark-up Language file in a database that identifies the biometric data for the person.

11. The biometric authentication system of claim 1, wherein the biometric enrollment system is configured to compute the particular similarity score that represents similarity between the particular image and the reference image by:

accessing data for multiple images of the portion of the particular person;

computing, for each of the multiple images, a similarity score that represents similarity between the corresponding image and the reference image; and

computing an average similarity score based on the similarity scores computed for the multiple images.

12. The biometric authentication system of claim 1, wherein the biometric enrollment system is configured to compute the particular similarity score that represents similarity between the particular image and the reference image by using an image similarity process to generate a similarity measure between the particular image and the reference image and normalizing the similarity measure to a similarity score between zero and one.

13. At least one non-transitory computer-readable storage medium encoded with executable instructions that, when executed by at least one processor, cause the at least one processor to perform operations comprising:

receiving, by an enrollment system, a particular image of at least a portion of a particular person;

computing, by the enrollment system, a particular similarity score that represents similarity between the particular image and a reference image used in computing the similarity scores for each person in a group of multiple, different people;

determining, by the enrollment system from the similarity scores stored in a data storage system for the reference image, a first similarity score that has a value greater than the particular similarity score without any other similarity scores from the similarity scores stored in the data storage system for the reference image having values between the first similarity score and the particular similarity score, wherein the data storage system is configured to maintain, for the group of multiple, different people, data for the corresponding person that includes sorted similarity scores and each similarity score represents a similarity between an image of at least a portion of a corresponding person from the group of multiple, different people and the reference image;

determining, by the enrollment system from the similarity scores stored in the data storage system for the reference image, a second similarity score that has a value less than the particular similarity score without any other similarity scores from the similarity scores stored in the data storage system for the reference image having values between the first similarity score and the second similarity score; and

determining, by the enrollment system, a location in the data storage system at which to store data for the particular person using the first similarity score, the second similarity score, and the particular similarity score as an index in the data storage system; and

storing, by the enrollment system in the data storage system, the data for the particular person at the location in the data storage system.

14. The computer-readable storage medium of claim 13, wherein storing, in the data storage system, the data for the particular person at the location in the data storage system comprises linking the data for the particular person with the particular similarity score.

15. The computer-readable storage medium of claim 14, wherein linking the data for the particular person with the particular similarity score comprises linking the data for the particular person with the particular similarity score using a unique identifier for the particular person.

16. The computer-readable storage medium of claim 13, wherein storing, in the data storage system, the data for the particular person at the location in the data storage system comprises storing, in the data storage system, the particular image for the particular person at the location in the data storage system.

17. The computer-readable storage medium of claim 13, wherein storing, in the data storage system, the data for the particular person at the location in the data storage system comprises storing, in the data storage system, blob data descriptive of the particular image for the particular person at the location in the data storage system.

18. The computer-readable storage medium of claim 13, wherein storing, in the data storage system, the data for the particular person at the location in the data storage system comprises storing, in the data storage system, fingerprint data for the particular person or iris data for the particular person at the location in the data storage system.

19. The computer-readable storage medium of claim 13, the operations comprising:

determining a particular type of data for the particular image from a group of multiple, different types; and

selecting a particular image as the reference image that has the particular type of data, wherein computing the particular similarity score that represents similarity between the particular image and the reference image used in computing the similarity scores for each person in a group of multiple, different people comprises computing the particular similarity score that represents similarity between the particular image of the particular type of data and the reference image of the particular type of data.

20. A method comprising:

receiving, by an enrollment system, a particular image of at least a portion of a particular person;

computing, by the enrollment system, a particular similarity score that represents similarity between the particular image and a reference image used in computing the similarity scores for each person in a group of multiple, different people;

determining, by the enrollment system from the similarity scores stored in a data storage system for the reference image, a first similarity score that has a value greater than the particular similarity score without any other similarity scores from the similarity scores stored in the data storage system for the reference image having values between the first similarity score and the particular similarity score, wherein the data storage system is configured to maintain, for the group of multiple, different people, biometric data for the corresponding person that includes sorted similarity scores and each similarity score represents a similarity between an image of at least a portion of a corresponding person from the group of multiple, different people and the reference image;

determining, by the enrollment system from the similarity scores stored in the data storage system for the reference image, a second similarity score that has a value less than the particular similarity score without any other similarity scores from the similarity scores stored in the data storage system for the reference image having values between the first similarity score and the second similarity score; and

determining, by the enrollment system, a location in the data storage system at which to store biometric data for the particular person using the first similarity score, the second similarity score, and the particular similarity score as an index in the data storage system; and

storing, by the enrollment system in the data storage system, the biometric data for the particular person at the location in the data storage system.