METHOD AND SYSTEM FOR CONDUCTING IDENTIFICATION MATCHING

• US 20110211735A1
• Filed: 11/24/2010
• Published: 09/01/2011
• Est. Priority Date: 03/01/2010
• Status: Active Grant

• Current Assignee: Corporation DAON Technology
• Original Assignee: Daon Holdings Limited
• Inventors: Langley, Richard Jay
• Granted Patent: US 8,989,520 B2
• Time in Patent Office: Days
• US Class Current: 382/115
• CPC Class Codes: G06F 21/32 using biometric data, e.g. fingerprints, iris scans or voiceprints
• CPC Class Codes: G06V 30/242 Division of the character sequences into groups prior to recognition; Selection of dictionaries
• CPC Class Codes: G06V 30/2504 Coarse or fine approaches, e.g. resolution of ambiguities or multiscale approaches
• CPC Class Codes: G06V 40/70 Multimodal biometrics, e.g. combining information from different biometric modalities

Abstract

A method of conducting pattern matching is provided that includes establishing probe categories. Each probe category corresponds to pattern characteristics of one of a plurality of subpopulations. Moreover, the method includes coordinating combinations of the subpopulations and probe categories with pattern matching systems such that each combination corresponds to at least one of a plurality of the pattern matching systems, obtaining pattern data for an object, configuring the obtained object pattern data as a probe, and determining the probe category of the probe. Furthermore, the method includes conducting a matching transaction between the probe and each of the subpopulations using the at least one matching system corresponding to each combination of subpopulation and the determined probe category, and determining at least one candidate match when the probe matches at least one enrollment data record in the at least one matching system of any of the subpopulations.

Claims

1. A method of conducting pattern matching comprising:

establishing probe categories, each probe category corresponding to pattern characteristics of one of a plurality of subpopulations;

coordinating combinations of the subpopulations and probe categories with pattern matching systems such that each combination corresponds to at least one of a plurality of the pattern matching systems,

obtaining pattern data for an object, configuring the obtained object pattern data as a probe, and determining the probe category of the probe;

conducting a matching transaction between the probe and each of the subpopulations using the at least one matching system corresponding to each combination of subpopulation and the determined probe category; and

determining at least one candidate match when the probe matches at least one enrollment data record in the at least one matching system of any of the subpopulations.

2. A method in accordance with claim 1 further comprising conducting a subsequent matching transaction when the one subpopulation is a non-residual subpopulation to determine final candidate matches.

3. A method in accordance with claim 2 further comprising consolidating the at least one final candidate match of the subpopulations into a single response by storing the at least one final candidate match in the queue.

4. A method in accordance with claim 2, wherein:

said conducting operation comprises conducting a 1;

N identity matching transaction; and

said conducting a subsequent matching transaction operation comprises conducting a 1;

1 verification matching transaction.

5. A method in accordance with claim 1 further comprising dividing an entire population into the plurality of subpopulations, wherein the pattern data comprises one of biometric modality data, biographic data, and object data.

6. A method in accordance with claim 1, said conducting operation comprising comparing the probe against the enrollment data records of each of the subpopulations in a 1:

N identity matching transaction based on reliable object pattern data.

7. A method in accordance with claim 1 further comprising conducting a 1:

1 verification transaction by evaluating the at least one candidate match when the at least one matching system is associated with additional object pattern data.

8. A method in accordance with claim 1, said conducting operation comprising conducting a parallel fusion matching transaction with best available object pattern data.

9. A method in accordance with claim 1 further comprising normalizing the at least one final candidate match.

10. A system for conducting pattern matching comprising:

at least one pattern matching system operable to store enrollment data records of a subpopulation assigned thereto;

at least one client system operable to at least obtain object pattern data; and

a computer configured as a server, said server including at least a database and being operable to

communicate with said at least one matching system and said at least one client system,

store within said database at least enrollment data records of a plurality of subpopulations,

establish probe categories that each correspond to pattern characteristics of one of the subpopulations, and

convert obtained object pattern data into a probe and determine the probe category of the probe,

said at least one pattern matching system being further operable to

conduct a matching transaction between the probe and each of the subpopulations, and determine at least one candidate match when the probe matches at least one enrollment data record from any of the subpopulations.

11. A system in accordance with claim 10, said server being further configured to coordinate combinations of the subpopulations and probe categories with said pattern matching systems such that each combination corresponds to one of said pattern matching systems.

12. A system in accordance with claim 10, said at least one pattern matching system being further operable to conduct a subsequent 1:

1 matching transaction when a corresponding at least one matching system is associated with a reliable one of the biometric modalities.

13. A system in accordance with claim 10, said at least one pattern matching system being further operable to conduct the matching transaction as a 1:

N identity matching transaction based on reliable object pattern data, and to conduct the matching transaction as a parallel fusion matching transaction with best available object pattern data.

14. A system in accordance with claim 10 said server being further operable to divide an entire population into the plurality of subpopulations, and wherein the object pattern data comprises one of biometric data and ship data.

15. A system in accordance with claim 12 said at least one pattern matching system being further operable to conduct the subsequent 1:

1 verification transaction by evaluating the at least one candidate match when said at least one matching system is associated with additional object pattern data.

16. A method of conducting object pattern matching comprising:

coordinating a plurality of subpopulations with matching systems such that each subpopulation corresponds to at least one of the matching systems, wherein said coordinating operation is based on at least one pattern associated with each subpopulation;

obtaining object pattern data and configuring the obtained object pattern data as a probe;

conducting a matching transaction between the probe and each subpopulation using the at least one matching system corresponding to each subpopulation; and

determining at least one candidate match when the probe matches at least one enrollment data record in the at least one corresponding matching system.

17. A method in accordance with claim 16 further comprising conducting a subsequent matching transaction when the corresponding at least one matching system is associated with reliable object pattern data.

18. A method in accordance with claim 16 further comprising:

normalizing the at least one candidate match; and

consolidating the at least one candidate match into a single response by storing the at least one candidate match in a queue.

19. A method in accordance with claim 17, wherein:

said conducting operation comprises conducting a 1;

N identity matching transaction; and

said conducting a subsequent matching transaction operation comprises conducting a 1;

1 verification matching transaction.

20. A method in accordance with claim 16, said conducting operation comprising conducting a parallel fusion matching transaction with best available object pattern data.