Method, system and computer program product for multiple biometric template screening

• US 8,171,304 B2
• Filed: 05/15/2003
• Issued: 05/01/2012
• Est. Priority Date: 05/15/2003
• Status: Active Grant

• Current Assignee: Activcard Ireland, Limited (Assa Abloy AB)
• Original Assignee: Activcard Ireland, Limited (Assa Abloy AB)
• Inventors: Hillhouse, Robert D.
• Primary Examiner(s): Zee, Edward
• Assistant Examiner(s): Gyorfi, Thomas
• Application Number:
  US10/438,067
• Publication Number:
  US 20040230810A1
• Time in Patent Office: 3,274 Days
• Field of Search: 382124-127, 382/115, 382/116, 382/190, 382/226, 713/186
• US Class Current: 713/186
• CPC Class Codes: G06V 40/1365 Matching; Classification

Abstract

A method, system and computer program product which allows identification of an enrollment biometric template having a highest probability of matching a sample biometric template from a plurality of enrolled biometric templates without compromising or significantly compromising system security. In one embodiment of the invention, first feature set information is derived from sample and enrollment biometric templates. The first feature set information generally comprises spatially dependent information associated with a fingerprint. The first feature set information is then used to determine which enrollment biometric template has the highest probability of matching the sample biometric template. Second feature set information is then derived from the biometric sample template and the determined enrollment biometric template and used to perform a one-to-one match. The second feature set information generally comprises pattern dependent information associated with a fingerprint.

Claims

1. A fingerprint biometric security method, comprising:

deriving, with a computer system, a sample first feature set from a biometric sample, wherein the sample first feature set comprises spatially dependent features including at least one of minutia points and ridge spacing;

orienting the sample first feature set to a standardized orientation based on the spatially dependent features;

comparing the sample first feature set to a plurality of enrollment first feature sets at the standardized orientation, wherein the enrollment first feature sets are derived from corresponding enrollment biometric templates;

determining a single most relevant enrollment biometric template by selecting the enrollment first feature set which most favorably compares to the sample first feature set;

deriving a sample second feature set from the biometric sample, wherein the sample second feature set comprises pattern dependent features including at least one of minutia types, ridge flow angles, minutia direction, and ridge patterns; and

comparing the sample second feature set to an enrollment second feature set at the standardized orientation, wherein the enrollment second feature set is derived from the most relevant enrollment biometric template, and wherein the sample first feature set is independent of the sample second feature set.

2. The method according to claim 1, further comprising retrieving the plurality of enrollment first feature sets from a storage location.

3. The method according to claim 1, further comprising deriving the plurality of enrollment first feature sets on demand.

4. The method according to claim 1, further comprising retrieving the enrollment second feature set from a storage location.

5. The method according to claim 1, further comprising deriving the enrollment second feature set on demand.

6. The method according to claim 1 wherein comparing the sample first features set and the determining the most relevant steps enrollment biometric template are performed by a security token in processing communications with a computer system.

7. The method according to claim 1 wherein the computer system is either a local computer system or a remote computer system.

8. The method according to claim 1 wherein the sample first feature set and the sample second feature set derived from the biometric sample are incorporated into a sample biometric template.

9. An apparatus including a non-transitory computer-readable storage medium having instructions stored thereon that, when executed by computing device having a processor and memory, causes the processor of the computing device to perform operations comprising:

deriving a sample first feature set from a biometric sample, wherein the sample first feature set comprises spatially dependent features including at least one of minutia points and ridge spacing;

deriving a plurality of enrollment first feature sets from each member of a plurality of enrollment biometric templates;

orienting the sample first feature set to a standardized orientation based on the spatially dependent features;

comparing the sample first feature set to the plurality of enrollment first feature sets at the standardized orientation;

determining a single most relevant enrollment biometric template based on the comparison of the sample first feature set;

deriving a sample second feature set from the biometric sample, wherein the sample second feature set comprises pattern dependent features including at least one of minutia types, ridge flow angles, minutia direction, and ridge patterns;

deriving an enrollment second feature set from the most relevant enrollment biometric template; and

comparing the enrollment second feature set to the sample second feature set at the standardized orientation, wherein the sample first feature set is independent of the sample second feature set.

10. The apparatus according to claim 9 wherein the plurality of enrollment first feature sets are derived in advance and incorporated into enrollment pre-match templates.

11. A non-transitory computer-readable storage medium having stored thereon, computer executable instructions that, if executed by an apparatus, cause the apparatus to perform operations comprising:

deriving a first sample-based feature set from a biometric sample, wherein the first sample-based feature set comprises spatially dependent features including at least one of minutia points and ridge spacing;

orienting the first sample-based feature set to a standardized orientation based on the spatially dependent features;

comparing the first sample-based feature set to a plurality of enrollment-based feature sets at the standardized orientation, wherein the enrollment-based feature sets are derived from plurality of enrollment biometric templates;

determining a single most relevant enrollment biometric template by selection of the enrollment-based feature set which most favorably compares to the first sample-based feature set;

deriving a second sample-based feature set from the biometric sample, wherein the second sample-based feature set comprises pattern dependent features including at least one of minutia types, ridge flow angles, minutia direction, and ridge patterns; and

comparing the second feature set to an enrollment second feature set at the standardized orientation, wherein the enrollment second feature set is derived from the most relevant enrollment biometric template, and wherein the first sample-based feature set is independent of the second sample-based feature set.

12. A fingerprint biometric security system, comprising:

a first component configured to receive a biometric sample;

a second component configured to generate a sample biometric template which incorporates a sample first feature set and a sample second feature set, wherein the sample first feature set is independent of the sample second feature set, and wherein the sample first feature set comprises spatially dependent features including at least one of minutia points and ridge spacing, and the sample second feature set comprises pattern dependent features including at least one of minutia types, ridge flow angles, minutia direction, and ridge patterns, and wherein the second component is further configured to orient the sample biometric template to a standardized orientation based on the spatially dependent features;

a third component configured to send the sample biometric template to a security token, wherein the security token includes the plurality of enrollment biometric templates operatively stored therein, and wherein the third component is further configured to—

receive the sample biometric template;

derive an enrollment first feature set from each member of the plurality of enrollment biometric templates;

compare the sample first feature set to each derived enrollment first feature set;

determine a single most relevant enrollment biometric template;

derive a most relevant second feature set from the most relevant enrollment biometric template; and

compare the sample second feature set to the most relevant second feature set at the standardized orientation

wherein at least one of the first, second, and third components comprises computer executable instructions stored in a non-transitory computer-readable storage medium for execution by a computing device.

13. The system according to claim 12 wherein the security token includes a plurality of pre-match enrollment templates operatively stored therein, wherein the pre-match enrollment templates are derived from and relationally associated with the plurality of enrollment biometric templates, and wherein the security token is configured to compare the sample first feature set to the plurality of pre-match enrollment templates.

14. The system according to claim 12 wherein the security token is further configured to:

derive a sample second feature set from the sample biometric template;

derive a most relevant second feature set from the most relevant enrollment biometric template; and

match the sample second feature set to the most relevant second feature set.