Method and apparatus for biometric verification with data packet transmission prioritization

• US 7,114,646 B2
• Filed: 02/25/2003
• Issued: 10/03/2006
• Est. Priority Date: 02/25/2003
• Status: Expired due to Term

• Current Assignee: Activcard Ireland, Limited
• Original Assignee: Activcard Ireland, Limited
• Inventors: Hillhouse, Robert D.
• Primary Examiner(s): Kim, Ahshik
• Application Number:
  US10/372,082
• Publication Number:
  US 20040164139A1
• Time in Patent Office: 1,316 Days
• Field of Search: 235/380, 235/382, 235/382.5, 235/375, 235/487, 713/185, 713/186, 382/115
• US Class Current: 235/375
• CPC Class Codes: G06V 40/1365 Matching; Classification

Abstract

An authentication mechanism for use with biometric systems which optimizes data extraction on areas or regions having a high probability of matching a reference biometric template, allows a reduction in both the size and number of data packet transmissions to be made to a biometric matching engine and includes data packet transmission prioritization.

Claims

1. A method of biometric authentication comprising:

a) extracting feature sample data from a biometric sample;

b) prioritizing feature sample data based on the probability that the feature sample data will lead to an accurate identification of the person providing the biometric sample;

c) receiving higher priority feature sample data before lower priority feature sample data and correlating a value of said prioritized feature sample data with a feature template value to determine a registration value representative of a mathematical correlation between said value of said prioritized feature sample data and said feature template value;

d) accumulating said registration value in a register to create an accumulated registration value;

e) comparing the accumulated registration value against a threshold indicative of a successful authentication of said biometric sample with said feature template; and

f) if the accumulated registration value exceeds said threshold, determining that a successful authentication has been conducted;

otherwise, determining that an unsuccessful authentication has been conducted.

2. A method as in claim 1, further comprising repeating a) through e) for a plurality of feature sample data packets representative of said biometric sample until the accumulated registration value exceeds said threshold, indicating that a successful authentication has been conducted, and ending biometric authentication;

otherwise, repeating a) through e) until successful authentication or all feature sample data packets have been processed without a successful authentication.

3. A method as in claim 2, wherein the feature sample data is prioritized based on likelihood of the feature sample data contributing most significantly to the accumulated registration value.

4. A method as in claim 3, wherein prioritizing the feature sample data comprises ordering the feature sample data in descending order of likelihood that the feature sample data will contribute most significantly to the accumulated registration value.

5. A method as in claim 2, wherein the feature sample data is prioritized based on the quality or uniqueness of the feature represented by the feature sample data.

6. A method as in claim 2, further comprising determining whether said feature sample data corresponds to a particular feature and, if so, accumulating a first accumulated registration value for said particular feature;

otherwise, accumulating a second accumulated registration value for the absence of said particular feature.

7. A method as in claim 2, wherein said biometric sample represents a fingerprint, further comprising dividing said fingerprint into respective areas within a coordinate system adapted for the location of biometric features of interest for extracting.

8. A method as in claim 7, wherein the feature sample data from respective areas is prioritized based on likelihood of the feature sample data contributing most significantly to the accumulated registration value.

9. A method as in claim 7, wherein the feature sample data from respective areas is prioritized based on the quality or uniqueness of the feature represented by the feature sample data in said respective areas.

10. A system for biometric data extraction and transmission of biometric feature sample data comprising:

a buffer capable of storing prioritized feature sample data extracted from a biometric sample, wherein prioritization of said feature sample data is based on the probability that the feature sample data will lead to an accurate identification of the person providing the biometric sample;

a processor that receives higher priority feature sample data before lower priority feature sample data and is capable of correlating a value of said prioritized feature sample data with a feature template value to determine a registration value representative of a mathematical correlation between said value of said prioritized feature sample data and said feature template value; and

an accumulation value register capable of storing an accumulation of said registration value in a register to create an accumulated registration value;

wherein said processor further is capable of comparing the accumulated registration value against a threshold indicative of a successful authentication of said biometric sample with said feature template and if the accumulated registration value exceeds said threshold, said processor is capable of determining that a successful authentication has been conducted;

otherwise, said processor is capable of determining that an unsuccessful authentication has been conducted.

11. A system as in claim 10, wherein said system is housed within a smart card.

12. A system as in claim 11, wherein said processor is capable of executing Java and wherein the feature sample data stored in said buffer is stored in temporary variables and the accumulated registration value stored in said accumulation value register upon processing of said feature sample data is stored in a temporary variable.

13. A system as in claim 10, wherein said system comprises a network server and wherein said buffer, said processor, and said accumulation value register are all housed within said network server.

14. A storage medium having data stored therein, said data relating to instructions for processing feature sample data extracted from a biometric sample to perform biometric authentication, said instructions instructing a processor to perform:

a) prioritizing feature sample data based on the probability that the feature sample data will lead to an accurate identification of the person providing the biometric sample;

b) receiving higher priority feature sample data before lower priority feature sample data and correlating a value of said prioritized feature sample data with a feature template value to determine a registration value representative of a mathematical correlation between said value of said prioritized feature sample data and said feature template value;

c) accumulating said registration value in a register to create an accumulated registration value;

d) comparing the accumulated registration value against a threshold indicative of a successful authentication of said biometric sample with said feature template; and

e) if the accumulated registration value exceeds said threshold, determining that a successful authentication has been conducted;

otherwise, determining that an unsuccessful authentication has been conducted.

15. A storage medium as in claim 14, wherein said storage medium is housed within a smart card.

16. A storage medium as in claim 15, wherein said smart card further comprises a processor that is capable of executing Java and wherein the feature sample data is stored in temporary variables and the accumulated registration value upon processing of said feature sample data is stored in a temporary variable.

17. A storage medium as in claim 14, wherein said storage medium is housed within a network server.

18. A method of biometric authentication comprising:

a) extracting feature sample data from a biometric sample;

b) prioritizing feature sample data based on the probability that the feature sample data will lead to an accurate identification of the person providing the biometric sample;

c) receiving higher priority feature sample data before lower priority feature sample data and correlating a value of said prioritized feature sample data with a feature template value to determine a registration value representative of a mathematical correlation between said value of said prioritized feature sample data and said feature template value;

d) accumulating said registration value in a register to create an accumulated registration value;

e) comparing the accumulated registration value against a threshold indicative of a successful authentication of said biometric sample with said feature template; and

f) if the accumulated registration value exceeds said threshold, determining that a successful authentication has been conducted;

otherwise, repeating a) through e) for a plurality of prioritized feature sample data packets representative of said biometric sample until the accumulated registration value exceeds said threshold, indicating that a successful authentication has been conducted, and ending biometric authentication;

otherwise, repeating a) through e) until successful authentication or all prioritized feature sample data packets have been processed without a successful authentication.

19. A method as in claim 18, wherein the comparing is performed once for every M data packets of feature sample data that are processed in a) through d).

20. A method as in claim 19, wherein M=1.

21. A method as in claim 19, wherein only one data packet is processed at a time and discarded once processed.

22. A method as in claim 21, comprising providing a new data packet of prioritized feature sample data once said one data packet has been completely processed and the accumulated registration value has failed to exceed said threshold.

23. A method as in claim 18, wherein the method is performed at least partially within a biometric matching engine and wherein the biometric matching engine comprises a server based application.

24. A system for biometric data extraction and transmission of biometric feature sample data comprising:

a buffer capable of storing prioritized feature sample data extracted from a biometric sample, wherein prioritization of said feature sample data is based on the probability that the feature sample data will lead to an accurate identification of the person providing the biometric sample;

a processor that receives higher priority feature sample data before lower priority feature sample data and is capable of correlating a value of said prioritized feature sample data with a feature template value to determine a registration value representative of a mathematical correlation between said value of said prioritized feature sample data and said feature template value; and

an accumulation value register capable of storing an accumulation of said registration value in a register to create an accumulated registration value;

wherein said processor further is capable of comparing the accumulated registration value against a threshold indicative of a successful authentication of said biometric sample with said feature template and if the accumulated registration value exceeds said threshold, said processor is capable of determining that a successful authentication has been conducted;

otherwise, said processor repeating the correlation, accumulation and comparison for a plurality of prioritized feature sample data packets representative of said biometric sample until the accumulated registration value exceeds said threshold, indicating that a successful authentication has been conducted, and ending biometric authentication, or until successful authentication or all prioritized feature sample data packets have been processed without a successful authentication.

25. A system as in claim 24, wherein said system is housed within a smart card.

26. A system as in claim 25, wherein said processor is capable of executing Java and wherein the feature sample data stored in said buffer is stored in temporary variables and the accumulated registration value stored in said accumulation value register upon processing of said feature sample data is stored in a temporary variable.

27. A system as in claim 24, wherein said system comprises a network server and wherein said buffer, said processor, and said accumulation value register are all housed within said network server.

28. A storage medium having data stored therein, said data relating to instructions for processing feature sample data extracted from a biometric sample to perform biometric authentication, said instructions instructing a processor to perform:

a) prioritizing feature sample data based on the probability that the feature sample data will lead to an accurate identification of the person providing the biometric sample;

b) receiving higher priority feature sample data before lower priority feature sample data and correlating a value of said prioritized feature sample data with a feature template value to determine a registration value representative of a mathematical correlation between said value of said prioritized feature sample data and said feature template value;

c) accumulating said registration value in a register to create an accumulated registration value;

d) comparing the accumulated registration value against a threshold indicative of a successful authentication of said biometric sample with said feature template; and

e) if the accumulated registration value exceeds said threshold, determining that a successful authentication has been conducted;

otherwise, repeating a) through d) for a plurality of prioritized feature sample data packets representative of said biometric sample until the accumulated registration value exceeds said threshold, indicating that a successful authentication has been conducted, and ending biometric authentication;

otherwise, repeating a) through d) until successful authentication or all prioritized feature sample data packets have been processed without a successful authentication.

29. A storage medium as in claim 28, wherein said storage medium is housed within a smart card.

30. A storage medium as in claim 29, wherein said smart card further comprises a processor that is capable of executing Java and wherein the feature sample data is stored in temporary variables and the accumulated registration value upon processing of said feature sample data is stored in a temporary variable.

31. A storage medium as in claim 28, wherein said storage medium is housed within a network server.