Multimodal biometry

• US 20030031348A1
• Filed: 07/02/2002
• Published: 02/13/2003
• Est. Priority Date: 07/03/2001
• Status: Active Grant

• Current Assignee: Siemens AG
• Original Assignee: Siemens AG
• Inventors: Schuster, Matthias, Kuepper, Wolfgang
• Granted Patent: US 7,092,553 B2
• Time in Patent Office: Days
• US Class Current: 382/116
• CPC Class Codes: G06F 18/256 of results relating to different input data, e.g. multimodal recognition

Abstract

A multimodal biometric method is provided for authenticating at least one user, in which at least one user is assigned to one of at least two classes, in which similarity measures are used that are measures of the similarity of biometric data, determined for the user, to reference data for one of the classes, in which a overall statistical statement on the user'"'"'s membership of the class is present for each of the at least two classes as a function of the similarity measure, in which the overall statistical statement for each of the at least two classes results from the combination of the statistical statements of at least two individual biometries for the respective class, the statistical statements of the individual biometries being statistical statements on the user'"'"'s membership of the class as a function of the similarity measures, and in which the user is assigned to one of at least two classes when a specific assignment criterion is fulfilled.

Claims

1. A multimodal biometric method, comprising the steps of:

assigning at least one user to one of at least two classes;

using similarity measures of biometric data, determined for the user, to reference data for the respective class;

presenting an overall statistical statement on the user'"'"'s membership of the class for each of the at least two classes as a function of the similarity measures, wherein the overall statistical statement for each of the at least two classes results from a combination of the statistical statements of at least two individual biometries for the respective class, the statistical statements of the individual biometries being statistical statements on the user'"'"'s membership of the class as a function of the similarity measures; and

assigning the user to one of the at least two classes when an assignment criterion is fulfilled that depends on the overall statistical statements.

2. A multimodal biometric method as claimed in claim 1 wherein the user is authenticated by the method.

3. A multimodal biometric method as claimed in claim 1, wherein at least one of the statistical statements of an individual biometry results from at least one of enumerating and interpolating measured data.

4. A multimodal biometric method as claimed in claim 1, wherein the overall statistical statement results from at least one of enumerating and interpolating the statistical statements of the individual biometries.

5. A multimodal biometric method as claimed in claim 1, wherein at least one of the statistical statements is a probability density.

6. A multimodal biometric method as claimed in claim 1, wherein the combination of the statistical statements of at least two individual biometries from which the overall statistical statement results is a multiplication.

7. A multimodal biometric method as claimed in claim 1, wherein the similarity measures include at least one of costs and scores.

8. A multimodal biometric method as claimed in claim 1, wherein at least one of the statistical statements and the overall statistical statements are normalized.

9. A multimodal biometric method as claimed in claim 1, wherein an assignment criterion is selected so as to produce a desired assignment rate of users to one of the at least two classes.

10. A multimodal biometric method as claimed in claim 9, wherein the assignment criterion is fulfilled when a ratio of the overall statistical statement on the user'"'"'s membership of the one of the at least two classes to the overall statistical statement on the user'"'"'s membership of the other of the at least two classes exceeds a prescribed value.

11. A multimodal biometric method as claimed in claim 10, wherein the prescribed value is at least approximately equal to one.

12. A multimodal biometric method as claimed in claim 10, wherein the prescribed value is selected so as to result in a desired assignment rate of users to one of the at least two classes.

13. A multimodal biometric method as claimed in claim 9, wherein the assignment criterion is fulfilled when the overall statistical statement on the user'"'"'s membership of the one of the at least two classes exceeds a prescribed limiting value.

14. A multimodal biometric method as claimed in claim 13, wherein the limiting value is selected so as to result in a desired assignment rate of users to one of the at least two classes.

15. A program product for a data processing system that includes software code sections with the aid of which a multimodal biometric method may be executed on the data processing system, the program product comprising:

a section for assigning at least one user to one of at least two classes;

a section for using similarity measures of biometric data, determined for the user, to reference data for the respective class;

a section for presenting an overall statistical statement on the user'"'"'s membership of the class for each of the at least two classes as a function of the similarity measures, wherein the overall statistical statement for each of the at least two classes results from a combination of the statistical statements of at least two individual biometries for the respective class, the statistical statements of the individual biometries being statistical statements on the user'"'"'s membership of the class as a function of the similarity measures; and

a section for assigning the user to one of the at least two classes when an assignment criterion is fulfilled that depends on the overall statistical statements.

16. A data processing system for executing a multimodal biometric method, wherein the method comprises the steps of assigning at least one user to one of at least two classes, using similarity measures of biometric data, determined for the user, to reference data for the respective class, presenting an overall statistical statement on the user'"'"'s membership of the class for each of the at least two classes as a function of the similarity measures, with the overall statistical statement for each of the at least two classes resulting from a combination of the statistical statements of at least two individual biometries for the respective class, the statistical statements of the individual biometries being statistical statements on the user'"'"'s membership of the class as a function of the similarity measures, and assigning the user to one of the at least two classes when an assignment criterion is fulfilled that depends on the overall statistical statements.