IP Library › Granted Patent US 10,713,342
Granted Patent B2
US 10,713,342 · App. 14/866,341 · Granted Jul 14, 2020

Techniques to determine distinctiveness of a biometric input in a biometric system

Inventors: Glen J. Anderson (Beaverton, OR); Lenitra M. Durham (Beaverton, OR)
Assignee: INTEL CORPORATION
G06F21/32G06K9/00892G06K9/036G06N20/00
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 10,713,342
App. No.
14/866,341
Granted
Jul 14, 2020
Kind
B2
Abstract

Various embodiments are generally directed to an apparatus, method and other techniques to receive a biometric input of a first input type, determine a distinctiveness value for the biometric input based on a comparison of an attributes score for the biometric input with an average of attributes scores for biometric inputs of the first input type from the plurality of biometric inputs, and determine an input type to use to perform an action based on the distinctiveness value.

Claims (65)

1. An apparatus, comprising:

memory to store a plurality of biometric inputs of two or more input types; and

a processor coupled with the memory, the memory comprising instructions that when executed by the processor cause the processor to:

receive a biometric input of a first input type of the two or more input types,

simulate a number of authentication attempts,

determine a distinctiveness value for the biometric input based on a number of failed simulated authentication attempts,

update a biometric profile for a user based the distinctiveness value, the biometric profile to identify at least one input type to use for authentication or training,

determine an input type of the two or more input types to use to perform a training operation based on the distinctiveness value,

perform the training operation,

determine a distinctiveness factor based on the training operation, and

adjust the training operation based on the distinctiveness factor.

2. The apparatus of claim 1 , the memory comprising instructions that when executed by the processor cause the processor to select the first input type as the input type for use to perform the training operation if the distinctiveness value is greater than or equal to a distinctiveness threshold value, and select a second input type as the input type for use to perform the training operation if the distinctiveness value is less than the distinctiveness threshold value.

3. The apparatus of claim 1 , the training operation to utilize a biometric sensor capable of detecting the input type.

4. The apparatus of claim 1 , comprising:

one or more biometric sensors, each of the one or more biometric sensors comprising a different one of a camera, a fingerprint reader, an iris scanner, and a microphone, and

the input type to comprise one of a facial input type, fingerprint input type, an iris input type, and a sound input type.

5. The apparatus of claim 1 , the memory comprising instructions that when executed by the processor cause the processor to focus the training operation on a specific characteristic of the biometric input to adjust the training operation based on the distinctiveness factor.

6. The apparatus of claim 1 , the distinctiveness factor to comprise at least one of a tonal frequency range, an area of a finger, an area of a face, and an area of an iris.

7. The apparatus of claim 1 , the memory comprising instructions that when executed by the processor cause the processor to perform a number of simulated authentication operations to determine the distinctiveness value based on a number of failed simulated authentication attempts.

8. The apparatus of claim 1 , the memory comprising instructions that when executed by the processor cause the processor to generate a biometric profile for a user based on one or more distinctiveness values each corresponding to a different biometric input type, the biometric profile to identify at least one input type to use for authentication.

9. The apparatus of claim 1 , comprising:

a biometric array comprising one or more biometric sensors;

a data storage array comprising one or more storage devices.

10. A computer-implemented method, comprising:

capturing, by a biometric sensor, a biometric input of a first input type;

simulating a number of authentication attempts;

determining a distinctiveness value for the biometric input based on a number of failed simulated authentication attempts;

updating a biometric profile for a user based the distinctiveness value, the biometric profile to identify at least one input type to use for authentication or training;

determining an input type of a plurality of input types to use to perform a training operation based on the distinctiveness value;

performing the training operation;

determining a distinctiveness factor based on the training operation; and

adjusting the training operation based on the distinctiveness factor.

11. The computer-implemented method of claim 10 , comprising:

selecting the first input type as the input type for use to perform the training operation if the distinctiveness value is greater than or equal to a distinctiveness threshold value; and

selecting a second input type, different than the first input type, as the input type for use to perform the training operation if the distinctiveness value is less than the distinctiveness threshold value.

12. The computer-implemented method of claim 10 , comprising:

performing the training operation using a biometric sensor capable of capturing the input type.

13. The computer-implemented method of claim 10 , comprising:

determining the first input type based on the biometric sensor comprising one of a camera, a fingerprint reader, an iris scanner, and a microphone; and

retrieving the plurality of biometric inputs from a data storage array having a same input type as the first input type.

14. The computer-implemented method of claim 10 , comprising:

the distinctiveness factor comprising at least one of a focus on a feature specific to the determined input type, a system configuration, and an environment configuration.

15. The computer-implemented method of claim 14 , the feature comprising a tonal frequency range, an area of a finger, an area of a face, and an area of an iris.

16. The computer-implemented method of claim 10 , comprising:

performing a number of simulated authentication operations to determine the distinctiveness value based on a number of failed simulated authentication attempts.

17. The computer-implemented method of claim 10 , comprising:

updating a biometric profile for a user based on one or more distinctiveness values each corresponding to a different biometric input type, the biometric profile to identify at least one input type to use for authentication or training.

18. A non-transitory computer-readable medium comprising instructions that, when executed, cause processing circuitry to:

capture a biometric input of a first input type;

simulating a number of authentication attempts;

determining a distinctiveness value for the biometric input based on a number of failed simulated authentication attempts;

update a biometric profile for a user based the distinctiveness value, the biometric profile to identify at least one input type to use for authentication or training;

determine an input type of a plurality of input types to use to perform a training operation based on the distinctiveness value;

perform the training operation;

determine a distinctiveness factor based on the training operation; and

adjust the training operation based on the distinctiveness factor.

19. The non-transitory computer-readable medium claim 18 , comprising instructions that, when executed, cause processing circuitry to:

select the first input type as the input type for use to perform the training operation if the distinctiveness value is greater than or equal to a distinctiveness threshold value; and

select a second input type, different than the first input type, as the input type for use to perform the training operation if the distinctiveness value is less than the distinctiveness threshold value.

20. The non-transitory computer-readable medium claim 18 , the training operation to utilize a biometric sensor capable of capturing the input type.

21. The non-transitory computer-readable medium claim 18 , comprising instructions, that, when executed, cause processing circuitry to:

determine the first input type based on a biometric sensor comprising one of a camera, a fingerprint reader, an iris scanner, and a microphone; and

retrieve the plurality of biometric inputs from a data storage array having a same input type as the first input type.

22. The non-transitory computer-readable medium claim 18 , the distinctiveness factor to comprise at least one of a focus on a feature specific to the determined input type, a system configuration, and an environment configuration.

23. The non-transitory computer-readable medium of claim 22 , the feature to comprise at least one of a tonal frequency range, an area of a finger, an area of a face, and an area of an iris.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Oct 29, 2015
From: ANDERSON, GLEN J.; DURHAM, LENITRA M.
To: INTEL CORPORATION
Reel/Frame 036989/0842 →
Continuity (1)
Related Publication 20170091433A1 · Mar 30, 2017