FINGERPRINT SENSING SYSTEM CONFIGURED TO DETERMINE IF A FINGER CONTACTS A FINGERPRINT SENSOR

• US 20180173978A1
• Filed: 11/09/2017
• Published: 06/21/2018
• Est. Priority Date: 12/20/2016
• Status: Active Grant

• Current Assignee: Fingerprint Cards IP AB
• Original Assignee: Fingerprint Cards AB
• Inventors: HANSEN, Morten, WITH PEDERSEN, Morten
• Granted Patent: US 10,325,168 B2
• Time in Patent Office: Days
• CPC Class Codes: G06F 21/32 using biometric data, e.g. fingerprints, iris scans or voiceprints
• CPC Class Codes: G06V 10/993 Evaluation of the quality of the acquired pattern
• CPC Class Codes: G06V 40/1365 Matching; Classification
• CPC Class Codes: G06V 40/1388 using image processing
• CPC Class Codes: G06V 40/40 Spoof detection, e.g. liveness detection

Abstract

The invention relates to a method performed by a fingerprint sensing system of determining if a finger contacts a fingerprint sensor of the system, and a fingerprint sensing system performing method. In a first aspect of the invention, a method performed by a fingerprint sensing system is provided for determining if a finger contacts a fingerprint sensor of the fingerprint sensing system. The method comprises capturing an image of an object contacting the fingerprint sensor, determining an intensity for a plurality of pixels of the captured image, estimating local curvatures of pixel intensity variation in the captured image, and determining from the estimated local curvatures if local pixel intensity variation is dominated by a single direction, in which case the object on the sensor is considered to constitute a finger.

Claims

1. Method performed by a fingerprint sensing system of determining if a finger contacts a fingerprint sensor of the fingerprint sensing system, comprising:

capturing an image of an object contacting the fingerprint sensor;

determining an intensity for a plurality of pixels of the captured image;

computing, for each of said plurality of pixels of the captured image, a Hessian matrix where the components of the Hessian matrix consist of second-order derivatives of the pixel intensity in the captured image;

computing the square of the Hessian matrix;

computing a squared Fractional Anisotropy, FA, measure using eigenvalues of the computed squared Hessian matrix; and

determining from the squared FA measure if local pixel intensity variation is dominated by a single direction, in which case the object on the fingerprint sensor is considered to constitute a finger.

3. The method of claim 1, further comprising:

computing trace and determinant of the Hessian matrix to derive its eigenvalues.

4. The method of claim 1, further comprising:

computing a fingerprint qualification score as a combination of all the FA measure values for said plurality of pixels normalized by the number of said plurality of pixels.

5. The method of claim 4, further comprising:

comparing the computed fingerprint qualification score to a threshold value, wherein the local pixel intensity variation is considered to be dominated by a single direction if the fingerprint qualification score exceeds the threshold value.

6. The method of claim 1, further comprising:

downsampling the captured image.

7. The method of claim 1, further comprising:

performing smoothing filtering of the captured image.

8. The method of claim 1, further comprising:

performing smoothing filtering of each component of the square of the Hessian matrix.

9. The method of claim 1, further comprising:

comparing a fingerprint of the captured image of the finger with one or more authorised pre-stored fingerprint templates; and

authenticating a user to which the finger belongs if the fingerprint of the captured image is considered to match one or more of the authorised pre-stored fingerprint templates.

20. A computer program product comprising a non-transitory computer readable medium storing computer-executable instructions that, when executed by one or more processors in a fingerprint sensing system, cause the fingerprint sensing system to perform the method of claim 1.

2. The method of claim 2, wherein the components of the Hessian matrix are computed by convolving the captured image with a first filter in an x-direction, convolving the captured image with a second filter in a y-direction, and convolving the captured image with a third filter in the x-direction and then convolving the result of the convolution with the third filter with a fourth filter in the y-direction.

10. Fingerprint sensing system comprising a fingerprint sensor and a processing unit, the fingerprint sensing system being configured to determine if a finger contacts the fingerprint sensor of the fingerprint sensing system,

the fingerprint sensor being configured to:

capture an image of an object contacting the fingerprint sensor; and

the processing unit being configured to;

determine an intensity for a plurality of pixels of the captured image;

compute, for each of said plurality of pixels of the captured image, a Hessian matrix where the components of the Hessian matrix consist of second-order derivatives of the pixel intensity in the captured image;

compute the square of the Hessian matrix;

compute a squared Fractional Anisotropy, FA, measure using eigenvalues of the computed Hessian matrix; and

determine from the squared FA measure if local pixel intensity variation is dominated by a single direction, in which case the object on the fingerprint sensor is considered to constitute a finger.

11. The fingerprint sensing system of claim 10, wherein the processing unit further is configured to compute the components of the Hessian matrix by convolving the captured image with a first filter in an x-direction, convolving the captured image with a second filter in a y-direction, and convolving the captured image with a third filter in the x-direction and then convolving the result of the convolution with the third filter with a fourth filter in the y-direction.

12. The fingerprint sensing system of claim 10, wherein the processing unit further is configured to:

compute trace and determinant of the Hessian matrix to derive its eigenvalues.

13. The fingerprint sensing system of claim 10, wherein the processing unit further is configured to:

compute a fingerprint qualification score as a linear combination of all the FA measure values for said plurality of pixels normalized by the number of said plurality of pixels.

14. The fingerprint sensing system of claim 13, wherein the processing unit further is configured to:

compare the computed fingerprint qualification score to a threshold value, wherein the local pixel intensity variation is considered to be dominated by a single direction if the fingerprint qualification score exceeds the threshold value.

15. The fingerprint sensing system of claim 10, wherein the processing unit further is configured to:

downsample the captured image.

16. The fingerprint sensing system of claim 10, wherein the processing unit further is configured to:

perform smoothing filtering of the captured image.

17. The fingerprint sensing system of claim 10, wherein the processing unit further is configured to:

perform smoothing filtering of each component of the square of the Hessian matrix.

18. The fingerprint sensing system of claim 10, further comprising a memory configured to store authorised fingerprint templates,

the processing unit being configured to:

compare a fingerprint of the captured image of the finger with one or more of the authorised fingerprint templates stored in the memory; and

authenticate a user to which the finger belongs if the fingerprint of the captured image is considered to match one or more of the authorised fingerprint templates.

19. An electronic device comprising the fingerprint sensing system of claim 10, the electronic device being configured to perform at least one action upon authentication of the user.