On-screen optical fingerprint capture for user authentication

• US 10,169,637 B2
• Filed: 10/18/2016
• Issued: 01/01/2019
• Est. Priority Date: 10/19/2015
• Status: Active Grant

• Current Assignee: Qualcomm, Inc.
• Original Assignee: Qualcomm, Inc.
• Inventors: Seo, Hae-Jong, Wyrwas, John
• Primary Examiner(s): Tran, Phuoc
• Application Number:
  US15/297,088
• Publication Number:
  US 20170109564A1
• Time in Patent Office: 805 Days
• CPC Class Codes: G06V 40/1347 Preprocessing; Feature extraction
• CPC Class Codes: G06V 40/1365 Matching; Classification

Abstract

Example methods, systems, computer-readable media, and apparatuses for on-screen optical fingerprint capture for user authentication are presented. These allow for the authentication of a fingerprint where the fingerprint image is propagated in a glass layer before being captured by a camera. In some examples, such propagation can result in multiple fingerprint images resulting from total internal reflection within the glass layer. Feature information can then be determined from the captured image of the fingerprint, which can include multiple fingerprint images. The amount of feature information can then be reduced. A histogram associated with the captured image based on the reduced number of features can be generated, and a user can be authenticated based on the histogram.

Claims

1. A method comprising:

receiving an image of a fingerprint captured by a camera, the image of the fingerprint being based on light reflected from a fingertip and propagated within a glass layer of a display assembly;

determining feature information from the captured image of the fingerprint;

reducing the amount of feature information through a quantization of the feature information;

generating a histogram associated with the captured image based on the reduced amount of feature information; and

authenticating a user based on the histogram.

2. The method of claim 1, wherein authenticating the user comprises providing the histogram to a machine learning algorithm and, responsive to providing the histogram to the machine learning algorithm, receiving a label from the machine learning algorithm.

3. The method of claim 2, wherein the label comprises one of a user name or an indication that the histogram was not recognized.

4. The method of claim 2, wherein the machine learning algorithm comprises one of a Random Forest classifier or a Support Vector Machine.

5. The method of claim 2, further comprising training the machine learning algorithm, wherein training the machine learning algorithm comprises providing the histogram and a label associated with the histogram to the machine learning algorithm.

6. The method of claim 1, wherein the captured image of the fingertip includes two or more fingertip images, each fingertip image having a different perspective of the fingertip.

7. The method of claim 1, further comprising:

receiving an image of a second fingerprint based on second propagating reflected light from a second fingertip, the receiving the image of the second fingerprint occurring at a time later than the receiving the captured image of the fingertip;

determining second feature information from the captured image of the second fingerprint;

reducing the amount of second feature information through a quantization of the second feature information;

generating a second histogram associated with the captured image of the second fingerprint based on the reduced amount of second feature information;

recognizing a user based on the second histogram or identifying no recognized user based on the second histogram; and

in response to recognizing an unauthorized user or not recognizing the second fingerprint, securing a computing device.

8. A computing device comprising:

a non-transitory computer-readable medium;

a processor in communication with the non-transitory computer-readable medium; and

a display assembly in communication with the processor, the display assembly comprising a glass layer; and

a camera comprising an image sensor, the image sensor oriented to receive light propagated within the glass layer of the display assembly; and

wherein the processor is configured to;

receive an image of a fingerprint from the camera, the image based on the propagated light within the glass layer;

determine feature information from the captured image of the fingerprint;

reduce the amount of feature information through a quantization of the feature information;

generate a histogram associated with the captured image based on the reduced amount of feature information; and

authenticate a user based on the histogram.

9. The computing device of claim 8, wherein the processor is further configured to provide the histogram to a machine learning algorithm and, responsive to providing the histogram to the machine learning algorithm, receive a label from the machine learning algorithm to authenticate the user.

10. The computing device of claim 9, wherein the label comprises one of a user name or an indication that the histogram was not recognized.

11. The computing device of claim 9, wherein the machine learning algorithm comprises one of a Random Forest classifier or a Support Vector Machine.

12. The computing device of claim 9, wherein the processor is further configured to provide histograms and labels associated with the histograms to the machine learning algorithm to train the machine learning algorithm.

13. The computing device of claim 8, wherein the captured image of the fingertip includes two or more fingertip images, each fingertip image having a different perspective of the fingertip.

14. The computing device of claim 8, wherein the processor is further configured to:

receive an image of a second fingerprint based on second propagating reflected light from a second fingertip, the image of the second fingerprint received after the image of the fingerprint;

determine second feature information from the captured image of the second fingerprint;

reduce the amount of second feature information through a quantization of the second feature information;

generate a second histogram associated with the captured image of the second fingerprint based on the reduced amount of second feature information;

recognize a user based on the second histogram or identify no recognized user based on the second histogram; and

in response to recognizing an unauthorized user or not recognizing the second fingerprint, secure the computing device.

15. An apparatus comprising:

means for propagating light within a display assembly;

means for capturing an image based on light received from the means for propagating light within a display assembly;

means for directing the propagating light onto the means for capturing an image;

means for determining feature information from the captured image of a fingerprint;

means for reducing the amount of feature information through a quantization of the feature information;

means for generating a histogram associated with the captured image based on the reduced amount of feature information; and

means for authenticating a user based on the histogram.

16. The apparatus of claim 15, wherein the means for authenticating the user comprises means for providing a label.

17. The apparatus of claim 16, wherein the label comprises one of a user name or an indication that the histogram was not recognized.

18. The apparatus of claim 16, wherein the means for authenticating comprises one of a Random Forest classifier or a Support Vector Machine.

19. The apparatus of claim 16, further comprising means for training the means for authenticating based on histograms and labels associated with the histograms.

20. The apparatus of claim 15, further comprising means for touch input coupled to the means for propagating light.

21. The apparatus of claim 15, further comprising means for securing a computing device in response to not authenticating the user.

22. The apparatus of claim 15, wherein the captured image includes two or more fingertip images, each fingertip image having a different perspective of the fingertip.

23. The apparatus of claim 15, further comprising:

means for receiving an image of a second fingerprint based on second propagating reflected light from a second fingertip, the receiving the image of the second fingerprint occurring at a time later than the receiving the captured image of the fingertip;

means for determining second feature information from the captured image of the second fingerprint;

means for reducing the amount of second feature information through a quantization of the second feature information;

means for generating a second histogram associated with the captured image of the second fingerprint based on the reduced amount of second feature information;

means for recognizing a user based on the second histogram or identifying no recognized user based on the second histogram; and

means for, in response to recognizing an unauthorized user or not recognizing the second fingerprint, securing a computing device.

24. A non-transitory computer-readable medium comprising processor-executable instructions configured to cause a processor to:

receive an image of a fingerprint based on light reflected from a fingertip;

determine feature information from the captured image of the fingerprint;

reduce the amount of feature information through a quantization of the feature information;

generate a histogram associated with the captured image based on the reduced amount of feature information; and

authenticate a user based on the histogram.

25. The non-transitory computer-readable medium of claim 24, wherein the processor-executable instructions are further configured to provide the histogram to a machine learning algorithm and, responsive to providing the histogram to the machine learning algorithm, receive a label from the machine learning algorithm to authenticate the user.

26. The non-transitory computer-readable medium of claim 25, wherein the label comprises one of a user name or an indication that the histogram was not recognized.

27. The non-transitory computer-readable medium of claim 25, wherein the machine learning algorithm comprises one of a Random Forest classifier or a Support Vector Machine.

28. The non-transitory computer-readable medium of claim 25, wherein the processor-executable instructions are further configured to provide the histogram and a first label associated with the histogram to the machine learning algorithm and to train the machine learning algorithm based on the histogram and the label.

29. The non-transitory computer-readable medium of claim 24, wherein the captured image of the fingertip includes two or more fingertip images, each fingertip image having a different perspective of the fingertip.

30. The non-transitory computer-readable medium of claim 24, wherein the processor-executable instructions are further configured to:

receive an image of a second fingerprint based on second propagating reflected light, the image of the second fingerprint received after the image of the fingerprint;

determine second feature information from the captured image of the second fingerprint;

reduce the amount of second feature information through a quantization of the second feature information;

generate a second histogram associated with the captured image of the second fingerprint based on the reduced amount of second feature information;

recognize a user based on the second histogram or identifying no recognized user based on the second histogram; and

in response to not recognizing a user based on the second histogram or identifying no recognized user based on the second histogram, secure a computing device.