Methods and systems for authenticating users

• US 10,084,776 B2
• Filed: 04/04/2016
• Issued: 09/25/2018
• Est. Priority Date: 04/04/2016
• Status: Active Grant

• Current Assignee: Corporation DAON Technology
• Original Assignee: Daon Holdings Limited
• Inventors: Ionita, Mircea, Peirce, Michael, Ahern, James, Watson, Michael Stephen
• Primary Examiner(s): Plecha, Thaddeus J
• Application Number:
  US15/089,608
• Publication Number:
  US 20170289144A1
• Time in Patent Office: 904 Days
• CPC Class Codes: G06F 21/32 using biometric data, e.g. fingerprints, iris scans or voiceprints
• CPC Class Codes: G06F 21/629 to features or functions of an application
• CPC Class Codes: G06F 2221/2103 Challenge-response
• CPC Class Codes: G06V 40/167 using comparisons between temporally consecutive images
• CPC Class Codes: G06V 40/172 Classification, e.g. identification
• CPC Class Codes: G06V 40/45 Detection of the body part being alive
• CPC Class Codes: H04L 63/0861 using biometrical features, e.g. fingerprint, retina-scan cryptographic mechanisms or cryptographic arrangements for entity authentication using biological data H04L9/3231
• CPC Class Codes: H04L 63/1483 service impersonation, e.g. phishing, pharming or web spoofing detection of rogue wireless access points H04W12/12

Abstract

A method of authenticating users is provided that includes storing data in a buffer. The data is within a temporal window and includes biometric data extracted from frames included in a video and quality feature values calculated for each frame. Each quality feature value corresponds to a different quality feature. Moreover, the method includes calculating a score for each different quality feature using the corresponding quality feature values, and determining a most recent frame included in the video includes biometric data usable in a biometric authentication matching transaction when the calculated score for each different quality feature satisfies a respective threshold score value.

Claims

1. A method for determining an image is a genuine image of a user comprising:

capturing in a sequence of frames during a remotely conducted biometric authentication transaction, by a computing device, images of a biometric modality of the user while the user responds to a challenge displayed by the computing device;

extracting the images of the biometric modality from the frames in the sequence;

calculating quality feature values for the frames from which the images were extracted, each quality feature value corresponding to a different quality feature;

storing the extracted images and quality feature values in a buffer of the computing device, the images and quality feature values being within a temporal window of the buffer, the temporal window having a length determined based on the challenge;

calculating a score for each different quality feature using the corresponding quality feature values; and

determining, by the computing device, a most recent frame in the sequence includes a genuine image of the user when the calculated score for each different quality feature satisfies a respective threshold score value.

2. A method for determining an image is a genuine image of a user in accordance with claim 1 further comprising storing the genuine image in the buffer.

3. A method for determining an image is a genuine image of a user in accordance with claim 1 further comprising:

calculating a weighted sum for the most recently captured frame;

comparing the calculated weighted sum against a weighted sum for a stored best quality image;

determining the genuine image is a better quality than the stored best quality image when the calculated weighted sum is greater than the stored best quality image weighted sum; and

replacing the stored best quality image with the genuine image.

4. A method for determining an image is a genuine image of a user in accordance with claim 1 further comprising

determining whether the user successfully responded to the challenge using an eye-blink based liveness detection algorithm.

5. A computing device for determining an image is a genuine image of a user comprising:

a processor; and

a memory configured to store a buffer of data, said device being associated with a network and said memory being in communication with said processor and having instructions stored thereon which, when executed by said processor, cause said computing device to;

capture in a sequence of frames, during a remotely conducted authentication transaction, images of a biometric modality of the user while the user responds to a challenge displayed by said computing device;

extract the images of the biometric modality from the frames in the sequence;

calculate quality feature values for the frames from which the images were extracted, each quality feature value corresponding to a different quality feature;

store the extracted images and quality feature values in the buffer, the images and quality feature values being within a temporal window of the buffer, the temporal window having a length determined based on the challenge;

calculate a score for each different quality feature using the corresponding quality features values; and

determine a most recent frame in the sequence includes a genuine image of the user when the calculated score for each different quality feature satisfies a respective threshold score value.

6. A computing device in accordance with claim 5, wherein the instructions when read and executed by said processor further cause said computing device to store the genuine image in the buffer.

7. A computing device in accordance with claim 5, wherein the instructions when read and executed by said processor further cause said computing device to:

calculate a weighted sum for the most recently captured frame;

compare the calculated weighted sum against a weighted sum for a stored best quality image;

determine the genuine image is a better quality than the stored best quality image when the calculated weighted sum is greater than the stored best quality image weighted sum; and

replace the stored best quality image with the genuine image.

8. A computing device in accordance with claim 5, wherein the instructions when read and executed by said processor further cause said computing device to

determine whether the user successfully responded to the challenge using an eye-blink based liveness detection algorithm.

9. A computer program recorded on a non-transitory computer-readable recording medium included in a computing device for determining an image is a genuine image of a user, the computer program being comprised of instructions, which when read and executed by the computing device, cause the computing device to:

capture in a sequence of frames, during a remotely conducted authentication transaction, images of a biometric modality of the user while the user responds to a challenge displayed by the computing device;

extract the images of the biometric modality from the frames in the sequence;

calculate quality feature values for the frames from which the images were extracted, each quality feature value corresponding to a different quality feature;

store the extracted images and quality feature values in a buffer of the computing device, the images and the quality feature values being within a temporal window of the buffer, the temporal window having a length determined based on the challenge;

calculate a score for each different quality feature using the corresponding quality features values; and

determine a most recent frame included in the sequence includes a genuine image of the user when the calculated score for each different quality feature satisfies a respective threshold score value.

10. A computer program in accordance with claim 9 further comprising instructions, which when read and executed by the computing device cause the computing device to store the genuine image in the buffer.

11. A computer program in accordance with claim 9 further comprising instructions, which when read and executed by the computing device cause the computing device to:

calculate a weighted sum for the most recently captured frame;

compare the calculated weighted sum against a weighted sum for a stored best quality image;

determine the genuine image is a better quality than the stored best quality image when the calculated weighted sum is greater than the stored best quality image weighted sum; and

replace the stored best quality image with the genuine image.

12. A computer program in accordance with claim 9 further comprising instructions, which when read and executed by the computing device cause the computing device to

determine whether the user successfully responded to the challenge using an eye-blink based liveness detection algorithm.