Methods and systems for authenticating users
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.
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.