Methods and systems for determining user liveness and verifying user identities

A computing device for verifying an identity of a user comprising:

• a processor;
• and
• a memory configured to store data, said computing device being associated with a network and said memory being in communication with said processor and having instructions stored thereon which, when read and executed by said processor, cause said computing device to:
• generate parameters for each processed frame in a video of a biometric modality of -the user, each of the parameters being different and resulting from movement of said computing device during capture of the video;
• create a signal for each of the parameters;
• store each of the created signals with previously stored signals for the respective parameter;
• create a classification model for the user from the stored created signals and the previously stored signals;
• normalize each of the created signals;
• calculate a correlation coefficient between the normalized signals, the correlation coefficient indicating a similarity between the created signals;
• determine the user is live when the correlation coefficient is at least equal to a threshold score;
• calculate, using the classification model, a confidence score for at east one of the created signals;
• and
• verify the identity of the user as true when the confidence score is at east equal to a threshold score.

A non-transitory computer-readable recording medium included in a computing device having a computer program recorded thereon for verifying an identity of a user, the computer program being comprised of instructions, which when read and executed by a processor included in the computing device, cause the computing device to:

• generate parameters for each processed frame in a video of a biometric modality of the user, each of the parameters being different and resulting from movement of the computing device during capture of the video;
• create a signal for each of the parameters;
• store each of the created signals with previously stored signals for the respective parameter;
• create a classification model for the user from the stored created signals and the previously stored signals;
• normalize each of the created signals;
• calculate a correlation coefficient between the normalized signals, the correlation coefficient indicating a similarity between the created signals;
• determine the user is live when the correlation coefficient is at least equal to a threshold score;
• calculate, using the classification model, a confidence score for at east one of the created signals;
• and
• verify the identity of the user as true when the confidence score is at least equal to a threshold score.