FACE IDENTIFICATION USING MULTIMODAL IMAGING DATA

1 . A device comprising:

an image capture device to obtain first imaging data;

a sensor; and

control logic coupled to the sensor, wherein the control logic is to:

obtain sensor data from the sensor;

generate second imaging data from the sensor data;

determine a first correlation metric between the first imaging data and the second imaging data;

determine whether the first correlation metric satisfies an authentication criterion; and

enable an authentication operation responsive to determining the first correlation metric satisfies the authentication criterion.

2 . The device of claim 1 , wherein the sensor comprises a Radio Detection and Ranging (RADAR) unit, and wherein to obtain sensor data the control logic is to:

determine a first path for the RADAR unit based on a first portion of the first imaging data; and

electronically steer the RADAR unit along the first path to capture a first portion of the sensor data with the RADAR unit.

3 . The device of claim 2 , wherein the control logic is further to:

determine whether the sensor data comprising the first portion of sensor data satisfies a quality criterion;

determine a second path for the RADAR unit based on third imaging data obtained from the image capture device responsive to determining that the sensor data does not satisfy the quality criterion; and

electronically steer the RADAR unit along the second path to capture a second portion of sensor data with the RADAR unit.

4 . The device of claim 3 , wherein to generate second imaging data from the sensor data, the control logic is to:

determine whether the sensor data comprising the first portion and the second portion of sensor data satisfies the quality criterion; and

indicate the second imaging data is to be generated using the sensor data comprising the first portion and the second portion of sensor data responsive to determining the sensor data satisfies the quality criterion.

5 . The device of claim 1 , wherein to determine the first correlation metric, the control logic is to:

determine first depth data from the first imaging data; and

determine second depth data from the second imaging data; and

wherein to determine whether the first correlation metric satisfies the authentication criterion, the control logic is to:

determine whether a difference between the first depth data and the second depth data is less than a discrepancy threshold, and

indicate that the authentication criterion is satisfied responsive to determining the difference is less than the discrepancy threshold.

6 . The device of claim 5 , wherein to determine first depth data from the first imaging data the control logic is to:

provide the first imaging data to a machine learning model trained to output three-dimensional (3D) imaging data based on a two-dimensional (2D) input;

obtain first 3D data as output from the machine learning model, wherein the first 3D data is generated by the machine learning model based on an input comprising the first imaging data; and

extract the first depth data from the first 3D data.

7 . The device of claim 1 , wherein to obtain sensor data from the sensor, the control logic is to:

determine whether the sensor data comprising a first portion of sensor data satisfies a quality criterion;

provide a notification to a user responsive to determining the sensor data does not satisfy the quality criterion;

obtain a second portion of sensor data;

determine whether the sensor data comprising the first portion and the second portion of sensor data satisfies the quality criterion; and

indicate the second imaging data is to be generated using the sensor data comprising the first portion and the second portion of sensor data responsive to determining the sensor data satisfies the quality criterion.

8 . The device of claim 1 , wherein the first imaging data comprises first facial data and first non-facial data and the second imaging data comprises second facial data and second non-facial data;

wherein to determine the first correlation metric between the first imaging data and the second imaging data, the control logic is to combine the first facial data with the second facial data to obtain user facial data; and

wherein to determine whether the first correlation metric satisfies the authentication criterion, the control logic is to:

determine whether a difference between the user facial data and a stored user facial data corresponding to an authenticated user is less than a discrepancy threshold, and

indicate that the authentication criterion is satisfied responsive to determining the difference is less than the discrepancy threshold.

9 . The device of claim 1 , wherein the control logic is further to:

receive an indication from the image capture device to begin capturing information with the sensor, wherein the information comprises the sensor data.

10 . The device of claim 1 , wherein the sensor is at least one of a Synthetic Aperture Radar (SAR) unit, a thermal imaging sensor unit, a Radio Detection and Ranging (RADAR) unit, a Sound Navigation and Ranging (SONAR) unit, an ultrasonic sensor unit, a hyperspectral imaging sensor unit, an electromagnetic field sensor unit, a radio frequency (RF) sensor unit, or a magnetic resonance imaging (MRI) unit.

11 . A system comprising:

a first sensor unit;

an image capture device; and

control logic coupled to the first sensor unit and the image capture device, wherein the control logic is to:

obtain first imaging data from the image capture device;

obtain first sensor data from the first sensor unit;

generate second imaging data from the first sensor data;

determine a first correlation metric between the first imaging data and the second imaging data;

determine whether the first correlation metric satisfies an authentication criterion; and

enable an authentication operation responsive to determining the first correlation metric satisfies the authentication criterion.

12 . The system of claim 11 , wherein the first sensor unit comprises a Radio Detection and Ranging (RADAR) unit, and wherein to obtain first sensor data the control logic is to:

determine a path for the RADAR unit based on the first imaging data; and

electronically steer the RADAR unit along the path to capture a first portion of the first sensor data with the RADAR unit.

13 . The system of claim 11 , wherein to determine the first correlation metric, the control logic is to:

determine first depth data from the first imaging data; and

determine second depth data from the second imaging data; and

wherein to determine whether the first correlation metric satisfies the authentication criterion, the control logic is to:

determine whether a difference between the first depth data and the second depth data is less than a discrepancy threshold, and

indicate that the authentication criterion is satisfied responsive to determining the difference is less than the discrepancy threshold.

14 . The system of claim 11 , wherein the first imaging data comprises first facial data and first non-facial data and the second imaging data comprises second facial data and second non-facial data;

wherein to determine the first correlation metric between the first imaging data and the second imaging data, the control logic is to combine the first facial data with the second facial data to obtain user facial data; and

wherein to determine whether the first correlation metric satisfies the authentication criterion, the control logic is to:

determine whether a difference between the user facial data and a stored user facial data corresponding to an authenticated user is less than a discrepancy threshold, and

indicate that the authentication criterion is satisfied responsive to determining the difference is less than the discrepancy threshold.

15 . The system of claim 11 further comprising a second sensor unit coupled to the control logic, wherein the control logic is to:

obtain second sensor data from the second sensor unit;

generate third imaging data from the second sensor data;

determine a second correlation metric between the first imaging data the second imaging data and the third imaging data;

determine whether the second correlation metric satisfies the authentication criterion; and

enable the authentication operation responsive to determining the second correlation metric satisfies the authentication criterion.

16 . The system of claim 11 , wherein the first sensor unit is at least one of a Synthetic Aperture Radar (SAR) unit, a thermal imaging sensor unit, a Radio Detection and Ranging (RADAR) unit, a Sound Navigation and Ranging (SONAR) unit, an ultrasonic sensor unit, a hyperspectral imaging sensor unit, an electromagnetic field sensor unit, a radio frequency (RF) sensor unit, or a magnetic resonance imaging (MRI) unit.

17 . A method comprising:

obtaining sensor data from a sensor;

generating sensor imaging data from the sensor data;

determining a first correlation metric between the sensor imaging data and imaging data obtained from an image capture device;

determining whether the first correlation metric satisfies an authentication criterion; and

enabling an authentication operation responsive to determining the first correlation metric satisfies the authentication criterion.

18 . The method of claim 17 , wherein the sensor comprises a Synthetic Aperture Radar (SAR) unit, and wherein obtaining sensor data from the sensor comprises:

determining a path for the RADAR unit based on the imaging data; and

electronically steering the RADAR unit along the path to capture a first portion of the sensor data with the RADAR unit.

19 . The method of claim 17 , wherein determining the first correlation metric comprises:

determining first depth data from the imaging data; and

determining second depth data from the sensor imaging data; and

wherein determining whether the first correlation metric satisfies the authentication criterion comprises:

determining whether a difference between the first depth data and the second depth data is less than a discrepancy threshold, and

indicating that the authentication criterion is satisfied responsive to determining the difference is less than the discrepancy threshold.

20 . The method of claim 17 , wherein obtaining sensor data from the sensor comprises:

determining whether the sensor data comprising a first portion of sensor data satisfies a quality criterion;

providing a notification to a user responsive to determining the sensor data does not satisfy the quality criterion;

obtaining a second portion of sensor data;

determining whether the sensor data comprising the first portion and the second portion of sensor data satisfies the quality criterion; and

indicating the sensor imaging data is to be generated using the sensor data comprising the first portion and the second portion of sensor data responsive to determining the sensor data satisfies the quality criterion.