Spoofing detection in image biometrics
System and techniques for spoofing detection in image biometrics are described herein. A sequence of images may be obtained from a camera; a first plurality of images in the sequence of images including a representation of a user body part, and a second plurality of images in the sequence of images including a representation of an environment of the user. A marker may be created for the representation of the body part. A feature of the environment of the user present during the second plurality of images may be identified in the sequence of images using a third group of circuits. A correlation between the marker and the feature of the environment in the sequence of images may be quantified to produce a synchronicity metric of the degree to which the marker and the feature of the environment correlate.
1. A system for spoofing detection in image biometrics, the method comprising:
a camera to obtain a sequences of images, a first plurality of images in the sequence of images including a representation of a user body part, and a second plurality of images in the sequence of images including a representation of an environment of the user, the environment being a three-dimensional space that is within a field of view of the camera;
a biometric feature detector to:
create a marker for the representation of the body part, the marker corresponding to a feature in the representation of the body part; and
track a gaze of an eye from the representation of the body part via user eyelid positions;
an environmental feature detector to identify a feature of the environment of the user present during the second plurality of images in the sequence of images;
a synchronicity detector to quantify a correlation between the marker and the feature of the environment in the sequence of images to produce a synchronicity metric of the degree to which the marker and the feature of the environment correlate; and
a spoofing indication controller to provide a spoofing attempt indication in response to the synchronicity metric being beyond a threshold.
2. The system of claim 1 wherein to identify the feature of the environment includes an emitter of the system to emit a pattern into the environment.
3. The system of claim 2 , wherein to emit the pattern includes the emitter to emit a non-uniform pattern in a visible light spectrum.
4. The system of claim 3 , wherein the non-uniform pattern is a moving pattern.
5. The system of claim 4 , wherein:
the synchronicity detector is to measure the degree to which the gaze tracks the moving pattern; and
the spoofing indication controller is to provide a second spoofing attempt indication in response to the degree to which the gaze tracks the moving pattern meets a predetermined range.
6. The system of claim 5 , the system is to perform a calibration session including:
presenting a moving prompt;
capturing a second sequence of images during presentation of the moving prompt;
measuring a correspondence of second user eyelid positions to the moving prompt from the second sequence of images;
using the correspondence as the threshold.
7. The system of claim 5 , wherein the gaze of the eye is determined by measuring the amount of iris visible for the eye.
8. A method for spoofing detection in image biometrics, the method comprising:
obtaining a sequences of images from a camera using computer hardware, a first plurality of images in the sequence of images including a representation of a user body part, and a second plurality of images in the sequence of images including a representation of an environment of the user, the environment being a three-dimensional space that is within a field of view of the camera;
creating a marker for the representation of the body part using the computer hardware, the marker corresponding to a feature in the representation of the body part;
tracking a gaze of an eye from the representation of the body part via user eyelid positions;
identifying a feature of the environment of the user present during the second plurality of images in the sequence of images using the computer hardware;
quantifying, using the computer hardware, a correlation between the marker and the feature of the environment in the sequence of images to produce a synchronicity metric of the degree to which the marker and the feature of the environment correlate; and
providing, using the computer hardware, a spoofing attempt indication in response to the synchronicity metric being beyond a threshold.
9. The method of claim 8 wherein identifying the feature of the environment includes emitting a pattern into the environment.
10. The method of claim 9 , wherein emitting the pattern includes emitting a non-uniform pattern in a visible light spectrum.
11. The method of claim 10 , wherein the non-uniform pattern is a moving pattern.
12. The method of claim 11 , further comprising:
measuring the degree to which the gaze tracks the moving pattern; and
providing a second spoofing attempt indication in response to the degree to which the gaze tracks the moving pattern meets a predetermined range.
13. The method of claim 12 , comprising a calibration session including:
presenting a moving prompt;
capturing a second sequence of images during presentation of the moving prompt;
measuring a correspondence of second user eyelid positions to the moving prompt from the second sequence of images;
using the correspondence as the threshold.
14. The method of claim 12 , wherein the gaze of the eye is determined by measuring the amount of iris visible for the eye.
15. At least one non-transitory machine readable medium including instructions for spoofing detection in image biometrics, the instructions, when executed by circuitry, cause the circuitry to perform operations comprising:
obtaining a sequences of images from a camera, a first plurality of images in the sequence of images including a representation of a user body part, and a second plurality of images in the sequence of images including a representation of an environment of the user;
creating a marker for the representation of the body part, the marker corresponding to a feature in the representation of the body part;
tracking a gaze of an eye from the representation of the body part via user eyelid positions;
identifying a feature of the environment of the user present during the second plurality of images in the sequence of images;
quantifying a correlation between the marker and the feature of the environment in the sequence of images to produce a synchronicity metric of the degree to which the marker and the feature of the environment correlate; and
providing a spoofing attempt indication in response to the synchronicity metric being beyond a threshold.
16. The at least one machine readable medium of claim 15 wherein identifying the feature of the environment includes emitting a pattern into the environment.
17. The at least one machine readable medium of claim 16 , wherein emitting the pattern includes emitting a non-uniform pattern in a visible light spectrum.
18. The at least one machine readable medium of claim 17 , wherein the nonuniform pattern is a moving pattern.
19. The at least one machine readable medium of claim 18 , wherein the operations further comprise:
measuring the degree to which the gaze tracks the moving pattern; and
providing a second spoofing attempt indication in response to the degree to which the gaze tracks the moving pattern meets a predetermined range.
20. The at least one machine readable medium of claim 19 , wherein the operations further comprise a calibration session including:
presenting a moving prompt;
capturing a second sequence of images during presentation of the moving prompt;
measuring a correspondence of second user eyelid positions to the moving prompt from the second sequence of images;
using the correspondence as the threshold.