Spoof detection using catadioptric spatiotemporal corneal reflection dynamics
Methods, systems, and computer-readable storage media for determining that a subject is a live person include obtaining, by an image capture device, a set of subject images. Each image is captured at a different corresponding relative location of the image capture device with respect to the subject. Parameters are determined from the set of images of the subject. The parameters represent corneal reflections of at least one object in at least one eye of the subject. A determination is made, based on the parameters, that the subject is a live person. Responsive to determining that the subject is a live person, an authentication process is initiated to authenticate the subject.
1. A computer-implemented method comprising:
obtaining, by an image capture device, a set of at least two images of a subject, wherein each image in the set is captured at a different corresponding relative location of the image capture device with respect to the subject;
determining, from the set of images of the subject, one or more parameters representing corneal reflections of at least one object in at least one eye of the subject;
determining, based on the one or more parameters, that the subject is a live person; and
in response to determining that the subject is a live person, initiating an authentication process to authenticate the subject.
2. The computer-implemented method of claim 1 , wherein the one or more parameters comprise a reflection size.
3. The computer-implemented method of claim 1 , wherein determining the one or more parameters comprises:
determining a first size of a reflection of the at least one object in a first image of particular eye of the subject, the first image being included in the set of the at least two images and captured with the image capture device being at a first distance from the particular eye; and
determining a second size of a reflection of the at least one object in a second image of the particular eye, the second image being included in the set of the at least two images and captured with the image capture device being at a second distance from the particular eye, the second distance being different from the first distance.
4. The computer-implemented method of claim 3 , wherein determining that the subject is a live person comprises:
determining that the first size is different from the second size; and
determining that the subject is a live person responsive to determining that the first size is different from the second size.
5. The computer-implemented method of claim 1 , wherein determining the one or more parameters comprises:
determining a first separation between the corneal reflections of the at least one object in the two eyes of the subject in a first image, the first image being included in the set of the at least two images and captured with the image capture device being at a first relative location with respect to the subject;
computing a first parameter of the one or more parameters as a function of a ratio of the first separation to an inter-ocular distance measured from the first image;
determining a second separation between the corneal reflections of the at least one object in the two eyes of the subject in a second image, the second image being included in the set of the at least two images and captured with the image capture device being at a second relative location with respect to the subject; and
computing a second parameter of the one or more parameters as a function of a ratio of the second separation to an inter-ocular distance measured from the second image.
6. The computer-implemented method of claim 5 , wherein determining that the subject is a live person comprises:
determining that the first parameter is different from the second parameter; and
determining that the subject is a live person responsive to determining that the first parameter is different from the second parameter.
7. The computer-implemented method of claim 1 , wherein determining that the subject is the live person comprises processing the set of the at least two images of the subject using a machine learning process trained to discriminate between live persons and alternative representations of the live persons based on the one or more parameters.
8. A non-transitory, computer-readable medium storing one or more instructions executable by a computer system to perform operations comprising:
capturing, by an image capture device, a set of at least two images of a subject, wherein each image in the set is captured at a different corresponding relative location of the image capture device with respect to the subject;
determining, from the set of images of the subject, one or more parameters representing corneal reflections of at least one object in at least one eye of the subject;
determining, based on the one or more parameters, that the subject is a live person; and
in response to determining that the subject is a live person, initiating an authentication process to authenticate the subject.
9. The non-transitory, computer-readable medium of claim 8 , wherein the one or more parameters comprise a reflection size.
10. The non-transitory, computer-readable medium of claim 8 , wherein determining the one or more parameters comprises:
determining a first size of a reflection of the at least one object in a first image of a particular eye of the subject, the first image being included in the set of the at least two images and captured with the image capture device being at a first distance from the particular eye; and
determining a second size of a reflection of the at least one object in a second image of the particular eye, the second image being included in the set of the at least two images and captured with the image capture device being at a second distance from the particular eye, the second distance being different from the first distance.
11. The non-transitory, computer-readable medium of claim 10 , wherein determining that the subject is a live person comprises:
determining that the first size is different from the second size; and
determining that the subject is a live person responsive to determining that the first size is different from the second size.
12. The non-transitory, computer-readable medium of claim 8 , wherein determining the one or more parameters comprises:
determining a first separation between the corneal reflections of the at least one object in the two eyes of the subject in a first image, the first image being included in the set of the at least two images and captured with the image capture device being at a first relative location with respect to the subject;
computing a first parameter of the one or more parameters as a function of a ratio of the first separation to an inter-ocular distance measured from the first image;
determining a second separation between the corneal reflections of the at least one object in the two eyes of the subject in a second image, the second image being included in the set of the at least two images and captured with the image capture device being at a second relative location with respect to the subject; and
computing a second parameter of the one or more parameters as a function of a ratio of the second separation to an inter-ocular distance measured from the second image.
13. The non-transitory, computer-readable medium of claim 12 , wherein determining that the subject is a live person comprises:
determining that the first parameter is different from the second parameter; and
determining that the subject is a live person responsive to determining that the first parameter is different from the second parameter.
14. The non-transitory, computer-readable medium of claim 8 , wherein determining that the subject is the live person comprises processing the set of the at least two images of the subject using a machine learning process trained to discriminate between live persons and alternative representations of the live persons based on the one or more parameters.
15. A computer-implemented system, comprising:
one or more computers; and
one or more computer memory devices interoperably coupled with the one or more computers and having tangible, non-transitory, machine-readable media storing one or more instructions that, when executed by the one or more computers, perform operations comprising:
capturing, by an image capture device, a set of at least two images of a subject, wherein each image in the set is captured at a different corresponding relative location of the image capture device with respect to the subject;
determining, from the set of images of the subject, one or more parameters representing corneal reflections of at least one object in at least one eye of the subject;
determining, based on the one or more parameters, that the subject is a live person; and
in response to determining that the subject is a live person, initiating an authentication process to authenticate the subject.
16. The computer-implemented system of claim 15 , wherein the one or more parameters comprise a reflection size.
17. The computer-implemented system of claim 15 , wherein determining the one or more parameters comprises:
determining a first size of a reflection of the at least one object in a first image of a particular eye of the subject, the first image being included in the set of the at least two images and captured with the image capture device being at a first distance from the particular eye; and
determining a second size of a reflection of the at least one object in a second image of the particular eye, the second image being included in the set of the at least two images and captured with the image capture device being at a second distance from the particular eye, the second distance being different from the first distance.
18. The computer-implemented system of claim 17 , wherein determining that the subject is a live person comprises:
determining that the first size is different from the second size; and
determining that the subject is a live person responsive to determining that the first size is different from the second size.
19. The computer-implemented system of claim 15 , wherein determining the one or more parameters comprises:
determining a first separation between the corneal reflections of the at least one object in the two eyes of the subject in a first image, the first image being included in the set of the at least two images and captured with the image capture device being at a first relative location with respect to the subject;
computing a first parameter of the one or more parameters as a function of a ratio of the first separation to an inter-ocular distance measured from the first image;
determining a second separation between the corneal reflections of the at least one object in the two eyes of the subject in a second image, the second image being included in the set of the at least two images and captured with the image capture device being at a second relative location with respect to the subject; and
computing a second parameter of the one or more parameters as a function of a ratio of the second separation to an inter-ocular distance measured from the second image.
20. The computer-implemented system of claim 19 , wherein determining that the subject is a live person comprises:
determining that the first parameter is different from the second parameter; and
determining that the subject is a live person responsive to determining that the first parameter is different from the second parameter.