Image analysis for user authentication
A user can be authenticated to a mobile computing device using an authentication process that recognizes the user and verifies that an actual human being is attempting to be authenticated, in order to minimize the ability of another person to spoof the authentication process. A model of a user can be generated and stored in the cloud, enabling that model to be synchronized across various devices. A user accessing one of these devices can have infrared image information captured, which can be used with a facial recognition process, to recognize the user, and with a human verification process, to verify that the facial information corresponds to a human user. Various approaches such as visual analysis and thermal imaging can be used to verify that the human user being recognized is interactive with the device.
1. A mobile device, comprising:
a processor; and
memory storing instructions that, as a result of being executed by the processor, cause the mobile device to:
obtain a request to authorize a transaction;
illuminate, with an infrared light emitting diode, a user that is interacting with the mobile device;
use a camera on the mobile device to capture an infrared image of a portion of a face of the user;
analyze the infrared image to identify eyes of the user;
determine that the infrared image corresponds to a living being by analyzing a thermal characteristic of the eyes of the user;
identify the user based at least in part on the infrared image;
authenticate the user as a result of the identity of the user being recognized as an authorized user and as a result of the infrared image corresponding to a living being; and
allow the transaction to be performed as a result of the user being authenticated.
2. The mobile device of claim 1 , wherein the infrared image captures a reflection of infrared light emitted from the infrared light emitting diode.
3. The mobile device of claim 1 , wherein the instructions further cause the mobile device to:
obtain identifying information for an authorized user by performing a visual authentication enrollment process; and
authenticate the user as a result of the identity of the user being recognized as the authorized user associated with the identifying information.
4. The mobile device of claim 1 , wherein the infrared light emitting diode is on the mobile device.
5. The mobile device of claim 1 , wherein:
the camera is capable of capturing thermal information; and
the infrared image includes thermal imaging data.
6. A computer-implemented method of authenticating a user of a mobile device, comprising:
projecting an infrared light onto a user that is interacting with the mobile device;
capturing an infrared image of a portion of the user with a camera on the mobile device;
analyzing the infrared image to identify an eye of the user;
determining that the infrared image corresponds to a living being by analyzing a variance in a thermal characteristic of the eye;
identifying the user based at least in part on the infrared image; and
authenticating the user as a result of the identity of the user being recognized as an authorized user and as a result of the infrared image corresponding to a living being.
7. The computer-implemented method of claim 6 , wherein:
facial data of the user is collected as part of a visual authentication enrollment process;
facial data of the user is obtained from the infrared image using a facial recognition algorithm; and
the identity of the user is determined based at least in part on the facial data.
8. The computer-implemented method of claim 6 , further comprising directing the user to look at the camera on the mobile device.
9. The computer-implemented method of claim 6 , wherein the infrared light is projected using an infrared light emitting diode under the control of the mobile device.
10. The computer-implemented method of claim 6 , further comprising obtaining the infrared image from a sequence of images in a video stream.
11. The computer-implemented method of claim 6 , further comprising:
obtaining a second image of the user, the second image representing light captured from a visible spectrum; and
identifying the user based at least in part on the second image.
12. The computer-implemented method of claim 6 , further comprising:
detecting that the user is looking at the camera; and
initiating an authentication process as a result of detecting that the user is looking at the camera.
13. The computer-implemented method of claim 6 , further comprising:
capturing a sequence of images of the eye of the user;
detecting a blink of the eye based on the sequence of images; and
determining that the image represents a living being as a result of detecting the blink.
14. The computer-implemented method of claim 6 , further comprising presenting a signal to the user indicating that the user should look at the mobile device to perform an authentication process.
15. The computer-implemented method of claim 6 , further comprising:
obtaining a request to authorize a transaction; and
determining that the identified user is authorized to perform the transaction.
16. The computer-implemented method of claim 15 , further comprising denying the transaction as a result of determining that the image does not correspond to a physical being.
17. A non-transitory computer-readable storage medium storing instructions that, as a result of being executed by a processor on a mobile computing device, cause the mobile computing device to:
project an infrared light onto a user that is interacting with the mobile computing device;
capture an infrared image of a portion of the user with a camera on the mobile computing device;
analyze the infrared image to identify an eye of the user;
determine that the infrared image corresponds to a living being by analyzing a variance in a thermal characteristic of the eye;
identify the user based at least in part on the infrared image; and
authorize a request initiated by the user as a result of the user being recognized as an authorized user stored in memory on the mobile computing device and as a result of the image corresponding to a physical being.
18. The non-transitory computer-readable storage medium of claim 17 , wherein the instructions executable to further cause the mobile computing device to:
as part of a visual authentication enrolment process, project an infrared light on to a face of an authorized user;
capture a reflection of the infrared light from the eye of the user using the camera; and
store a characteristic of the eye.
19. The non-transitory computer-readable storage medium of claim 17 , wherein the instructions executable to further cause the mobile computing device to determine that the gaze of the user is directed at the device.
20. The non-transitory computer-readable storage medium of claim 17 , wherein the instructions executable to further cause the mobile computing device to:
obtain a request to authorize a transaction; and
deny the transaction as a result of determining that the image does not correspond to a physical being.