Systems and methods for passive-subject liveness verification in digital media
The present system may be deployed in various scenarios to provide proof of liveness (also referred to herein as “liveness verification”) of an image without interaction of the subject of the image. The liveness verification process generally comprises imperative analysis and dynamic analysis of the image, after which liveness of the image may be determined.
1. A method of verifying liveness of a subject shown in an image, comprising the steps of:
receiving an image from an electronic computing device for liveness verification, wherein the image purports to show the face of the subject;
performing imperative analysis on the received image;
performing dynamic analysis on the received image; and
determining liveness based on the performed imperative analysis and the performed dynamic analysis.
2. The method of claim 1 , wherein performing dynamic analysis on the received image further comprises analyzing the image to determine that at least one of the following regarding the image is within a predetermined range: diffusion speed, contrast, blurriness, specularity, texture analysis, frequency analysis, or gamut differences.
3. The method of claim 2 , wherein the subject is a user of the electronic computing device attempting to access a third party system via the electronic computing device, further comprising the step of, upon verifying liveness, permitting the user to access the third party system via the electronic computing device.
4. The method of claim 3 , wherein the third party system comprises an email client, a banking system, a software system, a SaaS platform, a website, a smartphone, a computer, a watch, an ATM, a vehicle, or a building.
5. The method of claim 2 , wherein the electronic computing device further comprises a camera with a flash that captures the image.
6. The method of claim 5 , wherein prior to determining specularity, the electronic computing device receives a signal for engaging the flash for illuminating the subject's face.
7. The method of claim 1 , wherein performing texture analysis on the image comprises:
converting the image to generate a grayscale version of the image;
cropping the grayscale version of the image, wherein the cropped grayscale version of the image comprises only the subject's face; and
generating a resized image from the cropped grayscale version of the image, wherein the resized image is larger than the cropped grayscale version of the image.
8. The method of claim 7 , wherein performing frequency analysis comprises computing a fast fourier transform on the resized image.
9. The method of claim 1 , wherein performing imperative analysis comprises performing contour detection on the image for determining that the image does not comprise a frame surrounding a face.
10. The method of claim 9 , wherein performing contour detection comprises:
extracting one or more contours from the image, wherein the one or more extracted contours generally surround the face; and
determining that each of the one or more extracted contours does not comprise at least four corners with angles approximately 90 degrees.
11. A system for verifying liveness of a subject shown in an image, comprising:
an electronic computing device that transmits an image for liveness verification to a server, wherein the image purports to show the face of the subject; and
the server that receives the image for liveness verification, wherein the server performs imperative analysis on the received image, and performs dynamic analysis on the received image, to determine liveness of the subject based on the performed imperative analysis and the performed dynamic analysis.
12. The system of claim 11 , wherein performing dynamic analysis on the received image further comprises analyzing the image to determine that at least one of the following regarding the image is within a predetermined range: diffusion speed, contrast, blurriness, specularity, texture analysis, frequency analysis, or gamut differences.
13. The system of claim 12 , wherein the subject is a user of the electronic computing device attempting to access a third party system via the electronic computing device, further comprising the step of, upon verifying liveness, permitting the user to access the third party system via the electronic computing device.
14. The system of claim 13 , wherein the third party system comprises an email client, a banking system, a software system, a SaaS platform, a website, a smartphone, a computer, a watch, an ATM, a vehicle, or a building.
15. The system of claim 12 , wherein the electronic computing device further comprises a camera with a flash that captures the image.
16. The system of claim 15 , wherein prior to determining specularity, the electronic computing device receives a signal for engaging the flash for illuminating the subject's face.
17. The system of claim 11 , wherein performing texture analysis on the image comprises:
converting the image to generate a grayscale version of the image;
cropping the grayscale version of the image, wherein the cropped grayscale version of the image comprises only the subject's face; and
generating a resized image from the cropped grayscale version of the image, wherein the resized image is larger than the cropped grayscale version of the image.
18. The system of claim 17 , wherein performing frequency analysis comprises computing a fast fourier transform on the resized image.
19. The system of claim 11 , wherein performing imperative analysis comprises performing contour detection on the image for determining that the image does not comprise a frame surrounding a face.
20. The system of claim 19 , wherein performing contour detection comprises:
extracting one or more contours from the image, wherein the one or more extracted contours generally surround the face; and
determining that each of the one or more extracted contours does not comprise at least four corners with angles approximately 90 degrees.