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;
determining that the image is not monochromatic;
determining that the image does not comprise a frame surrounding the face; and
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, or gamut differences.
2. The method of claim 1 , wherein determining that the image is not monochromatic further comprises the steps of:
converting a first color space of the image to a second color space, wherein the second color space comprises two or more color components;
calculating a variance in the two or more color components; and
determining that the variance exceeds a predetermined threshold.
3. The method of claim 1 , wherein determining that the image does not comprise a frame surrounding the face further comprises the steps of:
extracting one or more contours from the image, wherein the one or more extracted contours generally surround the face;
determining that each of the one or more extracted contours does not comprise at least four corners with angles approximately 90°.
4. The method of claim 1 , wherein analyzing the image to determine the diffusion of the image is within the predetermined range further comprises determining that the diffusion of the image is within a predetermined uniformity range.
5. The method of claim 1 , wherein analyzing the image to determine that the contrast of the image is within the predetermined range further comprises the steps of:
converting the image to grayscale, wherein the converted images comprises a plurality of pixels each containing a contrast value;
detecting the face in the converted image, wherein the detected face comprises at least one eye;
aligning the at least one eye with a particular line;
cropping the aligned image to a particular size;
dividing the cropped image into a predetermined number of blocks for calculating a local contrast of each of the predetermined number of blocks, wherein the local contrast comprises a ratio of the maximum contrast value to the minimum contrast value within a particular block; and
determining that a majority of the calculated local contrasts exceeds a predetermined threshold.
6. The method of claim 1 , wherein analyzing the image to determine that the blurriness of the image is within the predetermined range further comprises determining that the blurriness does not exceed a predetermined threshold.
7. The method of claim 1 , wherein analyzing the image to determine that the specularity of the image is within the predetermined range further comprises determining that the specularity is not interrupted and exceeds a predetermined threshold.
8. The method of claim 1 , wherein analyzing the image to determine that the gamut differences of the image are within the predetermined range further comprises determining that the gamut differences exceed a predetermined threshold.
9. The method of claim 1 , wherein the electronic computing device further comprises a camera that captures the image.
10. The method of claim 1 , 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.
11. The method of claim 10 , 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.
12. A system of 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 determines that the image is not monochromatic, determines that the image does not comprise a frame surrounding the face, and analyzes the image to determine that at least one of the following regarding the image is within a predetermined range: diffusion speed, contrast, blurriness, specularity, or gamut differences.
13. The system of claim 12 , wherein the server, to determine that the image is not monochromatic:
converts a first color space of the image to a second color space, wherein the second color space comprises two or more color components;
calculates a variance in the two or more color components; and
determines that the variance exceeds a predetermined threshold.
14. The system of claim 12 , wherein the server, to determine that the image does not comprise a frame surrounding the face:
extracts one or more contours from the image, wherein the one or more extracted contours generally surround the face;
determines that each of the one or more extracted contours does not comprise at least four corners with angles approximately 90°.
15. The system of claim 12 , wherein the server, to analyze the image to determine that the diffusion of the image is within the predetermined range, determines that the diffusion of the image is within a predetermined uniformity range.
16. The system of claim 12 , wherein the server, to analyze the image to determine that the contrast of the image is within the predetermined range:
converts the image to grayscale, wherein the converted images comprises a plurality of pixels each containing a contrast value;
detects the face in the converted image, wherein the detected face comprises at least one eye;
aligns the at least one eye with a particular line;
crops the aligned image to a particular size;
divides the cropped image into a predetermined number of blocks for calculating a local contrast of each of the predetermined number of blocks, wherein the local contrast comprises a ratio of the maximum contrast value to the minimum contrast value within a particular block; and
determines that a majority of the calculated local contrasts exceeds a predetermined threshold.
17. The system of claim 12 , wherein the server, to analyze the image to determine that the blurriness of the image is within the predetermined range, determines that the blurriness does not exceed a predetermined threshold.
18. The system of claim 12 , wherein the server, to analyze the image to determine that the specularity of the image is within the predetermined range, determines that the specularity is not interrupted and exceeds a predetermined threshold.
19. The system of claim 12 , wherein the server, to analyze the image to determine that the gamut differences of the image are within the predetermined range, determines that the gamut differences exceed a predetermined threshold.
20. The system of claim 12 , wherein the electronic computing device further comprises a camera that captures the image.
21. 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, and wherein the server, upon verifying liveness, transmits authorization to the third party system permitting the user to access the third party system via the electronic computing device.
22. The system of claim 21 , 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.