System and method for using images to authenticate a user

Abstract

Systems and methods for authenticating a user, the method including receiving an image of a user of a device, identifying a first facial descriptor of the user from the received image and from previously captured images of the user, and determining a difference between the first facial descriptor from the received image and that from the previously captured images. The method further includes identifying a second facial descriptor of a non-user from the previously captured images of the user, and applying facial recognition to images stored in a plurality of second social networking profiles associated with a first social networking profile of the user to identify the second facial descriptor from the images stored in the second social networking profiles. Based on the difference and the second facial descriptor, the user may be authenticated.

What is claimed is: 
     
         1 . A computer-implemented method of authenticating a user, the method comprising: 
 receiving an image of a user of a device;   identifying at least one facial descriptor of the user from the image;   identifying at least one facial descriptor of the user from a plurality of previously captured images of the user stored in the device;   determining a difference between the at least one facial descriptor from the image and the at least one facial descriptor from the plurality of previously captured images;   cross-verifying the difference against a plurality of images of the user stored in a social networking profile of the user; and   authenticating the user in the image based on cross-verifying the difference.   
     
     
         2 . The computer-implemented method of  claim 1 , further comprising generating a notification that the user in the image is an authorized user when the difference between the at least one facial descriptor from the image and the at least one facial descriptor from the plurality of previously captured images is lower than a predetermined threshold. 
     
     
         3 . The computer-implemented method of  claim 1 , wherein the at least one facial descriptor of the user comprises at least one of an eye, a nose, or a mouth of the user. 
     
     
         4 . The computer-implemented method of  claim 1 , wherein determining the difference between the at least one facial descriptor from the image and the at least one facial descriptor from the plurality of previously captured images further comprises:
 generating a first color histogram of the at least one facial descriptor from the image; and   comparing the first color histogram with second color histograms of the at least one facial descriptor from the plurality of previously captured images.   
     
     
         5 . The computer-implemented method of  claim 1 , wherein determining the difference between the at least one facial descriptor from the image and the at least one facial descriptor from the plurality of previously captured images further comprises:
 aligning the at least one facial descriptor from the image with the at least one facial descriptor from the plurality of previously captured images.   
     
     
         6 . The computer-implemented method of  claim 1 , further comprising evaluating a liveness of the user by:
 requesting the user to make a predetermined facial expression;   capturing a second image of the user while the user is making the predetermined facial expression; and   performing a three-dimensional rendering of the second image.   
     
     
         7 . The computer-implemented method of  claim 1 , wherein cross-verifying the difference further comprises:
 aggregating social networking profiles of non-users associated with the social networking profile of the user;   calculating, based on a facial recognition performed, a number of images in which the at least one facial descriptor of the user was identified; and   authenticating the user when the number of images exceeds a predetermined threshold.   
     
     
         8 . The computer-implemented method of  claim 1 , further comprising:
 generating, based on at least the difference, a notification indicative of whether the user in the image is an authorized user, wherein the notification comprises at least one of a visual notification or an audible notification.   
     
     
         9 . The computer-implemented method of  claim 8 , wherein generating the notification further comprises at least one of:
 unlocking the device; and   enabling the user to access contents stored in the device or enabling the user to perform a financial transaction.   
     
     
         10 . The computer-implemented method of  claim 2 , further comprising enabling the user to perform a financial transaction when the difference is lower than the predetermined threshold, wherein the predetermined threshold varies based on a type of financial transaction requested by the user. 
     
     
         11 . A system for authenticating a user, comprising:
 at least one processor; and   at least one memory storing instructions, wherein the instructions cause the at least one processor to perform operations comprising: 
 receiving an image of the user of a device; 
 identifying at least one facial descriptor of the user from the image; 
 identifying at least one facial descriptor of the user from a plurality of previously captured images of the user stored in the device; 
 determining a difference between the at least one facial descriptor from the image and the at least one facial descriptor from the plurality of previously captured images; 
 cross-verifying the difference against a plurality of images of the user stored in a social networking profile of the user; and 
 authenticating the user in the image based on cross-verifying the difference. 
   
     
     
         12 . The system of  claim 11 , further comprising generating a notification that the user in the image is an authorized user when the difference between the at least one facial descriptor from the image and the at least one facial descriptor from the plurality of previously captured images is lower than a predetermined threshold. 
     
     
         13 . The system of  claim 11 , wherein the at least one facial descriptor of the user comprises at least one of an eye, a nose, or a mouth of the user. 
     
     
         14 . The system of  claim 11 , wherein determining the difference between the at least one facial descriptor from the image and the at least one facial descriptor from the plurality of previously captured images further comprises:
 generating a first color histogram of the at least one facial descriptor from the image; and   comparing the first color histogram with second color histograms of the at least one facial descriptor from the plurality of previously captured images.   
     
     
         15 . The system of  claim 11 , wherein determining the difference between the at least one facial descriptor from the image and the at least one facial descriptor from the plurality of previously captured images further comprises:
 aligning the at least one facial descriptor from the image with the at least one facial descriptor from the plurality of previously captured images.   
     
     
         16 . The system of  claim 11 , further comprising evaluating a liveness of the user by: requesting the user to make a predetermined facial expression;
 capturing a second image of the user while the user is making the predetermined facial expression; and   performing a three-dimensional rendering of the second image.   
     
     
         17 . The system of  claim 11 , wherein cross-verifying the difference further comprises:
 aggregating social networking profiles of non-users associated with the social networking profile of the user;   calculating, based on a facial recognition performed, a number of images in which the at least one facial descriptor of the user was identified; and   authenticating the user when the number of images exceeds a predetermined threshold.   
     
     
         18 . The system of  claim 11 , further comprising:
 generating, based on at least the difference, a notification indicative of whether the user in the image is an authorized user, wherein the notification comprises at least one of a visual notification or an audible notification.   
     
     
         19 . The system of  claim 18 , wherein generating the notification further comprises at least one of:
 unlocking the device; and   enabling the user to access contents stored in the device or enabling the user to perform a financial transaction.   
     
     
         20 . The system of  claim 12 , further comprising enabling the user to perform a financial transaction when the difference is lower than the predetermined threshold, wherein the predetermined threshold varies based on a type of financial transaction requested by the user.