Identity verification via validated facial recognition and graph database

Abstract

Technologies are provided herein for verifying identities of individuals via facial recognition and a graph database. Images of individuals to be identified can be can be captured with multiple mobile devices, such as by crowdsourcing, and transmitted to an identity verification server for identification. The identity verification server can maintain a graph database and locate a potential identity for an individual via facial recognition. Confirmation can he achieved by transmitting an image already in the database. A wide variety of validation techniques can be employed to filter out low quality data and improve the quality of matching. The identity verification server can manage profile information for the verified identity by creating and analyzing nodes and relationship records in the graph database. The identity verification server can update the graph database to track associations between verified identities.

1 - 20 . (canceled) 
     
     
         21 . A non-transitory computer-readable medium comprising instructions that, when executed by a processor of a mobile computing device, cause the mobile computing device to perform operations, the operations comprising:
 capturing a sequence of images using a camera of the mobile device;   determining, using the captured sequence of images, that a person depicted in the images is physically present at the mobile device when the sequence of images was captured by the mobile device;   responsive to the determining, transmitting a request from the mobile device to a server to identify the person depicted in the sequence of images, the request comprising one or more images of the sequence of images;   receiving another image at the mobile device, from the server, wherein the second image is a potential match to the one or more images of the sequence of images;   displaying the another image on a user interface of the mobile device;   receiving an indication, via the user interface of the mobile device, that the another image is an image of the person;   retrieving profile information associated with the another image from the server; and   presenting the profile information to the user via the user interface of the mobile device.   
     
     
         22 . The computer-readable medium of  claim 21 , wherein the determining that the person depicted in the sequence of images is physically present at the mobile device when the sequence of images was captured by the mobile device comprises:
 identifying one or more variations in the sequence of images that indicates one or more facial movements.   
     
     
         23 . The non-transitory computer-readable medium of  claim 22 , wherein the determining further comprises determining that the one or more variations indicate one or more of an eye movement, an eyelid movement, or a head movement. 
     
     
         24 . The non-transitory computer-readable medium of  claim 21 , wherein the determining further comprises transmitting the sequence of images to the server and receiving a response from the server indicating that the person is physically present at the mobile device. 
     
     
         25 . The computer-readable medium of  claim 21 , wherein the operations further comprise:
 displaying another image received from the camera of the mobile device via the user interface of the mobile device;   displaying a cut-out via the user interface of the mobile device that overlays the displayed image and obscures a portion of the displayed image that is outside the cut-out; and   prompting the user, via the user interface of the mobile device, to adjust a location of the camera of the mobile device so that the person's face is visible within the cut-out before capturing the sequence of images.   
     
     
         26 . The computer-readable medium of  claim 25 , wherein the cut-out displayed via the user interface of the mobile device comprises an outline of a human head. 
     
     
         27 . The computer-readable medium of  claim 21 , further comprising:
 prompting the user, via the user interface of the mobile device, to provide profile information for the person;   receiving profile information for the person via the user interface of the mobile device; and   transmitting the profile information to the server to be stored in association with the one or more images of the sequence of images.   
     
     
         28 . The computer-readable medium of  claim 21 , wherein the capturing the sequence of images using the camera of the mobile device comprises capturing a stereoscopic image using multiple cameras of the mobile device. 
     
     
         29 . The computer-readable medium of  claim 21 , wherein:
 the capturing the sequence of images using the camera of the mobile device comprises altering a focal length of the camera when capturing each image in the sequence of images; and   the determining that the sequence of images are of the person and not a picture of the person comprises using the focal lengths associated with the images to determine relative depths of features in the images compared to other features in the images.   
     
     
         30 . A method, comprising:
 capturing a sequence of images depicting a person using a camera of a mobile computing device;   determining, by detecting variations in the sequence of images, that the sequence of images are images of the person and not images of a picture of the person;   responsive to the determining, transmitting a request from the mobile computing device to a server to identify the person depicted in the sequence of images, the request comprising one or more images of the sequence of images;   receiving a matched image at the mobile computing device from the server;   displaying the matched image via a user interface of the mobile computing device;   receiving input, via the user interface of the mobile computing device, indicating that the matched image is an image of the person;   transmitting a message from the mobile computing device to the server, indicating that the matched image is an image of the person;   receiving information related to the identity of the person at the mobile computing device from the server; and   displaying the information related to the identity of the person via the user interface of the mobile computing device.   
     
     
         31 . The method of  claim 30 , wherein the detecting variations in the sequence of images comprises:
 identifying one or more differences in the sequence of images; and   determining that the one or more differences indicate one or more facial feature movements.   
     
     
         32 . The method of  claim 31 , wherein the determining further comprises determining that the one or more variations indicate one or more of an eye movement, an eyelid movement, or a head movement. 
     
     
         33 . The method of  claim 30 , further comprising:
 displaying an image received from the camera of the mobile computing device on the user interface of the mobile computing device;   displaying a cut-out via the user interface of the mobile computing device that overlays the image received from the camera of the mobile computing device and obscures a portion of the image that is outside the cut-out; and   prompting a user, via the user interface of the mobile computing device, to adjust a location of the camera of the mobile device so that the person's face is visible within the cut-out before capturing the sequence of images.   
     
     
         34 . The method of  claim 33 , wherein the cut-out displayed via the user interface comprises an outline of a human head. 
     
     
         35 . The method of  claim 30 , wherein the capturing the sequence of images using the camera of the mobile computing device comprises capturing a stereoscopic image using multiple cameras of the mobile computing device. 
     
     
         36 . The method of  claim 30 , wherein:
 the capturing the sequence of images using the camera of the mobile computing device comprises altering a focal length of the camera for each image in the sequence of images; and   the determining that the sequence of images are images of the person and not images of a picture of the person comprises using the focal lengths associated with the images to determine relative depths of features in the images compared to other features in the images.   
     
     
         37 . The method of  claim 30 , further comprising:
 capturing another sequence of images depicting another person using the camera of the mobile computing device;   transmitting another request from the mobile computing device to the server to identify the another person;   receiving another matched image at the mobile computing device from the server;   displaying the another matched image via the user interface of the mobile computing device;   receiving an indication, via the user interface of the mobile computing device, that the another matched image is not an image of the another person;   prompting a user, via the user interface of the mobile computing device, to provide profile information for the another person;   receiving profile information for the person via the user interface of the mobile computing device; and   transmitting the profile information from the mobile computing device to the server to be stored in association with one or more images of the another sequence of images.   
     
     
         38 . The method of  claim 30 , further comprising:
 capturing another sequence of images depicting another person using the camera of the mobile computing device;   determining that the another sequence of images are of a picture of the another person and not of the another person; and   responsive to the determining, displaying a message via the user interface indicating that no matches for the another person were found.   
     
     
         39 . A system, comprising:
 a mobile device, comprising a processor; a camera; a display; and a storage storing an application that, when executed by the processor, causes the mobile device to perform identity verification operations, the operations comprising:
 capturing multiple images depicting a person using the camera; 
 determining, by detecting one or more differences in the multiple images, that the multiple images are images of the person and not images of a picture of the person; 
 obtaining GPS coordinates of the mobile device using the GPS antenna; 
 transmitting a request to a server to verify an identity of the person, the request comprising at least one of the captured images; 
 receiving a matched image from the server; 
 displaying the matched image and one or more user interface components on the display, the one or more user interface components configured to receive input indicating whether or not the matched image is an image of the person; 
 receiving input via at least one of the one or more user interface components indicating that the matched image is an image of the person; 
 transmitting a message to the server, indicating that the matched image is an image of the person; 
 receiving information related to the identity of the person from the server; and 
 displaying the information related to the identity of the person on the display. 
   
     
     
         40 . The system of  claim 39 , wherein the determining that the multiple images are images of the person and not images of a picture of the person comprises:
 identifying one or more variations in the multiple images; and   determining that the one or more variations indicate one or more facial movements.