System and method for determining liveness

Abstract

Systems and methods are provided for recording a user's biometric features and generating an identifier representative of the user's biometric features and whether the user is alive (“liveness”) using mobile devices such as a smartphone. The systems and methods described herein enable a series of operations whereby a user using a mobile device can capture imagery of a user's face, eyes and periocular region. The mobile device is also configured analyze the imagery to identify and determine the position of low-level features spatially within the images and the changes in position of the low level features dynamically throughout the images. Using the spatial and dynamic information the mobile device is further configured to determine whether the user is alive and/or generate a biometric identifier characterizing the user's biometric features which can be used to authenticate the user by determining liveness and/or verify the user's identity.

What is claimed: 
     
         1 . A computer implemented method for authenticating a user according to the user's biometric features, the method comprising:
 a) capturing, by a mobile device having a camera, a storage medium, instructions stored on the storage medium, and a processor configured by executing the instructions, a plurality of images depicting at least one facial region of the user;   b) detecting, by the processor from a first image of the plurality of images, a plurality of low-level features depicted in the first image;   c) determining, by the processor from the first image, a first position of a first low-level feature, wherein the first position is relative to a respective position of each of at least one other low-level feature;   d) determining, by the processor from each of at least one other image of the plurality of images, at least one second respective position of the first low-level feature;   e) calculating, by the processor as a function of the determining in steps c) and d), changes in position of the first low-level feature;   f) determining, by the processor, that the first low-level feature represents a live biometric feature of the user and thereby indicates liveness of the user as a function of:
 i) the position of the first low-level feature depicted in the first image, and 
 ii) the calculated changes in position of the first low-level feature; and 
   g) authenticating, by the processor, the user according to determining that the first low-level feature indicates liveness of the user.   
     
     
         2 . The method of  claim 1 , wherein the step f) determining further comprises:
 h) generating, by the processor, a biometric identifier that is useable to determine liveness of the user as a function of the changes in position of the first low-level feature and at least one predetermined continuity criteria.   
     
     
         3 . The method of  claim 1 , wherein the step c) determining further comprises:
 i) determining, by the processor, a location of each of a plurality of pixels depicting the first low-level feature in the first image.   
     
     
         4 . The method of  claim 3 , wherein the step d) determining further comprises:
 j) determining, by the processor in the at least one other image, respective locations of each of a plurality of pixels depicting the first low-level feature in each of the at least one other image.   
     
     
         5 . The method of  claim 4 , wherein the step e) calculating further comprises:
 k) calculating, by the processor, the changes in position of the low-level feature in accordance with the determining in steps i) and j).   
     
     
         6 . The method of  claim 5 , further comprising:
 l) encoding, by the processor, the changes in position of the first low-level feature as temporal gradients in at least one spatiotemporal histogram, wherein each of the temporal gradients corresponds to at least one of the pixels depicting at least a portion of the first low-level feature in the first image.   
     
     
         7 . The method of  claim 6 , wherein the temporal gradients represent a difference between the location of the pixels depicting the first low-level feature in the first image and the respective locations of the pixels depicting the first low-level feature in each of the at least one other images. 
     
     
         8 . The method of  claim 6 , further comprising:
 m) encoding, by the processor, intensity values for each of the plurality of pixels depicting the first low-level feature in the first image as spatial gradients in the at least one spatiotemporal histogram.   
     
     
         9 . The method of  claim 8 , wherein the step f) determining further comprises:
 n) characterizing, by the processor, the first low-level feature as a function of a space of distributions of the spatial gradients and temporal gradients stored in the at least one spatiotemporal histograms on a pre-defined spatiotemporal domain.   
     
     
         10 . The method of  claim 6 , wherein the step f) generating further comprises:
 iii) determining, by the processor, that at least one of the temporal gradients encoded in the at least one spatiotemporal histogram have values representing continuous changes of position of the first low-level feature.   
     
     
         11 . The method of  claim 10 , wherein the step iii) determining is performed according to at least one predetermined continuity criteria. 
     
     
         12 . The method of  claim 1 , wherein the plurality of images depict at least a portion of the user's periocular region, eyes and face, and wherein the plurality of images are captured in at least one light spectrum selected from a group consisting of: visible light, near infra-red light, and infra-red light. 
     
     
         13 . The method of  claim 2 , further comprising:
 o) generating, by the processor, a second biometric identifier usable to determine liveness of the user; and   wherein the step f) determining further comprises:   p) comparing, by the processor, the first biometric identifier to the second biometric identifier.   
     
     
         14 . The method of  claim 13 , wherein the step o) generating comprises:
 q) capturing, by the processor and a microphone communicatively coupled to the processor, an audio data file including a recording of the user's voice; and   r) generating, by the processor from the audio data file, a voice print usable to determine liveness of the user.   
     
     
         15 . The method of  claim 14 , wherein the step g) authenticating further comprises:
 s) comparing, by the processor, at least a portion of the biometric identifier to the second biometric identifier; and   t) determining, by the processor, that the biometric identifier and the second biometric identifier match to a prescribed degree.   
     
     
         16 . The method of  claim 2 , wherein the step g) authenticating further comprises:
 u) comparing, by the processor, at least a portion of the biometric identifier to at least one previously generated biometric identifier; and   v) determining, by the processor, that the biometric identifier and the at least one previously generated biometric identifier match to a prescribed degree.   
     
     
         17 . The method of  claim 1 , further comprising:
 w) capturing, by the mobile device, at least one image depicting an object, wherein the object is an object known to the user, and wherein at least one previously captured image of the object is stored on the storage medium; and   wherein the step g) authenticating further comprises:   x) determining, by the processor, that the at least one image depicting the object and the at least one previously captured image of the object match to a prescribed degree.   
     
     
         18 . The method of  claim 1 , further comprising:
 y) capturing, by the processor using one or more sensors, non-machine-vision based information; and   wherein the step g) of authenticating further comprises:   z) comparing, by the processor, the non-machine vision based information to pre-defined behavioral characteristics stored on the storage medium; and   aa) determining, by the processor, that the non-machine vision based information is consistent with the pre-defined behavioral characteristics to a prescribed degree.   
     
     
         19 . The method of  claim 18 , wherein the non-machine-vision based information includes at least one of:
 a time received from an on-board clock;   a location received from a GPS sensor;   a distance from the user's face to the camera calculated from one or more of the plurality of images;   a distance from the user's face to the mobile device from an on-board proximity measuring device;   an orientation of the mobile device received from an accelerometer;   an acceleration of the mobile device received from an accelerometer;   an RF radiation signature received from an RF radiation detector;   a position or orientation of the mobile device received from a gravity magnetometer, and   a light signature received from a light intensity detector.   
     
     
         20 . A system for authenticating a user according to the user's biometric features, comprising:
 a computing device having a processor, a computer-readable storage medium, instructions in the form of at least one software module stored on the storage medium, comprising:   a biometric capture module that executes so as to configure the processor to cause a camera in communication with the processor to capture a plurality of images, wherein the plurality of images depict at least one facial region of the user,   an analysis module that executes so as to configure the processor to detect low-level features depicted in a first of the plurality of images, determine from the first image a first position of a first low-level feature relative to at least one other low-level feature, determine a at least one second respective position of the first low-level feature in each of at least one other image of the plurality of images, calculate changes in position of the first low-level feature, generate a biometric identifier useable to determine liveness for the user as a function of the first position and the calculated changes in position of the first low-level feature; and   a biometric authentication module that executes so as to configure the processor to authenticate the user by comparing the biometric identifier to at least one previously generated biometric identifier.