Systems and Methods for Generating and Using Anthropomorphic Signatures to Authenticate Users

Abstract

The technology disclosed relates to authenticating users using a plurality of non-deterministic registration biometric inputs. During registration, a plurality of non-deterministic biometric inputs are given as input to a trained machine learning model to generate sets of feature vectors. The non-deterministic biometric inputs can include a plurality of face images and a plurality of voice samples of a user. A characteristic identity vector for the user can be determined by averaging feature vectors. During authentication, a plurality of non-deterministic biometric inputs are given as input to a trained machine learning model to generate a set of authentication feature vectors. The sets of feature vectors are projected onto a surface of a hyper-sphere. The system can authenticate the user when a cosine distance between the authentication feature vector and a characteristic identity vector for the user is less than a pre-determined threshold.

We claim as follows: 
     
         1 . A computer-implemented method of authentication using a plurality of non-deterministic authentication biometric inputs, the method including:
 receiving a plurality of non-deterministic biometric inputs with a request for authentication;   feeding the non-deterministic biometric inputs to a trained machine learning model and generating a set of authentication feature vectors, wherein the non-deterministic authentication biometric input includes an image and a voice sample of a user;   projecting the set of feature vectors onto a surface of a hyper-sphere; and   authenticating the user when a cosine distance between the authentication feature vector and a characteristic identity vector previously registered for the user is less than a pre-determined threshold.   
     
     
         2 . The method of  claim 1 , wherein the sets of feature vectors are projected onto a surface of a unit hyper-sphere. 
     
     
         3 . The method of  claim 1 , wherein the characteristic identity vector for the user was determined by averaging feature vectors for from a plurality of images and for a plurality of voice samples on a user-by-user basis. 
     
     
         4 . The method of  claim 3 , wherein the predetermined threshold was determined from variance among projected feature vectors from the plurality of images and the plurality of voice samples on a user-by-user basis. 
     
     
         5 . The method of  claim 3 , wherein the predetermined threshold was determined from variance among projected feature vectors from the plurality of images and the plurality of voice samples for classes of users. 
     
     
         6 . The method of  claim 3 , wherein the predetermined threshold was determined from variance among projected feature vectors from the plurality of images and the plurality of voice samples across users. 
     
     
         7 . A non-transitory computer readable storage medium impressed with computer program instructions to authenticate using a plurality of non-deterministic authentication biometric inputs, the instructions, when executed on a processor, implement a method comprising:
 receiving a plurality of non-deterministic biometric inputs with a request for authentication;   feeding the non-deterministic biometric inputs to a trained machine learning model and generating a set of authentication feature vectors, wherein the non-deterministic authentication biometric input includes an image and a voice sample of a user;   projecting the set of feature vectors onto a surface of a hyper-sphere; and   authenticating the user when a cosine distance between the authentication feature vector and a characteristic identity vector previously registered for the user is less than a pre-determined threshold.   
     
     
         8 . The non-transitory computer readable storage medium of  claim 7 , wherein the sets of feature vectors are projected onto a surface of a unit hyper-sphere. 
     
     
         9 . The non-transitory computer readable storage medium of  claim 7 , wherein the characteristic identity vector for the user was determined by averaging feature vectors for from a plurality of images and for a plurality of voice samples on a user-by-user basis. 
     
     
         10 . The non-transitory computer readable storage medium of  claim 9 , wherein the predetermined threshold was determined from variance among projected feature vectors from the plurality of images and the plurality of voice samples on a user-by-user basis. 
     
     
         11 . The non-transitory computer readable storage medium of  claim 9 , wherein the predetermined threshold was determined from variance among projected feature vectors from the plurality of images and the plurality of voice samples for classes of users. 
     
     
         12 . The non-transitory computer readable storage medium of  claim 9 , wherein the predetermined threshold was determined from variance among projected feature vectors from the plurality of images and the plurality of voice samples across users. 
     
     
         13 . A system including one or more processors coupled to memory, the memory loaded with computer instructions to authenticate using a plurality of non-deterministic authentication biometric inputs, when executed on the processors implement the instructions of  claim 7 . 
     
     
         14 . The system of  claim 13 , wherein the sets of feature vectors are projected onto a surface of a unit hyper-sphere. 
     
     
         15 . The system of  claim 13 , wherein the characteristic identity vector for the user was determined by averaging feature vectors for from a plurality of images and for a plurality of voice samples on a user-by-user basis. 
     
     
         16 . The system of  claim 15 , wherein the predetermined threshold was determined from variance among projected feature vectors from the plurality of images and the plurality of voice samples on a user-by-user basis. 
     
     
         17 . The system of  claim 15 , wherein the predetermined threshold was determined from variance among projected feature vectors from the plurality of images and the plurality of voice samples for classes of users. 
     
     
         18 . The system of  claim 15 , wherein the predetermined threshold was determined from variance among projected feature vectors from the plurality of images and the plurality of voice samples across users. 
     
     
         19 . A computer-implemented method of authentication using a plurality of non-deterministic authentication biometric inputs, the method including:
 receiving the plurality of non-deterministic authentication biometric inputs with a request for authentication;   feeding the non-deterministic authentication biometric inputs to a plurality of trained machine learning models and generating a plurality of authentication feature vectors wherein the non-deterministic authentication biometric input includes an image and a voice sample of a user;   applying a distance preserving hash to the plurality of authentication feature vectors to generate an authentication hash representing the user; and   authenticating the user when a difference between the authentication hash and a registration hash previously registered for the user is less than a pre-determined threshold.   
     
     
         20 . A computer-implemented method of authentication using a plurality of non-deterministic authentication biometric inputs, the method including:
 receiving the plurality of non-deterministic authentication biometric inputs with a request for authentication;   feeding the non-deterministic authentication biometric inputs to a plurality of trained machine learning models and generating a plurality of authentication feature vectors wherein the non-deterministic authentication biometric input includes an image and a voice sample of a user;   applying a binning function to non-integer values in the plurality of authentication feature vectors to quantize the non-integer values to integer values;   applying a hash function to the plurality of quantized authentication feature vectors to generate an authentication hash; and   authenticating the user when the authentication hash matches a registration hash previously registered for the user.