Personal identity verification process and system

Abstract

A personal identity verification process and system adopts an error correcting output code (ECOC) classifier approach. Image data representing an input facial images is processed to generate a first (ECOC) classifier output vector and image data representing a class of different training images of the face of an individual are processed to generate a set of second ECOC classifier output vectors. Authenticity of the input facial image against the class of training images is evaluated by measuring distance between the first ECOC classifier output vector and the set of second ECOC classifier output vectors using a first order Minkowski metric.

1 - 14 . (canceled) 
   
   
       15 . A personal identity verification process for evaluating authenticity of an input facial image against a class of different training images representing the face of an individual, the process including
 processing image data representing the input facial image to generate a first error correcting output code (ECOC) classifier output vector,   processing image data representing the different training images of the class to generate a set of second ECOC classifier output vectors,   comparing the first ECOC classifier output vector with the set of second ECOC classifier output vectors, and   evaluating authenticity of the input facial image with respect to the class of training images in dependence on the comparing.   
   
   
       16 . The process according to  claim 15  wherein the comparing includes measuring a distance between the first ECOC classifier output vector and the set of second ECOC classifier output vectors. 
   
   
       17 . The process according to  claim 16  including measuring the distance using a first order Minkowski metric. 
   
   
       18 . The process as claimed in  claim 17  including:
 processing image data representing a plurality of the classes of different training images to generate a respective set of second ECOC classifier output vectors for each class, each class of training images representing the face of a different individual,   measuring a distance between the first ECOC classifier output vector and each set of second ECOC classifier output vectors, and   combining distances measured to evaluate authenticity of input facial image with respect to one of classes of training images.   
   
   
       19 . The process as claimed in  claim 15  including combining distances measured as a combination that is a summation of exponential kernel functions, each kernel function having an exponent related to a different respective distance. 
   
   
       20 . The process as claimed in  claim 15  wherein processing image data includes projecting the image data into a lower dimensional space and generating the first and second (ECOC) classifier output vectors from the image data so projected. 
   
   
       21 . The process as claimed in  claim 20  wherein projecting the image data includes Linear Discriminant Analysis. 
   
   
       22 . The process as claimed in  claim 21  wherein projecting the image data includes Principal Component Analysis. 
   
   
       23 . The process as claimed in  claim 15  including:
 processing image data representing a plurality of the classes of different training images to generate a respective set of second ECOC classifier output vectors for each class, each class of training images representing the face of a different individual,   comparing the first ECOC classifier output vector with different ones of the sets of second ECOC classifier output vectors, and   evaluating authenticity of the input facial image with respect to a respective class of training images in dependence on the comparing.   
   
   
       24 . A personal identity verification system including:
 means for storing image data representing an input facial image and at least one class of different training images, and   processing means for processing the stored image data according to the process of  claim 15 .