Method, system, and program product for transforming a biometric image

Abstract

The invention provides a method, system, and program product for transforming a multi-dimensional biometric feature point set. More particularly, the invention provides a method for transforming a biometric image using surface folding of the image. In one embodiment, the invention provides a method for transforming a multi-dimensional biometric feature point set, the method comprising: converting the multi-dimensional biometric feature point set to a canonical position and orientation; applying a non-invertible transform function to each of a plurality of points of the biometric feature point set; and providing a transformed biometric feature point set comprising a plurality of transformed points.

1 . A method for transforming a multi-dimensional biometric feature point set, the method comprising: 
 converting the multi-dimensional biometric feature point set to a canonical position and orientation;    applying a non-invertible transform function to each of a plurality of points of the biometric feature point set; and    providing a transformed biometric feature point set comprising a plurality of transformed points.    
   
   
       2 . The method of  claim 1 , wherein the non-invertible transform function includes a point offset direction as a first transform and a point offset amount as a second transform.  
   
   
       3 . The method of  claim 1 , further comprising: 
 applying the non-invertible transform function to at least one additional orientation of each of the plurality of points of the biometric feature point set.    
   
   
       4 . The method of  claim 1 , wherein applying includes: 
 applying a first transform function to a position of each of the plurality of points of the biometric feature point set; and    applying a second transform function to an orientation of each of the plurality of points of the biometric feature point set.    
   
   
       5 . The method of  claim 1 , wherein the multi-dimensional biometric feature point set is selected from a group consisting of: a fingerprint, a facial image, and a signature.  
   
   
       6 . The method of  claim 1 , wherein converting includes: 
 determining a reference point and a reference orientation.    
   
   
       7 . The method of  claim 6 , wherein the reference point includes a core of a fingerprint and the reference orientation includes an orientation of the core of the fingerprint.  
   
   
       8 . The method of  claim 6 , wherein the reference orientation includes a direction between a core of a fingerprint and a delta of a fingerprint.  
   
   
       9 . The method of  claim 1 , wherein the non-invertible transform function includes a mixture of Gaussian kernels.  
   
   
       10 . The method of  claim 1 , wherein the non-invertible transform function includes a point potential function.  
   
   
       11 . A system for transforming a multi-dimensional biometric feature point set, the system comprising: 
 a system for converting the multi-dimensional biometric feature point set to a canonical position and orientation;    a system for applying a non-invertible transform function to each of a plurality of points of the biometric feature point set; and    a system for providing a transformed biometric feature point set comprising a plurality of transformed points.    
   
   
       12 . The system of  claim 11 , wherein the non-invertible transform function includes a point offset direction as a first transform and a point offset amount as a second transform.  
   
   
       13 . The system of  claim 11 , further comprising: 
 a system for applying the non-invertible transform function to at least one additional orientation of each of the plurality of points of the biometric feature point set.    
   
   
       14 . The system of  claim 11 , wherein the system for applying includes: 
 a system for applying a first transform function to a position of each of the plurality of points of the biometric feature point set; and    a system for applying a second transform function to an orientation of each of the plurality of points of the biometric feature point set.    
   
   
       15 . The system of  claim 11 , wherein the multi-dimensional biometric feature point set is selected from a group consisting of: a fingerprint, a facial image, and a signature.  
   
   
       16 . The system of  claim 11 , wherein the system for converting includes: 
 a system for determining a reference point and a reference orientation,    wherein the reference point includes a core of a fingerprint and the reference orientation includes one of: an orientation of the core of the fingerprint and a direction between the core of the fingerprint and a delta of the fingerprint.    
   
   
       17 . A program product stored on a computer-readable medium, which when executed, transforms a multi-dimensional biometric feature point set, the program product comprising: 
 program code for converting the multi-dimensional biometric feature point set to a canonical position and orientation;    program code for applying a non-invertible transform function to each of a plurality of points of the biometric feature point set; and    program code for providing a transformed biometric feature point set comprising a plurality of transformed points.    
   
   
       18 . The program product of  claim 17 , wherein the program code for applying includes: 
 program code for applying a first transform function to a position of each of the plurality of points of the biometric feature point set; and    program code for applying a second transform function to an orientation of each of the plurality of points of the biometric feature point set.    
   
   
       19 . The program product of  claim 17 , wherein the biometric feature point set is selected from a group consisting of: a fingerprint, a facial image, and a signature.  
   
   
       20 . A method for deploying an application for transforming a multi-dimensional biometric feature point set, comprising: 
 providing a computer infrastructure being operable to: 
 convert the multi-dimensional biometric feature point set to a canonical position and orientation;  
 apply a non-invertible transform function to each of a plurality of points of the biometric feature point set; and  
 provide a transformed biometric feature point set comprising a plurality of transformed points.