Methods and systems for biometric identification

Abstract

A method for identifying an iris image can include obtaining an iris image of an eye, segmenting the iris image, generating, from the segmented iris image, a normalized iris image, and generating, from the normalized iris image, an iris template. The method can also include generating a modified iris template by extracting a portion of the iris template, comparing the modified iris template with a plurality of previously stored other modified iris templates and matching the modified iris template with one of the plurality of previously stored other modified iris templates. The method can also include generating a modified iris template by extracting a portion of the iris template, comparing the modified iris template with a plurality of previously stored other modified iris templates, and matching the modified iris template with one of the plurality of previously stored other modified iris templates.

1 . A method for identifying an iris image, the method comprising the steps of:
 obtaining an iris image of an eye;   generating, from the iris image, an iris template;   generating at least one characteristic metric from at least one of the iris template, the iris image and an intermediate product of a process of generating the iris template;   assigning the iris template to one of a plurality of categories based on the at least one characteristic metric; and   matching the iris template with one of a plurality of other iris templates stored in the assigned category.   
     
     
         2 . The method of  claim 1 , wherein the at least one characteristic metric is derived from the energy spectrum of the iris template. 
     
     
         3 . A method for building an iris template database, the method comprising the steps of:
 obtaining a plurality iris images of eyes;   generating, from each iris image, an iris template;   generating at least one characteristic metric from at least one of the iris template, iris image, and an intermediate product of a process of generating the iris template;   assigning each iris template to one of a plurality of categories based on the at least one characteristic metric; and   storing each iris template in an data structure searchable based on the category.   
     
     
         4 . The method of  claim 3 , wherein the at least one characteristic metric is derived from the energy spectrum of the iris template. 
     
     
         5 . A method for identifying an iris image, the method comprising the steps of:
 obtaining an iris image of an eye;   generating, from the iris image, an original iris template;   generating, from the original iris template, an error-corrected reduced iris template;   comparing the error-corrected iris template with a plurality of previously stored other error-corrected reduced iris templates to select at least one candidate for full unmodified template matching with the original template; and   comparing the original iris template with the corresponding other previously stored original iris templates of the selected at least one candidate.   
     
     
         6 . A method for building an iris template database, the method comprising the steps of:
 obtaining a plurality iris images of eyes;   generating, from each iris image, an iris template;   generating an error corrected reduced iris template from each iris template;   storing each reduced iris template in an indexed data structure allowing efficient access based on the content of the error corrected reduced iris template; and   associating with each entry in this data structure the corresponding original iris template.   
     
     
         7 . A method for identifying an iris image, the method comprising the steps of:
 obtaining an iris image of an eye;   segmenting the iris image;   establishing a non-polar coordinate system on the segmented iris image wherein the non-polar coordinate system models dilation of a pupil of the eye;   defining a plurality of regions within the iris image;   analyzing the iris to generate an iris code; and   comparing the iris code with a previously generated reference iris code within the plurality of regions to determine a measure of similarity between the iris code and the reference iris code.   
     
     
         8 . The method of  claim 7 , wherein the non-polar coordinate system is one of a torroidal coordinate system, and a non-classical complex coordinate system. 
     
     
         9 . The method of  claim 8 , wherein the step establishing a non-polar coordinate system further comprises steps of:
 applying a coordinate transformation to the segmented iris image to produce modified segmented iris image in rectangular coordinates; and   applying an additional transformation to establish the non-polar coordinate system.