Iris image data processing for use with iris recognition system

Abstract

Disclosed is an iris recognition method which is one of biometric technologies. According to a non-contact-type human iris recognition method by correction of a rotated iris image, the iris image is acquired by image acquisition equipment using an infrared illuminator. Inner and outer boundaries of the iris are detected by analyzing differences in pixels of a Canny edge detector and the image for the inputted iris image, so as to allow the boundaries of the iris to be more accurately detected from the eye image of a user. Thus, the iris image with a variety of deformation can be processed into a correct iris image, so that there is an advantage in that a false acceptance rate and a false rejection rate can be markedly reduced.

1 . A method of processing iris image data, comprising:
 providing data of an eye image comprising an iris defined between an inner boundary and an outer boundary;   providing information indicative of a center of the inner boundary, a first inner boundary pixel and a second inner boundary pixel, wherein the first and second inner boundary pixels are located on a first imagery line passing the center;   computing to locate a first outer boundary pixel on the first imaginary line extending outwardly from the first inner boundary pixel;   computing to locate a second outer boundary pixel on the first imaginary line extending outwardly from the second inner boundary pixel; and   computing to locate a center of the outer boundary using the first outer boundary pixel and the second outer boundary pixel.   
   
   
       2 . The method of  claim 1 , wherein computing to locate the center of the outer boundary comprises computing a bisectional point of the first and second outer boundary pixels. 
   
   
       3 . The method of  claim 1 , further comprising computing a first distance between the first inner boundary pixel and the first outer boundary pixel. 
   
   
       4 . The method of  claim 1 , further comprising obtaining a distance between the first inner boundary pixel and the second inner boundary pixel. 
   
   
       5 . The method of  claim 1 , wherein computing to locate the center of the outer boundary uses a first distance defined between the first inner boundary pixel and the first outer boundary pixel and a second distance defined between the second inner boundary pixel and the second outer boundary pixel. 
   
   
       6 . The method of  claim 5 , wherein computing the center of the outer boundary further uses a distance between the first inner boundary pixel and the second inner boundary pixel. 
   
   
       7 . The method of  claim 1 , wherein the center of outer boundary is off the center of the inner boundary. 
   
   
       8 . The method of  claim 1 , further comprising:
 providing information indicative of a third inner boundary pixel and a fourth inner boundary pixel, wherein the third and fourth inner boundary pixels are located on a second imagery line passing the center;   computing to locate a third outer boundary pixel on the second imaginary line extending outwardly from the third inner boundary pixel; and   computing to locate a fourth outer boundary pixel on the second imaginary line extending outwardly from the fourth inner boundary pixel,   wherein computing to locate the center of the outer boundary further uses the third outer boundary pixel and the fourth outer boundary pixel.   
   
   
       9 . The method of  claim 8 , wherein the second imaginary line is substantially perpendicular to the first imaginary line. 
   
   
       10 . The method of  claim 8 , wherein computing to locate the center of the outer boundary comprises computing a bisectional point of the first and second outer boundary pixels and a bisectional point of the third and fourth outer boundary pixels. 
   
   
       11 . The method of  claim 8 , wherein computing to locate the center of the outer boundary uses a first distance defined between the first inner boundary pixel and the first outer boundary pixel, a second distance defined between the second inner boundary pixel and the second outer boundary pixel, a third distance defined between the third inner boundary pixel and the third outer boundary pixel and a fourth distance defined between the fourth inner boundary pixel and the fourth outer boundary pixel. 
   
   
       12 . The method of  claim 11 , wherein computing to locate the center of the outer boundary further uses a distance between the first inner boundary pixel and the second inner boundary pixel. 
   
   
       13 . The method of  claim 1 , wherein the first imaginary line comprises a first line segment extending outwardly from the first inner boundary pixel and a second line segment extending outwardly from the second inner boundary pixel, wherein a pixel located on the first line segment is determined to be the first outer boundary pixel when the difference of the image information between the pixel and its neighboring pixel which are located on the first line segment becomes the maximum among differences of the image information between two neighboring pixels located on the first line segment, wherein a pixel located on the second line segment is determined to be the second outer boundary pixel when the difference of the image information between the pixel and its neighboring pixel which are located on the second line segment becomes the maximum among differences of the image information between two neighboring pixels located on the second line segment. 
   
   
       14 . The method of  claim 1 , wherein providing information indicative of a center of the inner boundary comprises performing a Canny edge detection method using the eye image data. 
   
   
       15 . The method of  claim 1 , further comprising:
 extracting data of a portion of the eye image that is located between the inner boundary and the outer boundary; and   processing the data of the portion to obtain a characteristic vector of a an iris pattern.   
   
   
       16 . The method of  claim 15 , wherein processing the data further comprises obtaining a plurality of characteristic vectors for the same eye image. 
   
   
       17 . A method of processing iris image data, comprising:
 providing data of an eye image comprising an iris defined between an inner boundary and an outer boundary;   providing information indicative of a first inner boundary pixel, a second inner boundary pixel, a third inner boundary pixel and a fourth inner boundary pixel, which are located at different positions on the inner boundary;   computing to locate a first outer boundary pixel on a first imaginary line extending generally radially from the first inner boundary pixel;   computing to locate a second outer boundary pixel on a second imaginary line extending generally radially from the second inner boundary pixel;   computing to locate a third outer boundary pixel on a third imaginary line extending generally radially from the third inner boundary pixel;   computing to locate a fourth outer boundary pixel on a fourth imaginary line extending generally radially from the fourth inner boundary pixel; and   using the first, second, third and fourth outer boundary pixels for further processing.   
   
   
       18 . The method of  claim 17 , further comprising computing to locate a center of the outer boundary using the first, second, third and fourth outer boundary pixels. 
   
   
       19 . The method of  claim 17 , wherein the first imaginary line is substantially perpendicular to the third and fourth imaginary lines, and wherein the second imaginary line is substantially perpendicular to the third and fourth imaginary lines. 
   
   
       20 . The method of  claim 17 , wherein a pixel located on the first imaginary line is determined to be the first outer boundary pixel when the difference of the image information between the pixel and its neighboring pixel which are located on the first imaginary line becomes the maximum among differences of the image information between two neighboring pixels located on the first imaginary line.