×

System and methods for transforming biometric image data to a consistent angle of inclination

  • US 7,916,907 B2
  • Filed: 11/30/2009
  • Issued: 03/29/2011
  • Est. Priority Date: 06/14/2004
  • Status: Expired due to Fees
First Claim
Patent Images

1. A method for spatially transforming biometric data for invariant feature extraction comprising the steps of:

  • using a processor to perform the following functions;

    acquiring and digitizing biometric information from a user and generating the biometric data responsive thereto;

    pixelating the biometric data to form a biometric image thereof, said image including a plurality of pixels at a corresponding plurality of pixel coordinates of an orthogonal coordinate system, said biometric data oriented in said image at an arbitrary submission angle with respect to a predetermined axis of said image;

    applying a coordinate transformation to said plurality of pixels of said biometric image to form a transformed biometric image, said transformed biometric image remaining substantially invariant for different submissions of said biometric information at variant submission angles, said transformed biometric image being defined according to one of the following characteristics;


    var(xi)=k1*var(yi), 



    1)where “

    var”

    is a variance, k1 is a scalar multiple, and xi, yi represent a plurality of transformed pixel coordinates, such that;


    xi=(Xi+M1Yi)/(1+M12)1/2 and
    yi=(Yi

    M
    1Xi)/(1+M12)1/2 wherein Xi, Yi represent said plurality of pixel coordinates of said biometric image; and

    ,wherein for k1=1;


    M1=[2ra+or−

    Sqrt(4r2a2+a4

    2a2+1)]/(a2

    1), if a≠

    1 and,
    M1=0, if a=1where a=sqrt[var(Xi)/var(Yi)]; and

    , r is a correlation coefficient of Xi and Yi;


    cov(xi,yi)=k2



    2)where “

    cov”

    is a covariance, k2 is a scalar multiple, and xi, yi represent a plurality of transformed pixel coordinates such that;


    xi=(Xi+M2Yi)/(1+M22)1/2 and
    yi=(Yi

    M
    2Xi)/(1+M22)1/2 wherein Xi, Yi represent said plurality of pixel coordinates of said biometric image; and

    wherein for k2=0;


    M2=[(1

    a
    2)+or−

    Sqrt(4r2a2+a4

    2a2+1)]/2ra, if r≠

    0and,
    M2=0, if r=0where a=sqrt[var(Xi)/var(Yi)]; and

    , r is a correlation coefficient of Xi and Yi.

View all claims
  • 3 Assignments
Timeline View
Assignment View
    ×
    ×