Image normalization using Daugman Rubber sheet model
显示 更早的评论
Hello everyone. i have segmenated image of iris and i need to normalize it using daugman rubber sheet model. i tried using https://www.mathworks.com/matlabcentral/fileexchange/51246-pupil-limbus-detection-and-daugman-normalization but i cannot get the output.
here's the error. can expalin how to use it?
i also put declaration like this; and dont get the output
% % Input parameters
% xPosPupil = 625;
% yPosPupil = 306;
% rPupil = 70;
% xPosIris = 625;
% yPosIris = 306;
% rIris = 250;
采纳的回答
Frank Martin
2019-4-15
0 个投票
You are calling the daugmanCircleDetection function which complains that it cannot find the class ASSStack. To solve this you should make sure that Matlab can find the class (https://github.com/frankcorneliusmartin/IrisAlgorithms/blob/master/Classes/ASSStack.m) . However: The function daugmanCircleDetection is used to segment the limbus and pupil, and not for normalization.
You should call the function rubberSheetNormalisation instead to perform the normalization, which is defined in https://github.com/frankcorneliusmartin/IrisAlgorithms/blob/master/Segmentation/rubberSheetNormalisation.m
Too see how this function works see example:https://github.com/frankcorneliusmartin/IrisAlgorithms/blob/master/Examples/RubbersheetModel.m
5 个评论
syahira samsudin
2019-4-15
编辑：syahira samsudin
2019-4-15
Frank Martin
2019-4-15
That would be a valid way to do this yes.
syahira samsudin
2019-4-16
this is how i insert the coding. is it correct?
function image = rubberSheetNormalisation( img, xPosPupil, yPosPupil, rPupil , xPosIris , yPosIris , rIris , varargin )
%rubberSheetNormalisation, function that normalizes the iris region. This is
%the region between the pupil boundary and the limbus. This is done
%according to the rubber sheet model proposed by Daugman (1).
%
% SYNOPSIS
% - image = rubberSheetNormalisation( img, xPosPupil, yPosPupil, rPupil , xPosIris , yPosIris , rIris )
% - image = rubberSheetNormalisation( img, xPosPupil, yPosPupil, rPupil , xPosIris , yPosIris , rIris , 'DebugMode' , 1 )
%
% INPUTS
% - img <double>
% Eye image from the cassini, preferably a NIR image. If no image
% is supplied, a pop up will ask to select one.
% - xPosPupil <integer>, yPosPupil <integer>, rPupil <integer>
% The x,y-position of the pupil center and the pupil radius
% - xPosIris <integer>, yPosIris <integer>, rIris <integer>
% The x,y-position of the iris center and the iris radius
% - varargin <optional>, input scheme
% 'DebugMode': {0: off, 1: on} - if set to 1 shows extra info
% 'AngleSamples': <integer> - number of radial samples
% 'RadiusSamples': <integer> - number of radius samples
% 'UseInterpolation': <boolean> - if 1, the samples will be
% interpolated else nearest neighbor interpolation is used.
%
% OUTPUT
% - image, containing the normalized iris region
%
% DEPENDANCIES
% - Communications Toolbox
% - Computer Vision System Toolbox (for debugmode)
%
% HISTORY
% - 26th may 2017: removed Communications Toolbox
% - 19th June 2016: added the interpolation option
%
% REFERENCES
% (1) How iris recognition works, Daugman, J.G.
%
% AUTHOR
% F.C. Martin <frank@grafikus.nl>
% 19th of May 2015 - 26th may 2017
%
% - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
% Load the image
img = imread('1.jpg');
% Input parameters
xPosPupil = 1007;
yPosPupil = 947;
rPupil = 503;
xPosIris = 313;
yPosIris = 323;
rIris = 156;
% Normalize the iris region according to daugmans model
irisRegion = rubberSheetNormalisation( img, xPosPupil, yPosPupil, rPupil , xPosIris , yPosIris , rIris, 'DebugMode', 1 );
%todo: remove for-loop for line detection
if(size(img, 3) == 3) % if RGB image is inputted
img = rgb2gray(img);
end
% parse input
p = inputParser();
addRequired( p , 'xPosPupil' , @isnumeric );
addRequired( p , 'yPosPupil' , @isnumeric );
addRequired( p , 'rPupil' , @isnumeric );
addRequired( p , 'xPosIris' , @isnumeric );
addRequired( p , 'yPosIris' , @isnumeric );
addRequired( p , 'rIris' , @isnumeric );
addOptional( p , 'AngleSamples', 360 ,@isnumeric );
addOptional( p , 'RadiusSamples', 360 ,@isnumeric );
addOptional( p , 'DebugMode', 0, @isnumeric );
addOptional( p , 'UseInterpolation', 1, @isnumeric );
parse( p , xPosPupil, yPosPupil, rPupil , xPosIris , yPosIris , rIris , varargin{:} )
% Normalize the iris region according to daugmans model
% irisRegion = rubberSheetNormalisation( img, xPosPupil, yPosPupil, rPupil , xPosIris , yPosIris , rIris, 'DebugMode', 1 );
% Note that internally matrix coordinates are used
xp = p.Results.yPosPupil;
yp = p.Results.xPosPupil;
rp = p.Results.rPupil;
xi = p.Results.yPosIris;
yi = p.Results.xPosIris;
ri = p.Results.rIris;
angleSamples = p.Results.AngleSamples;
RadiusSamples = p.Results.RadiusSamples;
debug = p.Results.DebugMode;
interpolateQ = p.Results.UseInterpolation;
% Initialize samples
angles = (0:pi/angleSamples:pi-pi/angleSamples) + pi/(2*angleSamples);%avoiding infinite slope
r = 0:1/RadiusSamples:1;
nAngles = length(angles);
% Calculate pupil points and iris points that are on the same line
x1 = ones(size(angles))*xi;
y1 = ones(size(angles))*yi;
x2 = xi + 10*sin(angles);
y2 = yi + 10*cos(angles);
dx = x2 - x1;
dy = y2 - y1;
slope = dy./dx;
intercept = yi - xi .* slope;
xout = zeros(nAngles,2);
yout = zeros(nAngles,2);
for i = 1:nAngles
[xout(i,:),yout(i,:)] = linecirc(slope(i),intercept(i),xp,yp,rp);
end
% Get samples on limbus boundary
xRightIris = yi + ri * cos(angles);
yRightIris = xi + ri * sin(angles);
xLeftIris = yi - ri * cos(angles);
yLeftIris = xi - ri * sin(angles);
% Get samples in radius direction
xrt = (1-r)' * xout(:,1)' + r' * yRightIris;
yrt = (1-r)' * yout(:,1)' + r' * xRightIris;
xlt = (1-r)' * xout(:,2)' + r' * yLeftIris;
ylt = (1-r)' * yout(:,2)' + r' * xLeftIris;
% Create Normalized Iris Image
if interpolateQ
image = uint8(reshape(interp2(double(img),[yrt(:);ylt(:)],[xrt(:);xlt(:)]),length(r), 2*length(angles))');
else
image = reshape(img(sub2ind(size(img),round([xrt(:);xlt(:)]),round([yrt(:);ylt(:)]))),length(r), 2*length(angles));
end
% Show all points on original input image
if debug
img = insertShape(img, 'circle', [yrt(:),xrt(:),2*ones(size(xrt(:)))],'Color','r');
img = insertShape(img, 'circle', [ylt(:),xlt(:),2*ones(size(xrt(:)))],'Color','r');
figure('name','Sample scheme of the rubber sheet normalization');
imshow(img);
drawnow;
end
% Show Resulting image
figure(2);
imshow(irisRegion);
end
Frank Martin
2019-4-16
I feel this is no longer in the scope of providing support for my script, as these are more general Matlab questions. I recommend you follow some basic Matlab tutorials from:
syahira samsudin
2019-4-16
更多回答（0 个）
类别
在 帮助中心 和 File Exchange 中查找有关 Tracking and Motion Estimation 的更多信息
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!
Translated by 
