如何在matlab中的3D图像上实现gabor滤波器

Question

我正在处理3D图像，并且我想实现Gabor特征。为此，我需要生成具有不同比例和方向（可能是3D，两个角度）的Gabor滤波器组，然后使用我的图像对其进行调整。我的问题是，是否有可能实现3D gabor滤镜，然后用3D图像对其进行校正。或者我在2D中一片一片地做。如果是这样，任何建议在matlab中实现它将不胜感激。

谢谢您提前

Answer 1

使它成为2D。 Gabor滤镜会自动将图像更改为灰度，因此无论如何，3D变得毫无用处。

这里是一个matlab的gabor滤波器，我用它，它完美的工作。

function gaborArray = gaborFilterBank(u,v,m,n) 

% GABORFILTERBANK generates a custum Gabor filter bank. 
% It creates a u by v array, whose elements are m by n matries; 
% each matrix being a 2-D Gabor filter. 
% 
% 
% Inputs: 
%  u : No. of scales (usually set to 5) 
%  v : No. of orientations (usually set to 8) 
%  m : No. of rows in a 2-D Gabor filter (an odd integer number usually set to 39) 
%  n : No. of columns in a 2-D Gabor filter (an odd integer number usually set to 39) 
% 
% Output: 
%  gaborArray: A u by v array, element of which are m by n 
%     matries; each matrix being a 2-D Gabor filter 
% 
% 
% Sample use: 
% 
% gaborArray = gaborFilterBank(5,8,39,39); 
% 
% 
% Details can be found in: 
% 
% M. Haghighat, S. Zonouz, M. Abdel-Mottaleb, "Identification Using 
% Encrypted Biometrics," Computer Analysis of Images and Patterns, 
% Springer Berlin Heidelberg, pp. 440-448, 2013. 
% 
% 
% (C) Mohammad Haghighat, University of Miami 
%  haghighat@ieee.org 
%  I WILL APPRECIATE IF YOU CITE OUR PAPER IN YOUR WORK. 



if (nargin ~= 4) % Check correct number of arguments 
    error('There should be four inputs.') 
end 


%% Create Gabor filters 

% Create u*v gabor filters each being an m*n matrix 

gaborArray = cell(u,v); 
fmax = 0.25; 
gama = sqrt(2); 
eta = sqrt(2); 

for i = 1:u 

    fu = fmax/((sqrt(2))^(i-1)); 
    alpha = fu/gama; 
    beta = fu/eta; 

    for j = 1:v 
     tetav = ((j-1)/v)*pi; 
     gFilter = zeros(m,n); 

     for x = 1:m 
      for y = 1:n 
       xprime = (x-((m+1)/2))*cos(tetav)+(y-((n+1)/2))*sin(tetav); 
       yprime = -(x-((m+1)/2))*sin(tetav)+(y-((n+1)/2))*cos(tetav); 
       gFilter(x,y) = (fu^2/(pi*gama*eta))*exp(-((alpha^2)*(xprime^2)+(beta^2)*(yprime^2)))*exp(1i*2*pi*fu*xprime); 
      end 
     end 
     gaborArray{i,j} = gFilter; 

    end 
end 


%% Show Gabor filters 

% Show magnitudes of Gabor filters: 
figure('NumberTitle','Off','Name','Magnitudes of Gabor filters'); 
for i = 1:u 
    for j = 1:v   
     subplot(u,v,(i-1)*v+j);   
     imshow(abs(gaborArray{i,j}),[]); 
    end 
end 

% Show real parts of Gabor filters: 
figure('NumberTitle','Off','Name','Real parts of Gabor filters'); 
for i = 1:u 
    for j = 1:v   
     subplot(u,v,(i-1)*v+j);   
     imshow(real(gaborArray{i,j}),[]); 
    end 
end 

Answer 2

可以通过延长过滤器3点的尺寸实现3D Gabor滤波器，所以它变成：

高斯（X，Y，Z）* EXP（j * 2P *（的Ux + VY + Z Z）） 。欲了解更多信息请查看本文：

http://www.sciencedirect.com/science/article/pii/S0031320312003421#bib32