I implemented a method for removing shadows based on invariant color features found in the paper Entropy Minimization for Shadow Removal. My implementation seems to be yielding similar computational results sometimes, but they are always off, and my grayscale image is blocky, maybe as a result of incorrectly taking the geometric mean.
Here is an example plot of the information potential from the horse image in the paper as well as my invariant image. Multiply the x-axis by 3 to get theta(which goes from 0 to 180):
And here is the grayscale Image my code outputs for the correct maximum theta (mine is off by 10):
You can see the blockiness that their image doesn't have:
Here is their information potential:
When dividing by the geometric mean, I have tried using NaN and tresholding the image so the smallest possible value is .01, but it doesn't seem to change my output.
Here is my code:
I = im2double(imread(strname));
[m,n,d] = size(I);
I = max(I, .01);
chrom = zeros(m, n, 3, 'double');
for i = 1:m
for j = 1:n
% if ((I(i,j,1)*I(i,j,2)*I(i,j,3))~= 0)
chrom(i,j, 1) = I(i,j,1)/((I(i,j,1)*I(i,j,2)*I(i,j, 3))^(1/3));
chrom(i,j, 2) = I(i,j,2)/((I(i,j,1)*I(i,j,2)*I(i,j, 3))^(1/3));
chrom(i,j, 3) = I(i,j,3)/((I(i,j,1)*I(i,j,2)*I(i,j, 3))^(1/3));
% else
% chrom(i,j, 1) = 1;
% chrom(i,j, 2) = 1;
% chrom(i,j, 3) = 1;
% end
end
end
p1 = mat2gray(log(chrom(:,:,1)));
p2 = mat2gray(log(chrom(:,:,2)));
p3 = mat2gray(log(chrom(:,:,3)));
X1 = mat2gray(p1*1/(sqrt(2)) - p2*1/(sqrt(2)));
X2 = mat2gray(p1*1/(sqrt(6)) + p2*1/(sqrt(6)) - p3*2/(sqrt(6)));
maxinf = 0;
maxtheta = 0;
data2 = zeros(1, 61);
for theta = 0:3:180
M = X1*cos(theta*pi/180) - X2*sin(theta*pi/180);
s = sqrt(std2(X1)^(2)*cos(theta*pi/180) + std2(X2)^(2)*sin(theta*pi/180));
s = abs(1.06*s*((m*n)^(-1/5)));
[m, n] = size(M);
length = m*n;
sources = zeros(1, length, 'double');
count = 1;
for x=1:m
for y = 1:n
sources(1, count) = M(x , y);
count = count + 1;
end
end
weights = ones(1, length);
sigma = 2*s;
[xc , Ak] = fgt_model(sources , weights , sigma , 10, sqrt(length) , 6 );
sum1 = sum(fgt_predict(sources , xc , Ak , sigma , 10 ));
sum1 = sum1/sqrt(2*pi*2*s*s);
data2(theta/3 + 1) = sum1;
if (sum1 > maxinf)
maxinf = sum1;
maxtheta = theta;
end
end
InvariantImage2 = cos(maxtheta*pi/180)*X1 + sin(maxtheta*pi/180)*X2;
Assume the Fast Gauss Transform is correct.
I don't know whether this makes any difference as it is more than a month now, but the blockiness and different information potential plot is simply caused by compression of the used image. You can't expect to be getting same results using this image as they had, because they have used raw, high resolution uncompressed version of it. I have to say I am fairly impressed with your results, especially with implementing the information potential. That thing went over my head a little.
John.
Related
I am using regress to perform linear regression on a large nc file (containing lat, lon, time, and temperature). So for each lat, lon, temperature is regressed over 30 years (one measurement each year).
In some years, some temperatures are 0 K, in those cases I want the loop to not regress, so the final mean slope does not include these.
Below is the important part of my code.
I am not getting an error but also not getting any difference in whether i include y(y==0) = NaN;, so I think there may be a better way. I had understood that regress ignores these automatically, but that also appears to not be the case.
% initialise time parameters
time_begin = [1981, 1, 1, 0,0,0];
time_end = [2010,12,31,23,0,0];
years = (time_begin(1):time_end(1))';
nyears = length(years);
% create storage and regress
TXx = randi(100, 288, 192, 30);
lat = rand(192, 1);
lon = rand(288, 1);
time = rand(30,1);
M = numel(lon);
N = numel(lat);
slope = zeros(M, N);
intercept = zeros(M, N);
T = numel(time);
x = ([ones(T, 1) years]);
% Regress each lat/lon location
for i = 1 : M
for j = 1 : N
% Get all time instances of each lat/lon location
y = squeeze(TXx(i, j, :));
y(y==0) = NaN;
% Create regression problem and solve
c = regress(y, x);
intercept(i, j) = c(1);
slope(i, j) = c(2);
end
end
The NaN's are being ignored, but not in the way you want... The individual data points are ignored, not the entire data set, and thus still a regression is made.
You could simply add a simple check using an if statement,
for i = 1 : M
for j = 1 : N
% Get all time instances of each lat/lon location
y = squeeze(TXx(i, j, :));
if ~any(y==0)
% Create regression problem and solve
c = regress(y, x);
intercept(i, j) = c(1);
slope(i, j) = c(2);
end
end
end
I am trying to implement a simple pixel level center-surround image enhancement. Center-surround technique makes use of statistics between the center pixel of the window and the surrounding neighborhood as a means to decide what enhancement needs to be done. In the code given below I have compared the center pixel with average of the surrounding information and based on that I switch between two cases to enhance the contrast. The code that I have written is as follows:
im = normalize8(im,1); %to set the range of pixel from 0-255
s1 = floor(K1/2); %K1 is the size of the window for surround
M = 1000; %is a constant value
out1 = padarray(im,[s1,s1],'symmetric');
out1 = CE(out1,s1,M);
out = (out1(s1+1:end-s1,s1+1:end-s1));
out = normalize8(out,0); %to set the range of pixel from 0-1
function [out] = CE(out,s,M)
B = 255;
out1 = out;
for i = s+1 : size(out,1) - s
for j = s+1 : size(out,2) - s
temp = out(i-s:i+s,j-s:j+s);
Yij = out1(i,j);
Sij = (1/(2*s+1)^2)*sum(sum(temp));
if (Yij>=Sij)
Aij = A(Yij-Sij,M);
out1(i,j) = ((B + Aij)*Yij)/(Aij+Yij);
else
Aij = A(Sij-Yij,M);
out1(i,j) = (Aij*Yij)/(Aij+B-Yij);
end
end
end
out = out1;
function [Ax] = A(x,M)
if x == 0
Ax = M;
else
Ax = M/x;
end
The code does the following things:
1) Normalize the image to 0-255 range and pad it with additional elements to perform windowing operation.
2) Calls the function CE.
3) In the function CE obtain the windowed image(temp).
4) Find the average of the window (Sij).
5) Compare the center of the window (Yij) with the average value (Sij).
6) Based on the result of comparison perform one of the two enhancement operation.
7) Finally set the range back to 0-1.
I have to run this for multiple window size (K1,K2,K3, etc.) and the images are of size 1728*2034. When the window size is selected as 100, the time consumed is very high.
Can I use vectorization at some stage to reduce the time for loops?
The profiler result (for window size 21) is as follows:
The profiler result (for window size 100) is as follows:
I have changed the code of my function and have written it without the sub-function. The code is as follows:
function [out] = CE(out,s,M)
B = 255;
Aij = zeros(1,2);
out1 = out;
n_factor = (1/(2*s+1)^2);
for i = s+1 : size(out,1) - s
for j = s+1 : size(out,2) - s
temp = out(i-s:i+s,j-s:j+s);
Yij = out1(i,j);
Sij = n_factor*sum(sum(temp));
if Yij-Sij == 0
Aij(1) = M;
Aij(2) = M;
else
Aij(1) = M/(Yij-Sij);
Aij(2) = M/(Sij-Yij);
end
if (Yij>=Sij)
out1(i,j) = ((B + Aij(1))*Yij)/(Aij(1)+Yij);
else
out1(i,j) = (Aij(2)*Yij)/(Aij(2)+B-Yij);
end
end
end
out = out1;
There is a slight improvement in the speed from 93 sec to 88 sec. Suggestions for any other improvements to my code are welcomed.
I have tried to incorporate the suggestions given to replace sliding window with convolution and then vectorize the rest of it. The code below is my implementation and I'm not getting the result expected.
function [out_im] = CE_conv(im,s,M)
B = 255;
temp = ones(2*s,2*s);
temp = temp ./ numel(temp);
out1 = conv2(im,temp,'same');
out_im = im;
Aij = im-out1; %same as Yij-Sij
Aij1 = out1-im; %same as Sij-Yij
Mij = Aij;
Mij(Aij>0) = M./Aij(Aij>0); % if Yij>Sij Mij = M/Yij-Sij;
Mij(Aij<0) = M./Aij1(Aij<0); % if Yij<Sij Mij = M/Sij-Yij;
Mij(Aij==0) = M; % if Yij-Sij == 0 Mij = M;
out_im(Aij>=0) = ((B + Mij(Aij>=0)).*im(Aij>=0))./(Mij(Aij>=0)+im(Aij>=0));
out_im(Aij<0) = (Mij(Aij<0).*im(Aij<0))./ (Mij(Aij<0)+B-im(Aij<0));
I am not able to figure out where I'm going wrong.
A detailed explanation of what I'm trying to implement is given in the following paper:
Vonikakis, Vassilios, and Ioannis Andreadis. "Multi-scale image contrast enhancement." In Control, Automation, Robotics and Vision, 2008. ICARCV 2008. 10th International Conference on, pp. 856-861. IEEE, 2008.
I've tried to see if I could get those times down by processing with colfiltand nlfilter, since both are usually much faster than for-loops for sliding window image processing.
Both worked fine for relatively small windows. For an image of 2048x2048 pixels and a window of 10x10, the solution with colfilt takes about 5 seconds (on my personal computer). With a window of 21x21 the time jumped to 27 seconds, but that is still a relative improvement on the times displayed on the question. Unfortunately I don't have enough memory to colfilt using windows of 100x100, but the solution with nlfilter works, though taking about 120 seconds.
Here the code
Solution with colfilt:
function outval = enhancematrix(inputmatrix,M,B)
%Inputmatrix is a 2D matrix or column vector, outval is a 1D row vector.
% If inputmatrix is made of integers...
inputmatrix = double(inputmatrix);
%1. Compute S and Y
normFactor = 1 / (size(inputmatrix,1) + 1).^2; %Size of column.
S = normFactor*sum(inputmatrix,1); % Sum over the columns.
Y = inputmatrix(ceil(size(inputmatrix,1)/2),:); % Center row.
% So far we have all S and Y, one value per column.
%2. Compute A(abs(Y-S))
A = Afunc(abs(S-Y),M);
% And all A: one value per column.
%3. The tricky part. If Y(i)-S(i) > 0 do something.
doPositive = (Y > S);
doNegative = ~doPositive;
outval = zeros(1,size(inputmatrix,2));
outval(doPositive) = (B + A(doPositive) .* Y(doPositive)) ./ (A(doPositive) + Y(doPositive));
outval(doNegative) = (A(doNegative) .* Y(doNegative)) ./ (A(doNegative) + B - Y(doNegative));
end
function out = Afunc(x,M)
% Input x is a row vector. Output is another row vector.
out = x;
out(x == 0) = M;
out(x ~= 0) = M./x(x ~= 0);
end
And to call it, simply do:
M = 1000; B = 255; enhancenow = #(x) enhancematrix(x,M,B);
w = 21 % windowsize
result = colfilt(inputImage,[w w],'sliding',enhancenow);
Solution with nlfilter:
function outval = enhanceimagecontrast(neighbourhood,M,B)
%1. Compute S and Y
normFactor = 1 / (length(neighbourhood) + 1).^2;
S = normFactor*sum(neighbourhood(:));
Y = neighbourhood(ceil(size(neighbourhood,1)/2),ceil(size(neighbourhood,2)/2));
%2. Compute A(abs(Y-S))
test = (Y>=S);
A = Afunc(abs(Y-S),M);
%3. Return outval
if test
outval = ((B + A) * Y) / (A + Y);
else
outval = (A * Y) / (A + B - Y);
end
function aval = Afunc(x,M)
if (x == 0)
aval = M;
else
aval = M/x;
end
And to call it, simply do:
M = 1000; B = 255; enhancenow = #(x) enhanceimagecontrast(x,M,B);
w = 21 % windowsize
result = nlfilter(inputImage,[w w], enhancenow);
I didn't spend much time checking that everything is 100% correct, but I did see some nice contrast enhancement (hair looks particularly nice).
This answer is the implementation that was suggested by Peter. I debugged the implementation and presenting the final working version of the fast implementation.
function [out_im] = CE_conv(im,s,M)
B = 255;
im = ( im - min(im(:)) ) ./ ( max(im(:)) - min(im(:)) )*255;
h = ones(s,s)./(s*s);
out1 = imfilter(im,h,'conv');
out_im = im;
Aij = im-out1; %same as Yij-Sij
Aij1 = out1-im; %same as Sij-Yij
Mij = Aij;
Mij(Aij>0) = M./Aij(Aij>0); % if Yij>Sij Mij = M/(Yij-Sij);
Mij(Aij<0) = M./Aij1(Aij<0); % if Yij<Sij Mij = M/(Sij-Yij);
Mij(Aij==0) = M; % if Yij-Sij == 0 Mij = M;
out_im(Aij>=0) = ((B + Mij(Aij>=0)).*im(Aij>=0))./(Mij(Aij>=0)+im(Aij>=0));
out_im(Aij<0) = (Mij(Aij<0).*im(Aij<0))./ (Mij(Aij<0)+B-im(Aij<0));
out_im = ( out_im - min(out_im(:)) ) ./ ( max(out_im(:)) - min(out_im(:)) );
To call this use the following code
I = imread('pout.tif');
w_size = 51;
M = 4000;
output = CE_conv(I(:,:,1),w_size,M);
The output for the 'pout.tif' image is given below
The execution time for Bigger image and with 100*100 block size is around 5 secs with this implementation.
Normally, a Gabor filter, as its name suggests, is used to filter an image and extract everything that it is oriented in the same direction of the filtering.
In this question, you can see more efficient code than written in this Link
Assume 16 scales of Filters at 4 orientations, so we get 64 gabor filters.
scales=[7:2:37], 7x7 to 37x37 in steps of two pixels, so we have 7x7, 9x9, 11x11, 13x13, 15x15, 17x17, 19x19, 21x21, 23x23, 25x25, 27x27, 29x29, 31x31, 33x33, 35x35 and 37x37.
directions=[0, pi/4, pi/2, 3pi/4].
The equation of Gabor filter in the spatial domain is:
The equation of Gabor filter in the frequency domain is:
In the spatial domain:
function [fSiz,filters,c1OL,numSimpleFilters] = init_gabor(rot, RF_siz)
image=imread('xxx.jpg');
image_gray=rgb2gray(image);
image_gray=imresize(image_gray, [100 100]);
image_double=double(image_gray);
rot = [0 45 90 135]; % we have four orientations
RF_siz = [7:2:37]; %we get 16 scales (7x7 to 37x37 in steps of two pixels)
minFS = 7; % the minimum receptive field
maxFS = 37; % the maximum receptive field
sigma = 0.0036*RF_siz.^2 + 0.35*RF_siz + 0.18; %define the equation of effective width
lambda = sigma/0.8; % it the equation of wavelength (lambda)
G = 0.3; % spatial aspect ratio: 0.23 < gamma < 0.92
numFilterSizes = length(RF_siz); % we get 16
numSimpleFilters = length(rot); % we get 4
numFilters = numFilterSizes*numSimpleFilters; % we get 16x4 = 64 filters
fSiz = zeros(numFilters,1); % It is a vector of size numFilters where each cell contains the size of the filter (7,7,7,7,9,9,9,9,11,11,11,11,......,37,37,37,37)
filters = zeros(max(RF_siz)^2,numFilters); % Matrix of Gabor filters of size %max_fSiz x num_filters, where max_fSiz is the length of the largest filter and num_filters the total number of filters. Column j of filters matrix contains a n_jxn_j filter (reshaped as a column vector and padded with zeros).
for k = 1:numFilterSizes
for r = 1:numSimpleFilters
theta = rot(r)*pi/180; % so we get 0, pi/4, pi/2, 3pi/4
filtSize = RF_siz(k);
center = ceil(filtSize/2);
filtSizeL = center-1;
filtSizeR = filtSize-filtSizeL-1;
sigmaq = sigma(k)^2;
for i = -filtSizeL:filtSizeR
for j = -filtSizeL:filtSizeR
if ( sqrt(i^2+j^2)>filtSize/2 )
E = 0;
else
x = i*cos(theta) - j*sin(theta);
y = i*sin(theta) + j*cos(theta);
E = exp(-(x^2+G^2*y^2)/(2*sigmaq))*cos(2*pi*x/lambda(k));
end
f(j+center,i+center) = E;
end
end
f = f - mean(mean(f));
f = f ./ sqrt(sum(sum(f.^2)));
p = numSimpleFilters*(k-1) + r;
filters(1:filtSize^2,p)=reshape(f,filtSize^2,1);
fSiz(p)=filtSize;
end
end
% Rebuild all filters (of all sizes)
nFilts = length(fSiz);
for i = 1:nFilts
sqfilter{i} = reshape(filters(1:(fSiz(i)^2),i),fSiz(i),fSiz(i));
%if you will use conv2 to convolve an image with this gabor, so you should also add the equation below. But if you will use imfilter instead of conv2, so do not add the equation below.
sqfilter{i} = sqfilter{i}(end:-1:1,end:-1:1); %flip in order to use conv2 instead of imfilter (%bug_fix 6/28/2007);
convv=imfilter(image_double, sqfilter{i}, 'same', 'conv');
figure;
imagesc(convv);
colormap(gray);
end
phi = ij*pi/4; % ij = 0, 1, 2, 3
theta = 3;
sigma = 0.65*theta;
filterSize = 7; % 7:2:37
G = zeros(filterSize);
for i=(0:filterSize-1)/filterSize
for j=(0:filterSize-1)/filterSize
xprime= j*cos(phi);
yprime= i*sin(phi);
K = exp(2*pi*theta*sqrt(-1)*(xprime+ yprime));
G(round((i+1)*filterSize),round((j+1)*filterSize)) =...
exp(-(i^2+j^2)/(sigma^2))*K;
end
end
As of R2015b release of the Image Processing Toolbox, you can create a Gabor filter bank using the gabor function in the image processing toolbox, and you can apply it to an image using imgaborfilt.
In the frequency domain:
sigma_u=1/2*pi*sigmaq;
sigma_v=1/2*pi*sigmaq;
u0=2*pi*cos(theta)*lambda(k);
v0=2*pi*sin(theta)*lambda(k);
for u = -filtSizeL:filtSizeR
for v = -filtSizeL:filtSizeR
if ( sqrt(u^2+v^2)>filtSize/2 )
E = 0;
else
v_theta = u*cos(theta) - v*sin(theta);
u_theta = u*sin(theta) + v*cos(theta);
E=(1/2*pi*sigma_u*sigma_v)*((exp((-1/2)*(((u_theta-u0)^2/sigma_u^2))+((v_theta-v0)^2/sigma_v^2))) + (exp((-1/2)*(((u_theta+u0)^2/sigma_u^2))+((v_theta+v0)^2/sigma_v^2))));
end
f(v+center,u+center) = E;
end
end
I'm trying to produce some computer generated holograms by using MATLAB. I used equally spaced mesh grid to initialize the spatial grid, and I got the following image
This pattern is sort of what I need except the center region. The fringe should be sharp but blurred. I think it might be the problem of the mesh grid. I tried generate a grid in polar coordinates and the map it into Cartesian coordinates by using MATLAB's pol2cart function. Unfortunately, it doesn't work as well. One may suggest that using fine grids. It doesn't work too. I think if I can generate a spiral mesh grid, perhaps the problem is solvable. In addition, the number of the spiral arms could, in general, be arbitrary, could anyone give me a hint on this?
I've attached the code (My final projects are not exactly the same, but it has a similar problem).
clc; clear all; close all;
%% initialization
tic
lambda = 1.55e-6;
k0 = 2*pi/lambda;
c0 = 3e8;
eta0 = 377;
scale = 0.25e-6;
NELEMENTS = 1600;
GoldenRatio = (1+sqrt(5))/2;
g = 2*pi*(1-1/GoldenRatio);
pntsrc = zeros(NELEMENTS, 3);
phisrc = zeros(NELEMENTS, 1);
for idxe = 1:NELEMENTS
pntsrc(idxe, :) = scale*sqrt(idxe)*[cos(idxe*g), sin(idxe*g), 0];
phisrc(idxe) = angle(-sin(idxe*g)+1i*cos(idxe*g));
end
phisrc = 3*phisrc/2; % 3 arms (topological charge ell=3)
%% post processing
sigma = 1;
polfilter = [0, 0, 1i*sigma; 0, 0, -1; -1i*sigma, 1, 0]; % cp filter
xboundl = -100e-6; xboundu = 100e-6;
yboundl = -100e-6; yboundu = 100e-6;
xf = linspace(xboundl, xboundu, 100);
yf = linspace(yboundl, yboundu, 100);
zf = -400e-6;
[pntobsx, pntobsy] = meshgrid(xf, yf);
% how to generate a right mesh grid such that we can generate a decent result?
pntobs = [pntobsx(:), pntobsy(:), zf*ones(size(pntobsx(:)))];
% arbitrary mesh may result in "wrong" results
NPNTOBS = size(pntobs, 1);
nxp = length(xf);
nyp = length(yf);
%% observation
Eobs = zeros(NPNTOBS, 3);
matlabpool open local 12
parfor nobs = 1:NPNTOBS
rp = pntobs(nobs, :);
Erad = [0; 0; 0];
for idx = 1:NELEMENTS
rs = pntsrc(idx, :);
p = exp(sigma*1i*2*phisrc(idx))*[1 -sigma*1i 0]/2; % simplified here
u = rp - rs;
r = sqrt(u(1)^2+u(2)^2+u(3)^2); %norm(u);
u = u/r; % unit vector
ut = [u(2)*p(3)-u(3)*p(2),...
u(3)*p(1)-u(1)*p(3), ...
u(1)*p(2)-u(2)*p(1)]; % cross product: u cross p
Erad = Erad + ... % u cross p cross u, do not use the built-in func
c0*k0^2/4/pi*exp(1i*k0*r)/r*eta0*...
[ut(2)*u(3)-ut(3)*u(2);...
ut(3)*u(1)-ut(1)*u(3); ...
ut(1)*u(2)-ut(2)*u(1)];
end
Eobs(nobs, :) = Erad; % filter neglected here
end
matlabpool close
Eobs = Eobs/max(max(sum(abs(Eobs), 2))); % normailized
%% source, gaussian beam
E0 = 1;
w0 = 80e-6;
theta = 0; % may be titled
RotateX = [1, 0, 0; ...
0, cosd(theta), -sind(theta); ...
0, sind(theta), cosd(theta)];
Esrc = zeros(NPNTOBS, 3);
for nobs = 1:NPNTOBS
rp = RotateX*[pntobs(nobs, 1:2).'; 0];
z = rp(3);
r = sqrt(sum(abs(rp(1:2)).^2));
zR = pi*w0^2/lambda;
wz = w0*sqrt(1+z^2/zR^2);
Rz = z^2+zR^2;
zetaz = atan(z/zR);
gaussian = E0*w0/wz*exp(-r^2/wz^2-1i*k0*z-1i*k0*0*r^2/Rz/2+1i*zetaz);% ...
Esrc(nobs, :) = (polfilter*gaussian*[1; -1i; 0]).'/sqrt(2)/2;
end
Esrc = [Esrc(:, 2), Esrc(:, 3), Esrc(:, 1)];
Esrc = Esrc/max(max(sum(abs(Esrc), 2))); % normailized
toc
%% visualization
fringe = Eobs + Esrc; % I'll have a different formula in my code
normEsrc = reshape(sum(abs(Esrc).^2, 2), [nyp nxp]);
normEobs = reshape(sum(abs(Eobs).^2, 2), [nyp nxp]);
normFringe = reshape(sum(abs(fringe).^2, 2), [nyp nxp]);
close all;
xf0 = linspace(xboundl, xboundu, 500);
yf0 = linspace(yboundl, yboundu, 500);
[xfi, yfi] = meshgrid(xf0, yf0);
data = interp2(xf, yf, normFringe, xfi, yfi);
figure; surf(xfi, yfi, data,'edgecolor','none');
% tri = delaunay(xfi, yfi); trisurf(tri, xfi, yfi, data, 'edgecolor','none');
xlim([xboundl, xboundu])
ylim([yboundl, yboundu])
% colorbar
view(0,90)
colormap(hot)
axis equal
axis off
title('fringe thereo. ', ...
'fontsize', 18)
I didn't read your code because it is too long to do such a simple thing. I wrote mine and here is the result:
the code is
%spiral.m
function val = spiral(x,y)
r = sqrt( x*x + y*y);
a = atan2(y,x)*2+r;
x = r*cos(a);
y = r*sin(a);
val = exp(-x*x*y*y);
val = 1/(1+exp(-1000*(val)));
endfunction
%show.m
n=300;
l = 7;
A = zeros(n);
for i=1:n
for j=1:n
A(i,j) = spiral( 2*(i/n-0.5)*l,2*(j/n-0.5)*l);
end
end
imshow(A) %don't know if imshow is in matlab. I used octave.
the key for the sharpnes is line
val = 1/(1+exp(-1000*(val)));
It is logistic function. The number 1000 defines how sharp your image will be. So lower it for more blurry image or higher it for sharper.
I hope this answers your question ;)
Edit: It is real fun to play with. Here is another spiral:
function val = spiral(x,y)
s= 0.5;
r = sqrt( x*x + y*y);
a = atan2(y,x)*2+r*r*r;
x = r*cos(a);
y = r*sin(a);
val = 0;
if (abs(x)<s )
val = s-abs(x);
endif
if(abs(y)<s)
val =max(s-abs(y),val);
endif
%val = 1/(1+exp(-1*(val)));
endfunction
Edit2: Fun, fun, fun! Here the arms do not get thinner.
function val = spiral(x,y)
s= 0.1;
r = sqrt( x*x + y*y);
a = atan2(y,x)*2+r*r; % h
x = r*cos(a);
y = r*sin(a);
val = 0;
s = s*exp(r);
if (abs(x)<s )
val = s-abs(x);
endif
if(abs(y)<s)
val =max(s-abs(y),val);
endif
val = val/s;
val = 1/(1+exp(-10*(val)));
endfunction
Damn your question I really need to study for my exam, arghhh!
Edit3:
I vectorised the code and it runs much faster.
%spiral.m
function val = spiral(x,y)
s= 2;
r = sqrt( x.*x + y.*y);
a = atan2(y,x)*8+exp(r);
x = r.*cos(a);
y = r.*sin(a);
val = 0;
s = s.*exp(-0.1*r);
val = r;
val = (abs(x)<s ).*(s-abs(x));
val = val./s;
% val = 1./(1.+exp(-1*(val)));
endfunction
%show.m
n=1000;
l = 3;
A = zeros(n);
[X,Y] = meshgrid(-l:2*l/n:l);
A = spiral(X,Y);
imshow(A)
Sorry, can't post figures. But this might help. I wrote it for experiments with amplitude spatial modulators...
R=70; % radius of curvature of fresnel lens (in pixel units)
A=0; % oblique incidence by linear grating (1=oblique 0=collinear)
B=1; % expanding by fresnel lens (1=yes 0=no)
L=7; % topological charge
Lambda=30; % linear grating fringe spacing (in pixels)
aspect=1/2; % fraction of fringe period that is white/clear
xsize=1024; % resolution (xres x yres number data pts calculated)
ysize=768; %
% define the X and Y ranges (defined to skip zero)
xvec = linspace(-xsize/2, xsize/2, xsize); % list of x values
yvec = linspace(-ysize/2, ysize/2, ysize); % list of y values
% define the meshes - matrices linear in one dimension
[xmesh, ymesh] = meshgrid(xvec, yvec);
% calculate the individual phase components
vortexPh = atan2(ymesh,xmesh); % the vortex phase
linPh = -2*pi*ymesh; % a phase of linear grating
radialPh = (xmesh.^2+ymesh.^2); % a phase of defocus
% combine the phases with appropriate scales (phases are additive)
% the 'pi' at the end causes inversion of the pattern
Ph = L*vortexPh + A*linPh/Lambda + B*radialPh/R^2;
% transmittance function (the real part of exp(I*Ph))
T = cos(Ph);
% the binary version
binT = T > cos(pi*aspect);
% plot the pattern
% imagesc(binT)
imagesc(T)
colormap(gray)
I'm trying to implement a very basic eigenface calculation in Matlab. It kind of works but I get only two meaningful eigenvalues - the rest are zero. The corresponding eigenvectors seem to be right since most of them will show an eigenface when converting to an image.
So why are most of my eigenvalues zero? I need them to be different from zero in order to sort the eigenfaces by their significance (greatest magnitude eigenvalues).
I am reading 400 images, each size h/w = 112/92 px
They can be found here: http://www.cl.cam.ac.uk/Research/DTG/attarchive/pub/data/att_faces.zip
The code:
clear all;
files = dir('eigenfaces2/training/*.pgm');
[numFaces, discard] = size(files);
h = 112;
w = 92;
s = h * w;
%calculate average face
avgFace = zeros(s, 1);
faces = [];
for i=1:numFaces
file = strcat('eigenfaces2/training/', files(i).name);
im = double(imread(file));
im = reshape(im, s, 1);
avgFace = avgFace + im;
faces(:,i) = im;
end
avgFace = avgFace ./ numFaces;
A = [];
for i=1:numFaces
diff = avgFace - faces(i);
A(:,i) = diff;
end
numEigs = 20;
L = (A' * A) / numFaces;
[tmpEigs, discard] = eigs(L, numEigs);
eigenfaces = [];
for i=1:numEigs
v = tmpEigs(:,i);
eigenfaces(:,i) = A * v;
end
%visualize largest eigenfaces
figure;
for i=1:numEigs
eigface = eigenfaces(:,i);
mmax = max(eigface);
mmin = min(eigface);
eigface = 255 .* (eigface-mmin) ./ (mmax-mmin);
eigface = reshape(eigface, h, w);
subplot(4,5,i); imshow(uint8(eigface));
end
I've don't have much experience with computer vision/image recognition, but I think you might want
diff = avgFace - faces(:,i);
in your second for loop. Otherwise it's just subtracting a constant from avgFace each time, and so A (and hence L) only gets a rank of 2.