Correct image size in image mosaic - image

I'm implementing image mosaic in Matlab using SURF.the problem is
outputView = imref2d(size(img1)*2);
Ir = imwarp(img2,tform,'OutputView',outputView);
it produces
i want it something like this
if i change
outputView = imref2d(size(img1)*2);
to
outputView = imref2d(size(img1));
matlab crops the second image so it can fit in first image size after transforming.

Notice that when you warp the image with respect to the target plane, many of the pixels in this new plane are equal to 0. A very rudimentary algorithm is to simply threshold your image so that you find values above 0 then find the largest bounding box that encompasses the non-zero pixels... then crop:
[rows,cols] = find(Ir(:,:,1) > 0);
topLeftRow = min(rows);
topLeftCol = min(cols);
bottomRightRow = max(rows);
bottomRightCol = max(cols);
Ir_crop = Ir(topLeftRow:bottomRightRow, topLeftCol:bottomRightCol, :);

Related

Matlab picture intensity level adjustment

I have a specific question to ask about the intensity adjustment for image processing. I need high constraint value to find small gaps in the image which is shown as a red circle in the image. I used a manual threshold value 0.99 to convert the grayscale image to binary image for other processing methods. However, as the illumination on the surface did not distribute evenly, some parts of the image is lost. I used the adaptive method suggested by Matlab, however, the results is similar to a global threshold graythresh.
I will show my code and result below.
I0 = imread('1_2.jpg');
[R,C,K] = size(I0);
if K==1
I1 = I0;
else
I1 = rgb2gray(I0);
end
%Adjsut image to get a standar binary picture
%Adjust image intensity value
I1 = imadjust(I1,[0.1 0.7],[]);
BW0 = im2bw(I1,0.99);
figure;
BW0 = bwareaopen(BW0,10000);
%Fill non_crack hole error
BW0 = bwareaopen(1-BW0,500);
BW0 = 1-BW0;
imshow(BW0);
After this process, only half of the image will be left. I want a whole image, with locally intensity threshold but show the same feature as the high-level threshold. What can I do?
Thanks
Try adaptthresh:
I0 = imread('1_2.jpg');
[R,C,K] = size(I0);
if K==1
I1 = I0;
else
I1 = rgb2gray(I0);
end
T = adaptthresh(I1, 0.4); %adaptive thresholding
% Convert image to binary image, specifying the threshold value.
BW = imbinarize(I1,T);
% Display the original image with the binary version, side-by-side.
figure
imshowpair(I1, BW, 'montage')

Crop the largest square inside a circle object - Matlab

I am trying to find a way to crop from a circle object (Image A) the largest square that can fit inside it.
Can someone please explain/show me how to find the biggest square fit parameters of the white space inside the circle (Image I) and based on them crop the square in the original image (Image A).
Script:
A = imread('E:/CirTest/Test.jpg');
%imshow(A)
level = graythresh(A);
BW = im2bw(A,level);
%imshow(BW)
I = imfill(BW, 'holes');
imshow(I)
d = imdistline;
[centers, radii, metric] = imfindcircles(A,[1 500]);
imageCrop=imcrop(A, [BoxBottomX BoxBottomY NewX NewY]);
I have a solution for you but it requires a bit of extra work. What I would do first is use imfill but directly on the grayscale image. This way, noisy pixels in uniform areas get inpainted with the same intensities so that thresholding is easier. You can still use graythresh or Otsu's thresholding and do this on the inpainted image.
Here's some code to get you started:
figure; % Open up a new figure
% Read in image and convert to grayscale
A = rgb2gray(imread('http://i.stack.imgur.com/vNECg.jpg'));
subplot(1,3,1); imshow(A);
title('Original Image');
% Find the optimum threshold via Otsu
level = graythresh(A);
% Inpaint noisy areas
I = imfill(A, 'holes');
subplot(1,3,2); imshow(I);
title('Inpainted image');
% Threshold the image
BW = im2bw(I, level);
subplot(1,3,3); imshow(BW);
title('Thresholded Image');
The above code does the three operations that I mentioned, and we see this figure:
Notice that the thresholded image has border pixels that need to be removed so we can concentrate on the circular object. You can use the imclearborder function to remove the border pixels. When we do that:
% Clear off the border pixels and leave only the circular object
BW2 = imclearborder(BW);
figure; imshow(BW2);
... we now get this image:
Unfortunately, there are some noisy pixels, but we can very easily use morphology, specifically the opening operation with a small circular disk structuring element to remove these noisy pixels. Using strel with the appropriate structuring element in addition to imopen should help do the trick:
% Clear out noisy pixels
SE = strel('disk', 3, 0);
out = imopen(BW2, SE);
figure; imshow(out);
We now get:
This mask contains the locations of the circular object we now need to use to crop our original image. The last part is to determine the row and column locations using this mask to locate the top left and bottom right corner of the original image and we thus crop it:
% Find row and column locations of circular object
[row,col] = find(out);
% Find top left and bottom right corners
top_row = min(row);
top_col = min(col);
bottom_row = max(row);
bottom_col = max(col);
% Crop the image
crop = A(top_row:bottom_row, top_col:bottom_col);
% Show the cropped image
figure; imshow(crop);
We now get:
It's not perfect, but it will of course get you started. If you want to copy and paste this in its entirety and run this on your computer, here we are:
figure; % Open up a new figure
% Read in image and convert to grayscale
A = rgb2gray(imread('http://i.stack.imgur.com/vNECg.jpg'));
subplot(2,3,1); imshow(A);
title('Original Image');
% Find the optimum threshold via Otsu
level = graythresh(A);
% Inpaint noisy areas
I = imfill(A, 'holes');
subplot(2,3,2); imshow(I);
title('Inpainted image');
% Threshold the image
BW = im2bw(I, level);
subplot(2,3,3); imshow(BW);
title('Thresholded Image');
% Clear off the border pixels and leave only the circular object
BW2 = imclearborder(BW);
subplot(2,3,4); imshow(BW2);
title('Cleared Border Pixels');
% Clear out noisy pixels
SE = strel('disk', 3, 0);
out = imopen(BW2, SE);
% Show the final mask
subplot(2,3,5); imshow(out);
title('Final Mask');
% Find row and column locations of circular object
[row,col] = find(out);
% Find top left and bottom right corners
top_row = min(row);
top_col = min(col);
bottom_row = max(row);
bottom_col = max(col);
% Crop the image
crop = A(top_row:bottom_row, top_col:bottom_col);
% Show the cropped image
subplot(2,3,6);
imshow(crop);
title('Cropped Image');
... and our final figure is:
You can use bwdist with L_inf distance (aka 'chessboard') to get the axis-aligned distance to the edges of the region, thus concluding the dimensions of the largest bounded box:
bw = imread('http://i.stack.imgur.com/7yCaD.png');
lb = bwlabel(bw);
reg = lb==2; %// pick largest area
d = bwdist(~reg,'chessboard'); %// compute the axis aligned distance from boundary inward
r = max(d(:)); %// find the largest distance to boundary
[cy cx] = find(d==r,1); %// find the location most distant
boundedBox = [cx-r, cy-r, 2*r, 2*r];
And the result is
figure;
imshow(bw,'border','tight');
hold on;
rectangle('Position', boundedBox, 'EdgeColor','r');
Once you have the bounding box, you can use imcrop to crop the original image
imageCrop = imcrop(A, boundedBox);
Alternatively, you can
imageCrop = A(cy + (-r:r-1), cx + (-r:r-1) );

Why does downsample appear as a gray image?

In the implementation of downsampling by a factor of 2 to the image, the downsampled image is gray. What should I do in order to add all of the color components to the downsampling implementation so that it will be a color image?
I = imread('lena.gif','gif');
[j k] = size(I)
x_new = j./2;
y_new = k./2;
x_scale = j./x_new;
y_scale = k./y_new;
M = zeros(x_new,y_new);
for count1 = 1:x_new
for count2 = 1:y_new
M(count1,count2) = I(count1.*x_scale,count2.*y_scale);
end
end
figure,imshow(I);
title('Original Image');
M = uint8(M);
figure,imshow(M);
title('Downsample');
GIF images are what are known as indexed images. This means that what you read in with imread are values that are indices to a colour map. Each index generates a unique colour for you, and that's how GIF images are stored. They choose from a predefined set of colours, and each pixel in the GIF image comes from one of the colours in the colour map.
You first need to convert the image into RGB, and you do that with ind2rgb. However, you need to read in the colour map first with the two-output version of imread. You also will want to convert the images to uint8 as good practice with im2uint8:
[X,map] = imread('lena.gif');
I = im2uint8(ind2rgb(X,map));
What you need to do next is what #NKN suggested. You must apply the algorithm to all channels.
As such, simply make an output matrix that has three channels, and apply the algorithm to each plane independently. If I can make a suggestion, when accessing pixels this way after you downsample, make sure you floor or round the image coordinates so you're not inadvertently specifying locations that aren't defined - things like (13.8, 25.5) for example. Image pixel locations are integer, so you need to make sure the coordinates are integer too.
[X,map] = imread('lena.gif');
I = im2uint8(ind2rgb(X,map));
j = size(I,1); %// Change
k = size(I,2);
x_new = j./2;
y_new = k./2;
x_scale = j./x_new;
y_scale = k./y_new;
M = zeros(x_new,y_new,size(I,3)); %// Change
for jj = 1 : size(I,3) %// Change
for count1 = 1:x_new
for count2 = 1:y_new
M(count1,count2,jj) = I(floor(count1.*x_scale),floor(count2.*y_scale),jj); %// Change
end
end
end
figure,imshow(I);
title('Original Image');
M = uint8(M);
figure,imshow(M);
title('Downsample');
To test this, I'm using the mandrill dataset that's part of MATLAB. It is an indexed image with an associated colour map. These are coincidentally stored in X and map respectfully:
load mandrill;
I = im2uint8(ind2rgb(X,map));
Running the modified code, I get these two figures:
When you read the original image it contains 3 layers, R-G-B (as suggested by #rayryeng:
[X,map] = imread('lena.gif');
I = ind2rgb(X,map);
size(I)
ans =
768 1024 3
You should perform the down-sampling process on all the layers:
The code you provided does not down-sample. A simple downsampling example is as follows:
imshow(I(1:2:end,1:2:end,:))

Image Fusion using stationary wavelet transform (SWT) (MATLAB)

I'm trying to fuse two images using SWT. But I'm getting this error :
The level of decomposition 1
and the size of the image (1,5)
are not compatible.
Suggested size: (2,6)
How to change the size of the image to make it compatible for transform?
Code I've used is :
clc
i=1;
fol=1;
n=0;
for fol=1:5
f='folder';
folder = strcat(f, num2str(fol));
cd(folder)
d= numel(D);
i=(n+1);
Fname1 = strcat(int2str(i),'.bmp');
Fname2 = strcat(int2str(i+1),'.bmp');
im1 = imread(Fname1);
im2 = imread(Fname2);
im1=double(im1);
im2=double(im2);
% image decomposition using discrete stationary wavelet transform
[A1L1,H1L1,V1L1,D1L1] = swt2(im1,1,'sym2');
[A2L1,H2L1,V2L1,D2L1] = swt2(im2,1,'sym2');
% fusion start
AfL1 = 0.5*(A1L1+A2L1);
D = (abs(H1L1)-abs(H2L1))>=0;
HfL1 = D.*H1L1 + (~D).*H2L1;
D = (abs(V1L1)-abs(V2L1))>=0;
VfL1 = D.*V1L1 + (~D).*V2L1;
D = (abs(D1L1)-abs(D2L1))>=0;
DfL1 = D.*D1L1 + (~D).*D2L1;
% fused image
imf = iswt2(AfL1,HfL1,VfL1,DfL1,'sym2');
figure;
imshow(imf,[]);
Iname= strcat(int2str(fol),'.bmp');
imwrite(imf,Iname);
end
To address your first problem, that image is really small. I'm assuming that's an image of size 1 x 5. I would suggest changing your image so that it's larger, or perhaps do an imresize on the image. However, as what Ander said in his comment to you... I wouldn't call a 1 x 5 matrix an image.
To address your second problem, once you finally load in an image, the wavelet transform will most likely give you floating point numbers that are beyond the dynamic range of any sensible floating point precision image. As such, it's good that you normalize the image first, then save it to file.
Therefore, do this right before you save the image:
%// ...
%// Your code...
imshow(imf,[]);
%// Normalize the image - Change
imf = (imf - min(imf(:))) / (max(imf(:)) - min(imf(:)));
%// Your code again
%// Now save
Iname= strcat(int2str(fol),'.bmp');
imwrite(imf,Iname);
The above transformation normalizes an image so that the minimum is 0 and the maximum is 1. Once you do that, it should be visualized properly. FWIW, doing imshow(imf,[]); does this normalization for you and displays that result, but it doesn't modify the image.

Binary Image Matrix

How to find the matrix value from this signature picture?
how to find the matrix value from:
RGB image to Gray Scale
Gray Scale to Binary Image
Binary Image to Inverted Binary Image
Inverted Binary Image with clean border
Inverted Binary Image with clean border to extract bounding box
I already know the code from RGB to extract bounding box:
%// Read in image and convert to binary
%// Also clear the borders
im = imread('http://postimg.org/image/qptg2jgsz/2a2705fb/');
im_bw = imclearborder(im2bw(rgb2gray(im)));
%// Find those non-zero pixel locations
[rows, cols] = find(im_bw);
min_row = min(rows);
max_row = max(rows);
min_col = min(cols);
max_col = max(cols);
%// Now extract the bounding box
bb = im_bw(min_row:max_row, min_col:max_col);
%// Show the image
imshow(bb);
Edit: Actually in your code you already have the binary image... BW stands for Black and white...
Have you tried the basic Matlab example?
BW = im2bw(I, level);
In case you want an automatic choice of threshold level try Otsu's method.
level = graythresh(I)

Resources