Conversion of grayscale to binary Image

when a dataset containing gray scale images are converted to binary images , few images are getting complemented i.e, few images with black as background and few with white as background.

I want all images to be in a uniform way, black background and white foreground.

how to use imcomplement() for selected images in a datasset? or is there anyother way?

i have attached few sample input and their corresponding binary images from the dataset.

Thankyou in advance

Answer 1

[Image Analyst]

There is an option for that in imbinarize to make sure you always get either the brighter thing or the darker thing:

BW = imbinarize(grayImage,'adaptive','ForegroundPolarity','dark','Sensitivity',0.4);

[ANUSHA H P]

Thankyou sir for the response

but when i apply this command, segmentation of lung doesnt happen properly.

i have used the same code given by you for the segmentation.

i have attached the images.

[Image Analyst]

Attach the original gray scale images, not screenshots of binary images, and your program

[yanqi liu]

yes，sir，may be use

clc; clear all; close all;
grayImage = imread('https://ww2.mathworks.cn/matlabcentral/answers/uploaded_files/864875/CHNCXR_0639_1-input.png');
if ndims(grayImage) == 3
    grayImage = rgb2gray(grayImage);
end
BW = ~imbinarize(grayImage,'adaptive','ForegroundPolarity','dark','Sensitivity',0.55);
figure; imshow(BW, []);

[ANUSHA H P]

I have attached the code and grayImage sir.

folder = pwd; % 'E:\project\dataset'
fullFileName = fullfile(folder, 'CHNCXR_0639_1-input.jpg');
rgbImage=imread(fullFileName);
[rows, columns, numberOfColorChannels] = size(rgbImage)
subplot(2, 2, 1);
imshow(rgbImage);
axis('on', 'image')
title('Original RGB image')
% Convert to gray scale.
if numberOfColorChannels == 3
    grayImage = rgb2gray(rgbImage);
else
    % It's already gray scale.
    grayImage = rgbImage; 
end
% Resize.
grayImage = imresize(grayImage,[256,256]);
subplot(2, 2, 2);
imshow(grayImage);
axis('on', 'image')
title('Resized gray scale image')
% Binarize
binaryImage = imbinarize(grayImage,'adaptive','ForegroundPolarity','dark','Sensitivity',0.4);
subplot(2, 2, 3);
imshow(binaryImage);
binaryImage = imclearborder(binaryImage);
binaryImage = bwareafilt(binaryImage,2);
subplot(2, 2, 3);
imshow(binaryImage);
axis('on', 'image')
title('Lungs Only')

[Image Analyst]

% Initialization Steps.
clc;    % Clear the command window.
close all;  % Close all figures (except those of imtool.)
clear;  % Erase all existing variables. Or clearvars if you want.
workspace;  % Make sure the workspace panel is showing.
format long g;
format compact;
fontSize = 16;
folder = pwd; % 'E:\project\dataset'
fullFileName = fullfile(folder, 'CHNCXR_0639_1-input.png');
rgbImage=imread(fullFileName);
[rows, columns, numberOfColorChannels] = size(rgbImage)
subplot(2, 3, 1);
imshow(rgbImage);
axis('on', 'image')
title('Original RGB image', 'FontSize', fontSize)
impixelinfo;
% Convert to gray scale.
if numberOfColorChannels == 3
    grayImage = rgb2gray(rgbImage);
else
    % It's already gray scale.
    grayImage = rgbImage; 
end
subplot(2, 3, 2);
imhist(grayImage);
grid on;
title('Histogram of gray scale image', 'FontSize', fontSize)
% Resize.
grayImage = imresize(grayImage,[256,256]);
subplot(2, 3, 3);
imshow(grayImage);
axis('on', 'image')
title('Resized gray scale image', 'FontSize', fontSize)
% Binarize
% Determine threshold
lowThreshold = 0;
highThreshold = 189;
% https://www.mathworks.com/matlabcentral/fileexchange/29372-thresholding-an-image?s_tid=srchtitle
% [lowThreshold, highThreshold] = threshold(lowThreshold, highThreshold, grayImage);
binaryImage = grayImage >= lowThreshold & grayImage <= highThreshold;
% binaryImage = imbinarize(grayImage,'adaptive','ForegroundPolarity','dark','Sensitivity',0.4);
% binaryImage = imbinarize(grayImage);
subplot(2, 3, 4);
imshow(binaryImage);
title('Binary Image', 'FontSize', fontSize)
binaryImage = imclearborder(binaryImage);
binaryImage = bwareafilt(binaryImage,2);
binaryImage = bwconvhull(binaryImage, 'objects');
subplot(2, 3, 5);
imshow(binaryImage);
axis('on', 'image')
title('Lungs Only', 'FontSize', fontSize)
% Plot the borders of all the blobs in the overlay above the original grayscale image 
% using the coordinates returned by bwboundaries().
% bwboundaries() returns a cell array, where each cell contains the row/column coordinates for an object in the image.
subplot(2, 3, 6);
imshow(grayImage); % Optional : show the original image again.  Or you can leave the binary image showing if you want.
% Here is where we actually get the boundaries for each blob.
boundaries = bwboundaries(binaryImage);
% boundaries is a cell array - one cell for each blob.
% In each cell is an N-by-2 list of coordinates in a (row, column) format.  Note: NOT (x,y).
% Column 1 is rows, or y.    Column 2 is columns, or x.
numberOfBoundaries = size(boundaries, 1); % Count the boundaries so we can use it in our for loop
% Here is where we actually plot the boundaries of each blob in the overlay.
hold on; % Don't let boundaries blow away the displayed image.
for k = 1 : numberOfBoundaries
    thisBoundary = boundaries{k}; % Get boundary for this specific blob.
    x = thisBoundary(:,2); % Column 2 is the columns, which is x.
    y = thisBoundary(:,1); % Column 1 is the rows, which is y.
    plot(x, y, 'r-', 'LineWidth', 2); % Plot boundary in red.
end
hold off;
caption = sprintf('%d Outlines, from bwboundaries()', numberOfBoundaries); 
fontSize = 15;
title(caption, 'FontSize', fontSize); 
axis('on', 'image'); % Make sure image is not artificially stretched because of screen's aspect ratio.

[ANUSHA H P]

thankyou sir

[Image Analyst]

If you want the shape to better hug/follow the binary image, instead of using the convex hull, you could fill the blobs and use activecontour. See attached demo.

[ANUSHA H P]

yes sir, it was of grt help ,thankyou.