MATLAB: Segmentation of dark lines when background is darker a bit.

image processingImage Processing Toolboximage segmentation

Helloo, Can someone suggest me how I can do good segmentation of lines, I want to extract those darker lines. I tried normal thresholding but the background is too dark to give me a good result.

Best Answer

You can use a modification of an algorithm used to find text on varying background. Basically you scan and do a local Otsu filter. Then you scan and find the local Sobel edges, then take the std dev of that and threshold. Then AND to find only blobs that are locally varying. Then do some cleanup by finding only tall and dark blobs that are large enough. Code is attached. There are a lot of parameters in my well commented code that you can vary to achieve different effects. I've already spent way more time on this than I normally do for people, so I'll leave that to you. Good luck.

Related Solutions

MATLAB: Crop dark area and display the face only

Convert to grayscale and then threshold and find the bounding box

clc;    % Clear the command window.
close all;  % Close all figures (except those of imtool.)
imtool close all;  % Close all imtool figures.
clear;  % Erase all existing variables. Or clearvars if you want.
workspace;  % Make sure the workspace panel is showing.
format long g;
format compact;
fontSize = 20;
% Read in the color image.
folder = pwd;
baseFileName = 'm2.bmp';
% Get the full filename, with path prepended.
fullFileName = fullfile(folder, baseFileName);
if ~exist(fullFileName, 'file')
  % Didn't find it there.  Check the search path for it.
  fullFileName = baseFileName; % No path this time.
  if ~exist(fullFileName, 'file')
    % Still didn't find it.  Alert user.
    errorMessage = sprintf('Error: %s does not exist.', fullFileName);
    uiwait(warndlg(errorMessage));
    return;
  end
end
rgbImage = imread(fullFileName);
% Get the dimensions of the image.  numberOfColorBands should be = 3.
[rows, columns, numberOfColorBands] = size(rgbImage);
% Display the original color image.
subplot(2, 3, 1);
imshow(rgbImage, []);
axis on;
title('Original Color Image', 'FontSize', fontSize);
drawnow;
% Enlarge figure to full screen.
set(gcf, 'units','normalized','outerposition',[0 0 1 1]);
% Histogram the red channel, but there is a huge spike at 255 so let's not count those.
subplot(2, 3, 2);
grayImage = rgb2gray(rgbImage);
imshow(grayImage, []);
title('Gray Scale version', 'FontSize', fontSize);
subplot(2, 3, 3);
histogram(grayImage(grayImage<255))
grid on;
title('Histogram of Gray Scale Image', 'FontSize', fontSize);
someThresholdValue = 150;
binaryImage = grayImage > someThresholdValue;
% Take largest blob
binaryImage = bwareafilt(binaryImage, 1);
subplot(2, 3, 4);
imshow(binaryImage);
grid on;
title('Binary Image', 'FontSize', fontSize);
% Label the binary image.
labeledImage = bwlabel(binaryImage);
props = regionprops(labeledImage, 'BoundingBox');
bbox = props.BoundingBox
croppedImageRGB = imcrop(rgbImage, bbox);
subplot(2, 3, 5);
imshow(croppedImageRGB);
grid on;
title('Cropped RGB Image', 'FontSize', fontSize);
% Gray scale version of cropped image
croppedImageGray = imcrop(grayImage, bbox);
subplot(2, 3, 6);
imshow(croppedImageGray);
grid on;
title('Cropped Gray Scale Image', 'FontSize', fontSize);

MATLAB: Remove parts from Image and Fill Parts

Pretty easy. Threshold, fill holes, take the 3 largest.

Solution below. Adapt as needed.

% 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 = 14;
filename = fullfile(pwd, 'image_1.jpg');
grayImage = imread(filename);
if ndims(grayImage) == 3
	% It's really an RGB image, not a gray scale image.  
	% Convert to gray scale
	grayImage = rgb2gray(grayImage);
end
subplot(2, 3, 1);
imshow(grayImage, []);
title('Original Image', 'FontSize', fontSize);
% Threshold
subplot(2, 3, 2);
imhist(grayImage);
grid on;
title('Histogram', 'FontSize', fontSize);
mask = grayImage < 128; % or whatever value works
subplot(2, 3, 3);
imshow(mask, []);
title('Initial Binary Image', 'FontSize', fontSize);
% Fill Holes
mask = imfill(mask, 'holes');
subplot(2, 3, 4);
imshow(mask, []);
title('After holes filled', 'FontSize', fontSize);
% Take 3 largest blobs then invert intensity.
mask = ~bwareafilt(mask, 3);
subplot(2, 3, 5);
imshow(mask, []);
title('Final Image Showing 3 Largest', 'FontSize', fontSize);

Best Answer

Related Solutions

MATLAB: Crop dark area and display the face only

MATLAB: Remove parts from Image and Fill Parts

Related Question