Crack detection on concrete

Hi, i have problem in measuring the length and width the crack image. i have follow the code but it only measure straight line (endpoint). I want the measurement by following the crack pattern. Please help me on this.

      %load image
      path=imgetfile();
      originalImage1=imread(path);
      imshow(originalImage1);

      %image to grayscale
      originalImage = rgb2gray(originalImage1);
      figure
      imshow(originalImage);

      %treshold 
      thresholdValue = 100;
      binaryImage = originalImage > thresholdValue;
      binaryImage = imfill(binaryImage, 'holes');
      hold on;
      % maxYValue = ylim;
      % line([thresholdValue, thresholdValue], maxYValue, 'Color', 'r');
      % annotationText = sprintf('Thresholded at %d gray levels', thresholdValue);
      % text(double(thresholdValue + 5), double(0.5 * maxYValue(2)), annotationText, 'FontSize', 10, 'Color', [0 .5 0]);
      % text(double(thresholdValue - 70), double(0.94 * maxYValue(2)), 'Background', 'FontSize', 10, 'Color', [0 0 .5]);
      % text(double(thresholdValue + 50), double(0.94 * maxYValue(2)), 'Foreground', 'FontSize', 10, 'Color', [0 0 .5]);
      figure
      imshow(binaryImage);

      % bw = bwareaopen(binaryImage,100,8);
      bw= bwareaopen(binaryImage, round(0.1*numel(binaryImage)));
      figure
      imshow(bw)

      g=bwmorph(bw,'clean');
      figure
      imshow(g);

      % %labeled image (on hold)
      labeledImage = bwlabel(g,4); 
      figure
      imshow(labeledImage, []);

      %colored label image
      coloredLabels = label2rgb (labeledImage, 'hsv', 'k', 'shuffle');
      figure
      imshow(coloredLabels);
      axis image;

      %blobmeasurement
      blobMeasurements = regionprops(labeledImage, originalImage, 'all');
      numberOfBlobs = size(blobMeasurements, 1);
      figure
      imshow(originalImage);

      axis image; % Make sure image is not artificially stretched because of screen's aspect ratio.
      hold on;
      boundaries = bwboundaries(binaryImage);
      numberOfBoundaries = size(boundaries, 1);
      for k = 1 : numberOfBoundaries
        thisBoundary = boundaries{k};
        plot(thisBoundary(:,2), thisBoundary(:,1), 'g', 'LineWidth', 2);
      end
      hold off;

      % Measure the area
      measurements = regionprops(labeledImage, 'Area');

      boundaries = bwboundaries(binaryImage);
      numberOfBoundaries = size(boundaries, 1);
      for blobIndex = 1 : numberOfBoundaries
        thisBoundary = boundaries{blobIndex};
        x = thisBoundary(:, 2); % x = columns.
        y = thisBoundary(:, 1); % y = rows.
        
        % Find which two bounary points are farthest from each other.
        maxDistance = -inf;
        for k = 1 : length(x)
          distances = sqrt( (x(k) - x) .^ 2 + (y(k) - y) .^ 2 );
          [thisMaxDistance, indexOfMaxDistance] = max(distances);
          if thisMaxDistance > maxDistance
            maxDistance = thisMaxDistance;
            index1 = k;
            index2 = indexOfMaxDistance;
          end
          end

      % Find the midpoint of the line.
        xMidPoint = mean([x(index1), x(index2)]);
        yMidPoint = mean([y(index1), y(index2)]);
        longSlope = (y(index1) - y(index2)) / (x(index1) - x(index2))
        perpendicularSlope = -1/longSlope
        % Use point slope formula (y-ym) = slope * (x - xm) to get points
        y1 = perpendicularSlope * (1 - xMidPoint) + yMidPoint;
        y2 = perpendicularSlope * (columns - xMidPoint) + yMidPoint;
        
        % Get the profile perpendicular to the midpoint so we can find out when if first enters and last leaves the object.
        [cx,cy,c] = improfile(binaryImage,[1, columns], [y1, y2], 1000);
        % Get rid of NAN's that occur when the line's endpoints go above or below the image.
        c(isnan(c)) = 0;
        firstIndex = find(c, 1, 'first');
        lastIndex = find(c, 1, 'last');
        % Compute the distance of that perpendicular width.
        perpendicularWidth = sqrt( (cx(firstIndex) - cx(lastIndex)) .^ 2 + (cy(firstIndex) - cy(lastIndex)) .^ 2 );
        % Get the average perpendicular width.  This will approximately be the area divided by the longest length.
        averageWidth = measurements(blobIndex).Area / maxDistance;
        
        % Plot the boundaries, line, and midpoints over the two images.
        % Plot the boundary over the gray scale image
        subplot(2, 2, 3);
        plot(x, y, 'y-', 'LineWidth', 3);
        % For this blob, put a line between the points farthest away from each other.
        line([x(index1), x(index2)], [y(index1), y(index2)], 'Color', 'r', 'LineWidth', 3);
        plot(xMidPoint, yMidPoint, 'r*', 'MarkerSize', 15, 'LineWidth', 2);
        % Plot perpendicular line.  Make it green across the whole image but magenta inside the blob.
        line([1, columns], [y1, y2], 'Color', 'g', 'LineWidth', 3);  
        line([cx(firstIndex), cx(lastIndex)], [cy(firstIndex), cy(lastIndex)], 'Color', 'm', 'LineWidth', 3);
        
        % Plot the boundary over the binary image
        subplot(2, 2, 4);
        plot(x, y, 'y-', 'LineWidth', 3);
        % For this blob, put a line between the points farthest away from each other.
        line([x(index1), x(index2)], [y(index1), y(index2)], 'Color', 'r', 'LineWidth', 3);
        plot(xMidPoint, yMidPoint, 'r*', 'MarkerSize', 15, 'LineWidth', 2);
        % Plot perpendicular line.  Make it green across the whole image but magenta inside the blob.
        line([1, columns], [y1, y2], 'Color', 'g', 'LineWidth', 3);  
        line([cx(firstIndex), cx(lastIndex)], [cy(firstIndex), cy(lastIndex)], 'Color', 'm', 'LineWidth', 3);
        
        message = sprintf('The longest line is red.\nPerpendicular to that, at the midpoint, is green.\nMax distance for blob #%d = %.2f\nPerpendicular distance at midpoint = %.2f\nAverage perpendicular width = %.2f (approximately\nArea = %d', ...
          blobIndex, maxDistance, perpendicularWidth, averageWidth, measurements(blobIndex).Area);
        fprintf('%s\n', message);
        uiwait(helpdlg(message));
      end
      hold off;

[KAMOOSH BABA SHAIK]

% Use point slope formula (y-ym) = slope * (x - xm) to get points

y1 = perpendicularSlope * (1 - xMidPoint) + yMidPoint;

y2 = perpendicularSlope * (columns - xMidPoint) + yMidPoint;

in y2 what i can replace to get the answer

in matlab shows like this,

Unrecognized function or variable 'columns'.

Error in lengthwidth (line 90)

y2 = perpendicularSlope * (columns - xMidPoint) + yMidPoint;

Answer 1

[Walter Roberson]

Skeletonize and then bwdistgeodesic

[Fairuz Husna]

can you show how can i use bwdistgeodesic in the code above. i'm new with matlab.

Answer 2

[Preetham Manjunatha]

Here is the MATLAB Crack segmentation and Crack width, length and area estimation codes to calculate/estimate the crack area, width and length. In addition, this package assumes the crack is segmented either using morphological method or multiscale gradient-based or deep learning semantic segmentation methods. This package estimates the crack area, width and length (pixel scale can be provided to estimate these physical quantities). Lastly, the semantic segmentation and object detection metrics for the cracks can be found using Cracks binary class bounding box and segmentation metrics package.