对于初学者来说，该MATLAB DEMO演示了简单的对象检测（分割、特征提取）、测量和滤波。DEMO的运行需要MATLAB自带的图像处理工具箱（IPT）支持，因为它演示了该工具箱提供的一些函数，并且使用了该工具箱提供的“硬币”演示图像。

DEMO演示的主要内容：

首先从图像中寻找所有对象，然后过滤结果以挑选出特定大小的对象。在这个简单的例子中，我们演示了thresholding、labeling和regionprops函数的用法。

该DEMO在MATLAB R2008b – R2011b上通过测试。完整源码列表如下，也可点击“阅读原文”下载。

%------------------------------------------------------------------------------------------------
% Demo to illustrate simple blob detection, measurement, and filtering.
% Requires the Image Processing Toolbox (IPT) because it demonstates some functions
% supplied by that toolbox, plus it uses the “coins” demo image supplied with that toolbox.
% If you have the IPT (you can check by typing ver on the command line), you should be able to
% run this demo code simply by copying and pasting this code into a new editor window,
% and then clicking the green “run” triangle on the toolbar.
% Running time = 7.5 seconds the first run and 2.5 seconds on subsequent runs.
% A similar Mathworks demo:
% http://www.mathworks.com/products/image/demos.html?file=/products/demos/shipping/images/ipexprops.html
% Code written and posted by ImageAnalyst, July 2009. Updated April 2015 for MATLAB release R2015a
%------------------------------------------------------------------------------------------------
% function BlobsDemo()
% echo on;
% Startup code.
tic; % Start timer.
clc; % Clear command window.
clearvars; % Get rid of variables from prior run of this m-file.
fprintf(‘Running BlobsDemo.m…\n’); % Message sent to command window.
workspace; % Make sure the workspace panel with all the variables is showing.
imtool close all; % Close all imtool figures.
format long g;
format compact;
captionFontSize = 14;

% Check that user has the Image Processing Toolbox installed.
hasIPT = license(‘test’, ‘image_toolbox’);
if ~hasIPT
% User does not have the toolbox installed.
message = sprintf(‘Sorry, but you do not seem to have the Image Processing Toolbox.\nDo you want to try to continue anyway?’);
reply = questdlg(message, ‘Toolbox missing’, ‘Yes’, ‘No’, ‘Yes’);
if strcmpi(reply, ‘No’)
% User said No, so exit.
return;
end
end

% Read in a standard MATLAB demo image of coins (US nickles and dimes, which are 5 cent and 10 cent coins)
baseFileName = ‘coins.png’;
folder = fileparts(which(baseFileName)); % Determine where demo folder is (works with all versions).
fullFileName = fullfile(folder, baseFileName);
if ~exist(fullFileName, ‘file’)
% It doesn’t exist in the current folder.
% Look on the search path.
if ~exist(baseFileName, ‘file’)
% It doesn’t exist on the search path either.
% Alert user that we can’t find the image.
warningMessage = sprintf(‘Error: the input image file\n%s\nwas not found.\nClick OK to exit the demo.’, fullFileName);
uiwait(warndlg(warningMessage));
fprintf(1, ‘Finished running BlobsDemo.m.\n’);
return;
end
% Found it on the search path. Construct the file name.
fullFileName = baseFileName; % Note: don’t prepend the folder.
end
% If we get here, we should have found the image file.
originalImage = imread(fullFileName);
% Check to make sure that it is grayscale, just in case the user substituted their own image.
[rows, columns, numberOfColorChannels] = size(originalImage);
if numberOfColorChannels > 1
promptMessage = sprintf(‘Your image file has %d color channels.\nThis demo was designed for grayscale images.\nDo you want me to convert it to grayscale for you so you can continue?’, numberOfColorChannels);
button = questdlg(promptMessage, ‘Continue’, ‘Convert and Continue’, ‘Cancel’, ‘Convert and Continue’);
if strcmp(button, ‘Cancel’)
fprintf(1, ‘Finished running BlobsDemo.m.\n’);
return;
end
% Do the conversion using standard book formula
originalImage = rgb2gray(originalImage);
end

% Display the grayscale image.
subplot(3, 3, 1);
imshow(originalImage);
% Maximize the figure window.
set(gcf, ‘units’,‘normalized’,‘outerposition’,[0 0 1 1]);
% Force it to display RIGHT NOW (otherwise it might not display until it’s all done, unless you’ve stopped at a breakpoint.)
drawnow;
caption = sprintf(‘Original “coins” image showing\n6 nickels (the larger coins) and 4 dimes (the smaller coins).’);
title(caption, ‘FontSize’, captionFontSize);
axis image; % Make sure image is not artificially stretched because of screen’s aspect ratio.

% Just for fun, let’s get its histogram and display it.
[pixelCount, grayLevels] = imhist(originalImage);
subplot(3, 3, 2);
bar(pixelCount);
title(‘Histogram of original image’, ‘FontSize’, captionFontSize);
xlim([0 grayLevels(end)]); % Scale x axis manually.
grid on;

% Threshold the image to get a binary image (only 0’s and 1’s) of class “logical.”
% Method #1: using im2bw()
% normalizedThresholdValue = 0.4; % In range 0 to 1.
% thresholdValue = normalizedThresholdValue * max(max(originalImage)); % Gray Levels.
% binaryImage = im2bw(originalImage, normalizedThresholdValue); % One way to threshold to binary
% Method #2: using a logical operation.
thresholdValue = 100;
binaryImage = originalImage > thresholdValue; % Bright objects will be chosen if you use >.
% ========== IMPORTANT OPTION ============================================================
% Use < if you want to find dark objects instead of bright objects.
% binaryImage = originalImage < thresholdValue; % Dark objects will be chosen if you use <.

% Do a “hole fill” to get rid of any background pixels or “holes” inside the blobs.
binaryImage = imfill(binaryImage, ‘holes’);

% Show the threshold as a vertical red bar on the histogram.
hold on;
maxYValue = ylim;
line([thresholdValue, thresholdValue], maxYValue, ‘Color’, ‘r’);
% Place a text label on the bar chart showing the threshold.
annotationText = sprintf(‘Thresholded at %d gray levels’, thresholdValue);
% For text(), the x and y need to be of the data class “double” so let’s cast both to double.
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]);

% Display the binary image.
subplot(3, 3, 3);
imshow(binaryImage);
title(‘Binary Image, obtained by thresholding’, ‘FontSize’, captionFontSize);

% Identify individual blobs by seeing which pixels are connected to each other.
% Each group of connected pixels will be given a label, a number, to identify it and distinguish it from the other blobs.
% Do connected components labeling with either bwlabel() or bwconncomp().
labeledImage = bwlabel(binaryImage, 8); % Label each blob so we can make measurements of it
% labeledImage is an integer-valued image where all pixels in the blobs have values of 1, or 2, or 3, or … etc.
subplot(3, 3, 4);
imshow(labeledImage, []); % Show the gray scale image.
title(‘Labeled Image, from bwlabel()’, ‘FontSize’, captionFontSize);

% Let’s assign each blob a different color to visually show the user the distinct blobs.
coloredLabels = label2rgb (labeledImage, ‘hsv’, ‘k’, ‘shuffle’); % pseudo random color labels
% coloredLabels is an RGB image. We could have applied a colormap instead (but only with R2014b and later)
subplot(3, 3, 5);
imshow(coloredLabels);
axis image; % Make sure image is not artificially stretched because of screen’s aspect ratio.
caption = sprintf(‘Pseudo colored labels, from label2rgb().\nBlobs are numbered from top to bottom, then from left to right.’);
title(caption, ‘FontSize’, captionFontSize);

% Get all the blob properties. Can only pass in originalImage in version R2008a and later.
blobMeasurements = regionprops(labeledImage, originalImage, ‘all’);
numberOfBlobs = size(blobMeasurements, 1);

% bwboundaries() returns a cell array, where each cell contains the row/column coordinates for an object in the image.
% Plot the borders of all the coins on the original grayscale image using the coordinates returned by bwboundaries.
subplot(3, 3, 6);
imshow(originalImage);
title(‘Outlines, from bwboundaries()’, ‘FontSize’, captionFontSize);
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;

textFontSize = 14; % Used to control size of “blob number” labels put atop the image.
labelShiftX = -7; % Used to align the labels in the centers of the coins.
blobECD = zeros(1, numberOfBlobs);
% Print header line in the command window.
fprintf(1,‘Blob # Mean Intensity Area Perimeter Centroid Diameter\n’);
% Loop over all blobs printing their measurements to the command window.
for k = 1 : numberOfBlobs % Loop through all blobs.
% Find the mean of each blob. (R2008a has a better way where you can pass the original image
% directly into regionprops. The way below works for all versions including earlier versions.)
thisBlobsPixels = blobMeasurements(k).PixelIdxList; % Get list of pixels in current blob.
meanGL = mean(originalImage(thisBlobsPixels)); % Find mean intensity (in original image!)
meanGL2008a = blobMeasurements(k).MeanIntensity; % Mean again, but only for version >= R2008a

blobArea = blobMeasurements(k).Area;		% Get area.
blobPerimeter = blobMeasurements(k).Perimeter;		% Get perimeter.
blobCentroid = blobMeasurements(k).Centroid;		% Get centroid one at a time
blobECD(k) = sqrt(4 * blobArea / pi);					% Compute ECD - Equivalent Circular Diameter.
fprintf(1,'#%2d %17.1f %11.1f %8.1f %8.1f %8.1f % 8.1f\n', k, meanGL, blobArea, blobPerimeter, blobCentroid, blobECD(k));
% Put the "blob number" labels on the "boundaries" grayscale image.
text(blobCentroid(1) + labelShiftX, blobCentroid(2), num2str(k), 'FontSize', textFontSize, 'FontWeight', 'Bold');

end

% Now, I’ll show you another way to get centroids.
% We can get the centroids of ALL the blobs into 2 arrays,
% one for the centroid x values and one for the centroid y values.
allBlobCentroids = [blobMeasurements.Centroid];
centroidsX = allBlobCentroids(1:2:end-1);
centroidsY = allBlobCentroids(2:2:end);
% Put the labels on the rgb labeled image also.
subplot(3, 3, 5);
for k = 1 : numberOfBlobs % Loop through all blobs.
text(centroidsX(k) + labelShiftX, centroidsY(k), num2str(k), ‘FontSize’, textFontSize, ‘FontWeight’, ‘Bold’);
end

% Now I’ll demonstrate how to select certain blobs based using the ismember() function.
% Let’s say that we wanted to find only those blobs
% with an intensity between 150 and 220 and an area less than 2000 pixels.
% This would give us the three brightest dimes (the smaller coin type).
allBlobIntensities = [blobMeasurements.MeanIntensity];
allBlobAreas = [blobMeasurements.Area];
% Get a list of the blobs that meet our criteria and we need to keep.
% These will be logical indices - lists of true or false depending on whether the feature meets the criteria or not.
% for example [1, 0, 0, 1, 1, 0, 1, …]. Elements 1, 4, 5, 7, … are true, others are false.
allowableIntensityIndexes = (allBlobIntensities > 150) & (allBlobIntensities < 220);
allowableAreaIndexes = allBlobAreas < 2000; % Take the small objects.
% Now let’s get actual indexes, rather than logical indexes, of the features that meet the criteria.
% for example [1, 4, 5, 7, …] to continue using the example from above.
keeperIndexes = find(allowableIntensityIndexes & allowableAreaIndexes);
% Extract only those blobs that meet our criteria, and
% eliminate those blobs that don’t meet our criteria.
% Note how we use ismember() to do this. Result will be an image - the same as labeledImage but with only the blobs listed in keeperIndexes in it.
keeperBlobsImage = ismember(labeledImage, keeperIndexes);
% Re-label with only the keeper blobs kept.
labeledDimeImage = bwlabel(keeperBlobsImage, 8); % Label each blob so we can make measurements of it
% Now we’re done. We have a labeled image of blobs that meet our specified criteria.
subplot(3, 3, 7);
imshow(labeledDimeImage, []);
axis image;
title(’“Keeper” blobs (3 brightest dimes in a re-labeled image)’, ‘FontSize’, captionFontSize);

% Plot the centroids in the original image in the upper left.
% Dimes will have a red cross, nickels will have a blue X.
message = sprintf(‘Now I will plot the centroids over the original image in the upper left.\nPlease look at the upper left image.’);
reply = questdlg(message, ‘Plot Centroids?’, ‘OK’, ‘Cancel’, ‘Cancel’);
% Note: reply will = ‘’ for Upper right X, ‘OK’ for OK, and ‘Cancel’ for Cancel.
if strcmpi(reply, ‘Cancel’)
return;
end
subplot(3, 3, 1);
hold on; % Don’t blow away image.
for k = 1 : numberOfBlobs % Loop through all keeper blobs.
% Identify if blob #k is a dime or nickel.
itsADime = allBlobAreas(k) < 2200; % Dimes are small.
if itsADime
% Plot dimes with a red +.
plot(centroidsX(k), centroidsY(k), ‘r+’, ‘MarkerSize’, 10, ‘LineWidth’, 2);
else
% Plot dimes with a blue x.
plot(centroidsX(k), centroidsY(k), ‘bx’, ‘MarkerSize’, 10, ‘LineWidth’, 2);
end
end

% Now use the keeper blobs as a mask on the original image.
% This will let us display the original image in the regions of the keeper blobs.
maskedImageDime = originalImage; % Simply a copy at first.
maskedImageDime(~keeperBlobsImage) = 0; % Set all non-keeper pixels to zero.
subplot(3, 3, 8);
imshow(maskedImageDime);
axis image;
title(‘Only the 3 brightest dimes from the original image’, ‘FontSize’, captionFontSize);

% Now let’s get the nickels (the larger coin type).
keeperIndexes = find(allBlobAreas > 2000); % Take the larger objects.
% Note how we use ismember to select the blobs that meet our criteria.
nickelBinaryImage = ismember(labeledImage, keeperIndexes);
% Let’s get the nickels from the original grayscale image, with the other non-nickel pixels blackened.
% In other words, we will create a “masked” image.
maskedImageNickel = originalImage; % Simply a copy at first.
maskedImageNickel(~nickelBinaryImage) = 0; % Set all non-nickel pixels to zero.
subplot(3, 3, 9);
imshow(maskedImageNickel, []);
axis image;
title(‘Only the nickels from the original image’, ‘FontSize’, captionFontSize);

elapsedTime = toc;
% Alert user that the demo is done and give them the option to save an image.
message = sprintf(‘Done making measurements of the features.\n\nElapsed time = %.2f seconds.’, elapsedTime);
message = sprintf(’%s\n\nCheck out the figure window for the images.\nCheck out the command window for the numerical results.’, message);
message = sprintf(’%s\n\nDo you want to save the pseudo-colored image?’, message);
reply = questdlg(message, ‘Save image?’, ‘Yes’, ‘No’, ‘No’);
% Note: reply will = ‘’ for Upper right X, ‘Yes’ for Yes, and ‘No’ for No.
if strcmpi(reply, ‘Yes’)
% Ask user for a filename.
FilterSpec = {’.PNG’, 'PNG Images (.png)’; ‘.tif’, 'TIFF images (.tif)’; ‘.’, ‘All Files (.)’};
DialogTitle = ‘Save image file name’;
% Get the default filename. Make sure it’s in the folder where this m-file lives.
% (If they run this file but the cd is another folder then pwd will show that folder, not this one.
thisFile = mfilename(‘fullpath’);
[thisFolder, baseFileName, ext] = fileparts(thisFile);
DefaultName = sprintf(’%s/%s.tif’, thisFolder, baseFileName);
[fileName, specifiedFolder] = uiputfile(FilterSpec, DialogTitle, DefaultName);
if fileName ~= 0
% Parse what they actually specified.
[folder, baseFileName, ext] = fileparts(fileName);
% Create the full filename, making sure it has a tif filename.
fullImageFileName = fullfile(specifiedFolder, [baseFileName ‘.tif’]);
% Save the labeled image as a tif image.
imwrite(uint8(coloredLabels), fullImageFileName);
% Just for fun, read image back into the imtool utility to demonstrate that tool.
tifimage = imread(fullImageFileName);
imtool(tifimage, []);
end
end

message = sprintf(‘Would you like to crop out each coin to individual images?’);
reply = questdlg(message, ‘Extract Individual Images?’, ‘Yes’, ‘No’, ‘Yes’);
% Note: reply will = ‘’ for Upper right X, ‘Yes’ for Yes, and ‘No’ for No.
if strcmpi(reply, ‘Yes’)
figure; % Create a new figure window.
% Maximize the figure window.
set(gcf, ‘Units’,‘Normalized’,‘OuterPosition’,[0 0 1 1]);
for k = 1 : numberOfBlobs % Loop through all blobs.
% Find the bounding box of each blob.
thisBlobsBoundingBox = blobMeasurements(k).BoundingBox; % Get list of pixels in current blob.
% Extract out this coin into it’s own image.
subImage = imcrop(originalImage, thisBlobsBoundingBox);
% Determine if it’s a dime (small) or a nickel (large coin).
if blobMeasurements(k).Area > 2200
coinType = ‘nickel’;
else
coinType = ‘dime’;
end
% Display the image with informative caption.
subplot(3, 4, k);
imshow(subImage);
caption = sprintf(‘Coin #%d is a %s.\nDiameter = %.1f pixels\nArea = %d pixels’, …
k, coinType, blobECD(k), blobMeasurements(k).Area);
title(caption, ‘FontSize’, textFontSize);
end

% Display the MATLAB "peaks" logo.
logoFig = subplot(3, 4, 11:12);
caption = sprintf('A MATLAB Tutorial by ImageAnalyst');
text(0.5,1.15, caption, 'Color','r', 'FontSize', 18, 'FontWeight','b', 'HorizontalAlignment', 'Center') ;
positionOfLowerRightPlot = get(logoFig, 'position');
L = 40*membrane(1,25);
logoax = axes('CameraPosition', [-193.4013 -265.1546  220.4819],...
	'CameraTarget',[26 26 10], ...
	'CameraUpVector',[0 0 1], ...
	'CameraViewAngle',9.5, ...
	'DataAspectRatio', [1 1 .9],...
	'Position', positionOfLowerRightPlot, ...
	'Visible','off', ...
	'XLim',[1 51], ...
	'YLim',[1 51], ...
	'ZLim',[-13 40], ...
	'parent',gcf);
s = surface(L, ...
	'EdgeColor','none', ...
	'FaceColor',[0.9 0.2 0.2], ...
	'FaceLighting','phong', ...
	'AmbientStrength',0.3, ...
	'DiffuseStrength',0.6, ... 
	'Clipping','off',...
	'BackFaceLighting','lit', ...
	'SpecularStrength',1, ...
	'SpecularColorReflectance',1, ...
	'SpecularExponent',7, ...
	'Tag','TheMathWorksLogo', ...
	'parent',logoax);
l1 = light('Position',[40 100 20], ...
	'Style','local', ...
	'Color',[0 0.8 0.8], ...
	'parent',logoax);
l2 = light('Position',[.5 -1 .4], ...
	'Color',[0.8 0.8 0], ...
	'parent',logoax);

end

下载DEMO地址：

http://page2.dfpan.com/fs/dlcje22112919651a82/

更多精彩文章请关注微信号：