Target Recognition
in [Matlab]
|
Prev: Convert uint16 to fixed point
Next: structure length
From: ImageAnalyst on 29 Mar 2010 20:04 On Mar 29, 1:47 pm, "Rebecca " <ronumbe...(a)hotmail.com> wrote: > Here's a link to an example image. You can see the orange hexagonal target with a yellow "R" on it. > > <a href = "http://i174.photobucket.com/albums/w101/becca23_photos/633495612991.jpg"> Example Image </a> ------------------------------------------------------------------------------------------ Yes I see it. My color detection example will work just fine on it. Did you try it, like I suggested earlier? If not, why not? Well I did and it works fine. Here is the code. Be sure to join any lines split into two by the newsreader (look for the red lines along the right side of the editor to locate the syntax errors created by line splitting). % Demo macro to very, very simple color detection in RGB color space % by ImageAnalyst function SimpleColorDetection() clc; % Clear the command window. ver % Display their toolboxes in the command window. % Introduce the demo, and ask user if they want to continue or exit. message = sprintf('This demo will illustrate very simple color detection in RGB color space.\nIt requires the Image Processing Toolbox.\nDo you wish to continue?'); reply = questdlg(message, 'Run Demo?', 'OK','Cancel', 'OK'); if strcmpi(reply, 'Cancel') % User canceled so exit. return; end % Check that user has the Image Processing Toolbox installed. versionInfo = ver; % Capture their toolboxes in the variable. hasIPT = false; for k = 1:length(versionInfo) if strcmpi(versionInfo(k).Name, 'Image Processing Toolbox') > 0 hasIPT = true; end end 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 % Continue with the demo. Do some initialization stuff. close all; fontSize = 16; figure; % Maximize the figure. set(gcf, 'Position', get(0, 'ScreenSize')); % Change the current folder to the folder of this m-file. % (The line of code below is from Brett Shoelson of The Mathworks.) if(~isdeployed) cd(fileparts(which(mfilename))); end % Ask user if they want to use a demo image or their own image. message = sprintf('Do you want use a standard demo image,\nOr pick one of your own?'); reply = questdlg(message, 'Which Image?', 'Demo','My Own', 'Demo'); % Open an image. if strcmpi(reply, 'Demo') % Read standard MATLAB demo image. % fullImageFileName = 'peppers.png'; message = sprintf('Which demo image do you want to use?'); selectedImage = questdlg(message, 'Which Demo Image?', 'Onions', 'Peppers', 'Canoe', 'Onions'); if strcmp(selectedImage, 'Onions') fullImageFileName = 'onion.png'; elseif strcmp(selectedImage, 'Peppers') fullImageFileName = 'peppers.png'; else fullImageFileName = 'canoe.tif'; end else % They want to pick their own. % Change default directory to the one containing the standard demo images for the MATLAB Image Processing Toolbox. originalFolder = pwd; folder = 'C:\Program Files\MATLAB\R2009b\toolbox\images\imdemos'; if ~exist(folder, 'dir') folder = pwd; end cd(folder); % Browse for the image file. [baseFileName, folder] = uigetfile('*.*', 'Specify an image file'); fullImageFileName = fullfile(folder, baseFileName); % Set current folder back to the original one. cd(originalFolder); end % Check to see that the image exists. (Mainly to check on the demo images.) if ~exist(fullImageFileName, 'file') message = sprintf('This file does not exist:\n%s', fullImageFileName); uiwait(msgbox(message)); return; end % Read in image into an array. [rgbImage storedColorMap] = imread(fullImageFileName); [rows columns numberOfColorBands] = size(rgbImage); % If it's monochrome (indexed), convert it to color. if numberOfColorBands == 1 rgbImage = ind2rgb(rgbImage, storedColorMap); % rgbImage = cat(3, rgbImage, rgbImage, rgbImage); end % Check to see if it's an 8-bit image needed later for scaling). if strcmpi(class(rgbImage), 'uint8') % Flag for 256 gray levels. eightBit = true; else eightBit = false; end % Display the original image. subplot(3, 4, 1); imshow(rgbImage); drawnow; % Make it display immediately. if numberOfColorBands > 1 title('Original Color Image', 'FontSize', fontSize); else caption = sprintf('Original Monochrome Image\n(converted to color)'); title(caption, 'FontSize', fontSize); end % Extract out the color bands from the original image % into 3 separate 2D arrays, one for each color component. redBand = rgbImage(:, :, 1); greenBand = rgbImage(:, :, 2); blueBand = rgbImage(:, :, 3); % Display them. subplot(3, 4, 2); imshow(redBand); title('Red Band', 'FontSize', fontSize); subplot(3, 4, 3); imshow(greenBand); title('Green Band', 'FontSize', fontSize); subplot(3, 4, 4); imshow(blueBand); title('Blue Band', 'FontSize', fontSize); message = sprintf('These are the individual color bands.\nNow we will compute the image histograms'); uiwait(msgbox(message)); fontSize = 13; % Compute and plot the red histogram. hR = subplot(3, 4, 6); [countsR, grayLevelsR] = imhist(redBand); maxGLValueR = find(countsR > 0, 1, 'last'); maxCountR = max(countsR); bar(countsR, 'r'); grid on; xlabel('Gray Levels'); ylabel('Pixel Count'); title('Histogram of Red Band', 'FontSize', fontSize); % Compute and plot the green histogram. hG = subplot(3, 4, 7); [countsG, grayLevelsG] = imhist(greenBand); maxGLValueG = find(countsG > 0, 1, 'last'); maxCountG = max(countsG); bar(countsG, 'g'); grid on; xlabel('Gray Levels'); ylabel('Pixel Count'); title('Histogram of Green Band', 'FontSize', fontSize); % Compute and plot the blue histogram. hB = subplot(3, 4, 8); [countsB, grayLevelsB] = imhist(blueBand); maxGLValueB = find(countsB > 0, 1, 'last'); maxCountB = max(countsB); bar(countsB, 'b'); grid on; xlabel('Gray Levels'); ylabel('Pixel Count'); title('Histogram of Blue Band', 'FontSize', fontSize); % Set all axes to be the same width and height. % This makes it easier to compare them. maxGL = max([maxGLValueR, maxGLValueG, maxGLValueB]); if eightBit maxGL = 255; end maxCount = max([maxCountR, maxCountG, maxCountB]); axis([hR hG hB], [0 maxGL 0 maxCount]); % Plot all 3 histograms in one plot. subplot(3, 4, 5); plot(grayLevelsR, countsR, 'r', 'LineWidth', 2); grid on; xlabel('Gray Levels'); ylabel('Pixel Count'); hold on; plot(grayLevelsG, countsG, 'g', 'LineWidth', 2); plot(grayLevelsB, countsB, 'b', 'LineWidth', 2); title('Histogram of All Bands', 'FontSize', fontSize); maxGrayLevel = max([maxGLValueR, maxGLValueG, maxGLValueB]); % Trim x-axis to just the max gray level on the bright end. if eightBit xlim([0 255]); else xlim([0 maxGrayLevel]); end % Now select thresholds for the 3 color bands. message = sprintf('Now we will select some color threshold ranges\nand display them over the histograms.'); uiwait(msgbox(message)); % Assign the low and high thresholds for each color band. if strcmp(reply, 'My Own') || strcmp(selectedImage, 'Canoe') > 0 % Take a guess at the values that might work for the user's image. redThresholdLow = graythresh(redBand); redThresholdHigh = 255; greenThresholdLow = 0; greenThresholdHigh = graythresh(greenBand); blueThresholdLow = 0; blueThresholdHigh = graythresh(blueBand); if eightBit redThresholdLow = uint8(redThresholdLow * 255); greenThresholdHigh = uint8(greenThresholdHigh * 255); blueThresholdHigh = uint8(blueThresholdHigh * 255); end else % Use values that I know work for the onions and peppers demo images. redThresholdLow = 85; redThresholdHigh = 255; greenThresholdLow = 0; greenThresholdHigh = 70; blueThresholdLow = 0; blueThresholdHigh = 90; end % Show the thresholds as vertical red bars on the histograms. PlaceThresholdBars(6, redThresholdLow, redThresholdHigh); PlaceThresholdBars(7, greenThresholdLow, greenThresholdHigh); PlaceThresholdBars(8, blueThresholdLow, blueThresholdHigh); message = sprintf('Now we will apply each color band threshold range to the color band.'); uiwait(msgbox(message)); % Now apply each color band's particular thresholds to the color band redMask = (redBand >= redThresholdLow) & (redBand <= redThresholdHigh); greenMask = (greenBand >= greenThresholdLow) & (greenBand <= greenThresholdHigh); blueMask = (blueBand >= blueThresholdLow) & (blueBand <= blueThresholdHigh); % Display the thresholded binary images. fontSize = 16; subplot(3, 4, 10); imshow(redMask, []); title('Is-Red Mask', 'FontSize', fontSize); subplot(3, 4, 11); imshow(greenMask, []); title('Is-Not-Green Mask', 'FontSize', fontSize); subplot(3, 4, 12); imshow(blueMask, []); title('Is-Not-Blue Mask', 'FontSize', fontSize); % Combine the masks to find where all 3 are "true." % Then we will have the mask of only the red parts of the image. redObjectsMask = uint8(redMask & greenMask & blueMask); subplot(3, 4, 9); imshow(redObjectsMask, []); caption = sprintf('Mask of Only\nThe Red Objects'); title(caption, 'FontSize', fontSize); % Tell user that we're going to filter out small objects. smallestAcceptableArea = 100; % Keep areas only if they're bigger than this. message = sprintf('Note the small regions in the image in the lower left.\nNext we will eliminate regions smaller than %d pixels.', smallestAcceptableArea); uiwait(msgbox(message)); % Open up a new figure, since the existing one is full. figure; % Maximize the figure. set(gcf, 'Position', get(0, 'ScreenSize')); % Get rid of small objects. Note: bwareaopen returns a logical. redObjectsMask = uint8(bwareaopen(redObjectsMask, smallestAcceptableArea)); subplot(3, 3, 1); imshow(redObjectsMask, []); fontSize = 13; caption = sprintf('bwareaopen() removed objects\nsmaller than %d pixels', smallestAcceptableArea); title(caption, 'FontSize', fontSize); % Smooth the border using a morphological closing operation, imclose(). structuringElement = strel('disk', 4); redObjectsMask = imclose(redObjectsMask, structuringElement); subplot(3, 3, 2); imshow(redObjectsMask, []); fontSize = 16; title('Border smoothed', 'FontSize', fontSize); % Fill in any holes in the regions, since they are most likely red also. redObjectsMask = uint8(imfill(redObjectsMask, 'holes')); subplot(3, 3, 3); imshow(redObjectsMask, []); title('Regions Filled', 'FontSize', fontSize); message = sprintf('This is the filled, size-filtered mask.\nNow we will apply this mask to the original image'); uiwait(msgbox(message)); % You can only multiply integers if they are of the same type. % (redObjectsMask is a logical array.) % We need to convert the type of redObjectsMask to the same data type as redBand. strDataType = class(redBand); redObjectsMask = eval([strDataType '(redObjectsMask)']); % Use the red object mask to mask out the red-only portions of the rgb image. maskedImageR = redObjectsMask .* redBand; maskedImageG = redObjectsMask .* greenBand; maskedImageB = redObjectsMask .* blueBand; % Show the masked off red image. subplot(3, 3, 4); imshow(maskedImageR); title('Masked Red Image', 'FontSize', fontSize); % Show the masked off green image. subplot(3, 3, 5); imshow(maskedImageG); title('Masked Green Image', 'FontSize', fontSize); % Show the masked off blue image. subplot(3, 3, 6); imshow(maskedImageB); title('Masked Blue Image', 'FontSize', fontSize); % Concatenate the masked color bands to form the rgb image. maskedRGBImage = cat(3, maskedImageR, maskedImageG, maskedImageB); % Show the masked off, original image. subplot(3, 3, 8); imshow(maskedRGBImage); fontSize = 13; caption = sprintf('Masked Original Image\nShowing Only the Red Objects'); title(caption, 'FontSize', fontSize); % Show the original image next to it. subplot(3, 3, 7); imshow(rgbImage); title('The Original Image (Again)', 'FontSize', fontSize); message = sprintf('Done!\n\nThe demo has finished.'); uiwait(msgbox(message)); % ---------- End of main function --------------------------------- %---------------------------------------------------------------------------- % Function to show the low and high threshold bars on the histogram plots. function PlaceThresholdBars(plotNumber, lowThresh, highThresh) % Show the thresholds as vertical red bars on the histograms. subplot(3, 4, plotNumber); hold on; maxYValue = ylim; maxXValue = xlim; hStemLines = stem([lowThresh highThresh], [maxYValue(2) maxYValue(2)], 'r'); children = get(hStemLines, 'children'); set(children(2),'visible', 'off'); % Place a text label on the bar chart showing the threshold. annotationTextL = sprintf('%d', lowThresh); annotationTextH = sprintf('%d', highThresh); % For text(), the x and y need to be of the data class "double" so let's cast both to double. text(double(lowThresh + 5), double(0.85 * maxYValue(2)), annotationTextL, 'FontSize', 10, 'Color', [0 .5 0]); text(double(highThresh + 5), double(0.85 * maxYValue(2)), annotationTextH, 'FontSize', 10, 'Color', [0 .5 0]); % Show the range as arrows. % Can't get it to work, with either gca or gcf. % annotation(gca, 'arrow', [lowThresh/maxXValue(2) highThresh/ maxXValue(2)],[0.7 0.7]); return; % from PlaceThresholdBars
From: Rebecca on 29 Mar 2010 20:57 ImageAnalyst <imageanalyst(a)mailinator.com> wrote in message <7250931a-c091-446e-af13-f1d8472759b7(a)j21g2000yqh.googlegroups.com>... > On Mar 29, 1:47 pm, "Rebecca " <ronumbe...(a)hotmail.com> wrote: > > Here's a link to an example image. You can see the orange hexagonal target with a yellow "R" on it. > > > > <a href = "http://i174.photobucket.com/albums/w101/becca23_photos/633495612991.jpg"> Example Image </a> > ------------------------------------------------------------------------------------------ > > > Yes I see it. My color detection example will work just fine on it. > Did you try it, like I suggested earlier? If not, why not? Well I > did and it works fine. Here is the code. Be sure to join any lines > split into two by the newsreader (look for the red lines along the > right side of the editor to locate the syntax errors created by line > splitting). > > > % Demo macro to very, very simple color detection in RGB color space > % by ImageAnalyst > function SimpleColorDetection() > clc; % Clear the command window. > ver % Display their toolboxes in the command window. > % Introduce the demo, and ask user if they want to continue or exit. > message = sprintf('This demo will illustrate very simple color > detection in RGB color space.\nIt requires the Image Processing > Toolbox.\nDo you wish to continue?'); > reply = questdlg(message, 'Run Demo?', 'OK','Cancel', 'OK'); > if strcmpi(reply, 'Cancel') > % User canceled so exit. > return; > end > > % Check that user has the Image Processing Toolbox installed. > versionInfo = ver; % Capture their toolboxes in the variable. > hasIPT = false; > for k = 1:length(versionInfo) > if strcmpi(versionInfo(k).Name, 'Image Processing Toolbox') > 0 > hasIPT = true; > end > end > 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 > > % Continue with the demo. Do some initialization stuff. > close all; > fontSize = 16; > figure; > % Maximize the figure. > set(gcf, 'Position', get(0, 'ScreenSize')); > > % Change the current folder to the folder of this m-file. > % (The line of code below is from Brett Shoelson of The Mathworks.) > if(~isdeployed) > cd(fileparts(which(mfilename))); > end > > % Ask user if they want to use a demo image or their own image. > message = sprintf('Do you want use a standard demo image,\nOr pick one > of your own?'); > reply = questdlg(message, 'Which Image?', 'Demo','My Own', 'Demo'); > % Open an image. > if strcmpi(reply, 'Demo') > % Read standard MATLAB demo image. > % fullImageFileName = 'peppers.png'; > message = sprintf('Which demo image do you want to use?'); > selectedImage = questdlg(message, 'Which Demo Image?', 'Onions', > 'Peppers', 'Canoe', 'Onions'); > if strcmp(selectedImage, 'Onions') > fullImageFileName = 'onion.png'; > elseif strcmp(selectedImage, 'Peppers') > fullImageFileName = 'peppers.png'; > else > fullImageFileName = 'canoe.tif'; > end > else > % They want to pick their own. > % Change default directory to the one containing the standard demo > images for the MATLAB Image Processing Toolbox. > originalFolder = pwd; > folder = 'C:\Program Files\MATLAB\R2009b\toolbox\images\imdemos'; > if ~exist(folder, 'dir') > folder = pwd; > end > cd(folder); > % Browse for the image file. > [baseFileName, folder] = uigetfile('*.*', 'Specify an image file'); > fullImageFileName = fullfile(folder, baseFileName); > % Set current folder back to the original one. > cd(originalFolder); > end > > % Check to see that the image exists. (Mainly to check on the demo > images.) > if ~exist(fullImageFileName, 'file') > message = sprintf('This file does not exist:\n%s', > fullImageFileName); > uiwait(msgbox(message)); > return; > end > > % Read in image into an array. > [rgbImage storedColorMap] = imread(fullImageFileName); > [rows columns numberOfColorBands] = size(rgbImage); > % If it's monochrome (indexed), convert it to color. > if numberOfColorBands == 1 > rgbImage = ind2rgb(rgbImage, storedColorMap); > % rgbImage = cat(3, rgbImage, rgbImage, rgbImage); > end > % Check to see if it's an 8-bit image needed later for scaling). > if strcmpi(class(rgbImage), 'uint8') > % Flag for 256 gray levels. > eightBit = true; > else > eightBit = false; > end > % Display the original image. > subplot(3, 4, 1); > imshow(rgbImage); > drawnow; % Make it display immediately. > if numberOfColorBands > 1 > title('Original Color Image', 'FontSize', fontSize); > else > caption = sprintf('Original Monochrome Image\n(converted to color)'); > title(caption, 'FontSize', fontSize); > end > > % Extract out the color bands from the original image > % into 3 separate 2D arrays, one for each color component. > redBand = rgbImage(:, :, 1); > greenBand = rgbImage(:, :, 2); > blueBand = rgbImage(:, :, 3); > % Display them. > subplot(3, 4, 2); > imshow(redBand); > title('Red Band', 'FontSize', fontSize); > subplot(3, 4, 3); > imshow(greenBand); > title('Green Band', 'FontSize', fontSize); > subplot(3, 4, 4); > imshow(blueBand); > title('Blue Band', 'FontSize', fontSize); > message = sprintf('These are the individual color bands.\nNow we will > compute the image histograms'); > uiwait(msgbox(message)); > > fontSize = 13; > > % Compute and plot the red histogram. > hR = subplot(3, 4, 6); > [countsR, grayLevelsR] = imhist(redBand); > maxGLValueR = find(countsR > 0, 1, 'last'); > maxCountR = max(countsR); > bar(countsR, 'r'); > grid on; > xlabel('Gray Levels'); > ylabel('Pixel Count'); > title('Histogram of Red Band', 'FontSize', fontSize); > > % Compute and plot the green histogram. > hG = subplot(3, 4, 7); > [countsG, grayLevelsG] = imhist(greenBand); > maxGLValueG = find(countsG > 0, 1, 'last'); > maxCountG = max(countsG); > bar(countsG, 'g'); > grid on; > xlabel('Gray Levels'); > ylabel('Pixel Count'); > title('Histogram of Green Band', 'FontSize', fontSize); > > % Compute and plot the blue histogram. > hB = subplot(3, 4, 8); > [countsB, grayLevelsB] = imhist(blueBand); > maxGLValueB = find(countsB > 0, 1, 'last'); > maxCountB = max(countsB); > bar(countsB, 'b'); > grid on; > xlabel('Gray Levels'); > ylabel('Pixel Count'); > title('Histogram of Blue Band', 'FontSize', fontSize); > > % Set all axes to be the same width and height. > % This makes it easier to compare them. > maxGL = max([maxGLValueR, maxGLValueG, maxGLValueB]); > if eightBit > maxGL = 255; > end > maxCount = max([maxCountR, maxCountG, maxCountB]); > axis([hR hG hB], [0 maxGL 0 maxCount]); > > % Plot all 3 histograms in one plot. > subplot(3, 4, 5); > plot(grayLevelsR, countsR, 'r', 'LineWidth', 2); > grid on; > xlabel('Gray Levels'); > ylabel('Pixel Count'); > hold on; > plot(grayLevelsG, countsG, 'g', 'LineWidth', 2); > plot(grayLevelsB, countsB, 'b', 'LineWidth', 2); > title('Histogram of All Bands', 'FontSize', fontSize); > maxGrayLevel = max([maxGLValueR, maxGLValueG, maxGLValueB]); > % Trim x-axis to just the max gray level on the bright end. > if eightBit > xlim([0 255]); > else > xlim([0 maxGrayLevel]); > end > > % Now select thresholds for the 3 color bands. > message = sprintf('Now we will select some color threshold ranges\nand > display them over the histograms.'); > uiwait(msgbox(message)); > > % Assign the low and high thresholds for each color band. > if strcmp(reply, 'My Own') || strcmp(selectedImage, 'Canoe') > 0 > % Take a guess at the values that might work for the user's image. > redThresholdLow = graythresh(redBand); > redThresholdHigh = 255; > greenThresholdLow = 0; > greenThresholdHigh = graythresh(greenBand); > blueThresholdLow = 0; > blueThresholdHigh = graythresh(blueBand); > if eightBit > redThresholdLow = uint8(redThresholdLow * 255); > greenThresholdHigh = uint8(greenThresholdHigh * 255); > blueThresholdHigh = uint8(blueThresholdHigh * 255); > end > else > % Use values that I know work for the onions and peppers demo images. > redThresholdLow = 85; > redThresholdHigh = 255; > greenThresholdLow = 0; > greenThresholdHigh = 70; > blueThresholdLow = 0; > blueThresholdHigh = 90; > end > > % Show the thresholds as vertical red bars on the histograms. > PlaceThresholdBars(6, redThresholdLow, redThresholdHigh); > PlaceThresholdBars(7, greenThresholdLow, greenThresholdHigh); > PlaceThresholdBars(8, blueThresholdLow, blueThresholdHigh); > > message = sprintf('Now we will apply each color band threshold range > to the color band.'); > uiwait(msgbox(message)); > > % Now apply each color band's particular thresholds to the color band > redMask = (redBand >= redThresholdLow) & (redBand <= > redThresholdHigh); > greenMask = (greenBand >= greenThresholdLow) & (greenBand <= > greenThresholdHigh); > blueMask = (blueBand >= blueThresholdLow) & (blueBand <= > blueThresholdHigh); > > % Display the thresholded binary images. > fontSize = 16; > subplot(3, 4, 10); > imshow(redMask, []); > title('Is-Red Mask', 'FontSize', fontSize); > subplot(3, 4, 11); > imshow(greenMask, []); > title('Is-Not-Green Mask', 'FontSize', fontSize); > subplot(3, 4, 12); > imshow(blueMask, []); > title('Is-Not-Blue Mask', 'FontSize', fontSize); > % Combine the masks to find where all 3 are "true." > % Then we will have the mask of only the red parts of the image. > redObjectsMask = uint8(redMask & greenMask & blueMask); > subplot(3, 4, 9); > imshow(redObjectsMask, []); > caption = sprintf('Mask of Only\nThe Red Objects'); > title(caption, 'FontSize', fontSize); > > % Tell user that we're going to filter out small objects. > smallestAcceptableArea = 100; % Keep areas only if they're bigger than > this. > message = sprintf('Note the small regions in the image in the lower > left.\nNext we will eliminate regions smaller than %d pixels.', > smallestAcceptableArea); > uiwait(msgbox(message)); > > % Open up a new figure, since the existing one is full. > figure; > % Maximize the figure. > set(gcf, 'Position', get(0, 'ScreenSize')); > > % Get rid of small objects. Note: bwareaopen returns a logical. > redObjectsMask = uint8(bwareaopen(redObjectsMask, > smallestAcceptableArea)); > subplot(3, 3, 1); > imshow(redObjectsMask, []); > fontSize = 13; > caption = sprintf('bwareaopen() removed objects\nsmaller than %d > pixels', smallestAcceptableArea); > title(caption, 'FontSize', fontSize); > > % Smooth the border using a morphological closing operation, > imclose(). > structuringElement = strel('disk', 4); > redObjectsMask = imclose(redObjectsMask, structuringElement); > subplot(3, 3, 2); > imshow(redObjectsMask, []); > fontSize = 16; > title('Border smoothed', 'FontSize', fontSize); > > % Fill in any holes in the regions, since they are most likely red > also. > redObjectsMask = uint8(imfill(redObjectsMask, 'holes')); > subplot(3, 3, 3); > imshow(redObjectsMask, []); > title('Regions Filled', 'FontSize', fontSize); > > message = sprintf('This is the filled, size-filtered mask.\nNow we > will apply this mask to the original image'); > uiwait(msgbox(message)); > > % You can only multiply integers if they are of the same type. > % (redObjectsMask is a logical array.) > % We need to convert the type of redObjectsMask to the same data type > as redBand. > strDataType = class(redBand); > redObjectsMask = eval([strDataType '(redObjectsMask)']); > > % Use the red object mask to mask out the red-only portions of the rgb > image. > maskedImageR = redObjectsMask .* redBand; > maskedImageG = redObjectsMask .* greenBand; > maskedImageB = redObjectsMask .* blueBand; > % Show the masked off red image. > subplot(3, 3, 4); > imshow(maskedImageR); > title('Masked Red Image', 'FontSize', fontSize); > % Show the masked off green image. > subplot(3, 3, 5); > imshow(maskedImageG); > title('Masked Green Image', 'FontSize', fontSize); > % Show the masked off blue image. > subplot(3, 3, 6); > imshow(maskedImageB); > title('Masked Blue Image', 'FontSize', fontSize); > % Concatenate the masked color bands to form the rgb image. > maskedRGBImage = cat(3, maskedImageR, maskedImageG, maskedImageB); > % Show the masked off, original image. > subplot(3, 3, 8); > imshow(maskedRGBImage); > fontSize = 13; > caption = sprintf('Masked Original Image\nShowing Only the Red > Objects'); > title(caption, 'FontSize', fontSize); > % Show the original image next to it. > subplot(3, 3, 7); > imshow(rgbImage); > title('The Original Image (Again)', 'FontSize', fontSize); > > message = sprintf('Done!\n\nThe demo has finished.'); > uiwait(msgbox(message)); > % ---------- End of main function --------------------------------- > > > %---------------------------------------------------------------------------- > % Function to show the low and high threshold bars on the histogram > plots. > function PlaceThresholdBars(plotNumber, lowThresh, highThresh) > % Show the thresholds as vertical red bars on the histograms. > subplot(3, 4, plotNumber); > hold on; > maxYValue = ylim; > maxXValue = xlim; > hStemLines = stem([lowThresh highThresh], [maxYValue(2) > maxYValue(2)], 'r'); > children = get(hStemLines, 'children'); > set(children(2),'visible', 'off'); > % Place a text label on the bar chart showing the threshold. > annotationTextL = sprintf('%d', lowThresh); > annotationTextH = sprintf('%d', highThresh); > % For text(), the x and y need to be of the data class "double" so > let's cast both to double. > text(double(lowThresh + 5), double(0.85 * maxYValue(2)), > annotationTextL, 'FontSize', 10, 'Color', [0 .5 0]); > text(double(highThresh + 5), double(0.85 * maxYValue(2)), > annotationTextH, 'FontSize', 10, 'Color', [0 .5 0]); > > % Show the range as arrows. > % Can't get it to work, with either gca or gcf. > % annotation(gca, 'arrow', [lowThresh/maxXValue(2) highThresh/ > maxXValue(2)],[0.7 0.7]); > > return; % from PlaceThresholdBars > Yes, I did run your demo with that photo and it worked excellently. I have a few other example photos, though, that I can't get it to recognize. How can I tweak it to recognize blue or yellow or purple objects? http://i174.photobucket.com/albums/w101/becca23_photos/633495614593.jpg http://i174.photobucket.com/albums/w101/becca23_photos/633495613901.jpg
From: ImageAnalyst on 29 Mar 2010 21:22 You have to tweak the values. You have to figure out what color yellow and blue are. Maybe you could try calling imtool() on them and seeing what their RGB values are and then tweaking this lines: redThresholdLow = 85; redThresholdHigh = 255; greenThresholdLow = 0; greenThresholdHigh = 70; blueThresholdLow = 0; blueThresholdHigh = 90; to have the correct values for whatever color you're after.
From: Rebecca on 30 Mar 2010 18:37
ImageAnalyst <imageanalyst(a)mailinator.com> wrote in message <96902bff-f150-4f36-968d-6e33252b9b11(a)q23g2000yqd.googlegroups.com>... > You have to tweak the values. You have to figure out what color > yellow and blue are. Maybe you could try calling imtool() on them and > seeing what their RGB values are and then tweaking this lines: > redThresholdLow = 85; > redThresholdHigh = 255; > greenThresholdLow = 0; > greenThresholdHigh = 70; > blueThresholdLow = 0; > blueThresholdHigh = 90; > to have the correct values for whatever color you're after. Thanks so much! I think this does exactly what I needed it to do, and I can detect other colors by using the advice you gave. I very much appreciate your help with this subject. |