theta = 0 : 0.01 : 2*pi;radius = 35;I = imread('Image1.jpg');NoseDetect = vision.CascadeObjectDetector('Nose','MergeThreshold',30);imshow(I);hold onnbox = step(NoseDetect, I); nx = nbox(1) + nbox(3)/2; ny = nbox(2) + nbox(4)/2; final_x = nx - 120;final_y = ny - 20;X = radius * cos(theta) + final_x;Y = radius * sin(theta) + final_y;plot(X, Y, 'b-', 'LineWidth', 1);MATLAB: How do i change the skin color in the plotted circle using HSV color space
hsv color spaceImage Processing Toolbox
Related Solutions
Try this. I drew the nose up higher so you can see the difference. Adjust the blur window size to soften the rosy disk.
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 = 25;%===============================================================================
% Get the name of the image the user wants to use.
baseFileName = 'capture.png';% Get the full filename, with path prepended.
folder = pwdfullFileName = fullfile(folder, baseFileName);% Check if file exists.
if ~exist(fullFileName, 'file') % The file doesn't exist -- didn't find it there in that folder.
% Check the entire search path (other folders) for the file by stripping off the folder.
fullFileNameOnSearchPath = baseFileName; % No path this time.
if ~exist(fullFileNameOnSearchPath, 'file') % Still didn't find it. Alert user.
errorMessage = sprintf('Error: %s does not exist in the search path folders.', fullFileName); uiwait(warndlg(errorMessage)); return; endend%===============================================================================% Read in demo image.
rgbImage = imread(fullFileName);% Get the dimensions of the image.
[rows, columns, numberOfColorChannels] = size(rgbImage);% Display the original image.
% subplot(2, 2, 1);
imshow(rgbImage, []);axis on;caption = sprintf('Original Color Image, %s', baseFileName);title(caption, 'FontSize', fontSize, 'Interpreter', 'None');hp = impixelinfo();% Set up figure properties:
% Enlarge figure to full screen.
set(gcf, 'Units', 'Normalized', 'OuterPosition', [0 0.05 1 0.95]);% Get rid of tool bar and pulldown menus that are along top of figure.
% set(gcf, 'Toolbar', 'none', 'Menu', 'none');
% Give a name to the title bar.
set(gcf, 'Name', 'Demo by ImageAnalyst', 'NumberTitle', 'Off')drawnow;hp = impixelinfo(); % Set up status line to see values when you mouse over the image.
% Extract the individual red, green, and blue color channels.
redChannel = rgbImage(:, :, 1);% greenChannel = rgbImage(:, :, 2);
% blueChannel = rgbImage(:, :, 3);
% Let user draw a box around the nose.
uiwait(helpdlg('Locate the nose. Double-click inside it to accept it'));hRect = imrect();noseBox = wait(hRect);% Draw the image again.
subplot(2, 2, 1);imshow(rgbImage);title(caption, 'FontSize', fontSize, 'Interpreter', 'None');hold on;rectangle('Position', noseBox, 'EdgeColor', 'b');axis on;% Convert from RGB color space to HSV color space.
hsvImage = rgb2hsv(rgbImage);hueImage = hsvImage(:,:,1);satImage = hsvImage(:,:,2);valueImage = hsvImage(:,:,3);subplot(2, 2, 2);imshow(hsvImage);title('HSV Image, displayed in RGB', 'FontSize', fontSize, 'Interpreter', 'None');hold onhold on;rectangle('Position', noseBox, 'EdgeColor', 'r');axis on;impixelinfo(); % Display status line when user mouses around over image.
%=========================================================
% Create a mask of two circles.
% Define center of circle to the right of the nose.
nx = noseBox(1) + noseBox(3)/2; ny = noseBox(2) + noseBox(4)/2; final_x = nx - 145;final_y = ny - 25;% Make a circular mask on the left side of the image (right side of her face).
theta = 0 : 0.01 : 2*pi;radius = 45;X = radius * cos(theta) + final_x;Y = radius * sin(theta) + final_y;plot(X, Y, 'b-', 'LineWidth', 1);leftMask = poly2mask(X, Y, rows, columns);% Make a circular mask on the right side of the image (left side of her face).
final_x = nx + 145;theta = 0 : 0.01 : 2*pi;X2 = radius * cos(theta) + final_x;plot(X2, Y, 'b-', 'LineWidth', 1);rightMask = poly2mask(X2, Y, rows, columns);% Make a mask with both of the circles.
mask = leftMask | rightMask;% Blur the mask to soften the edges.
blurWindowWidth = 21;se = strel('disk', blurWindowWidth, 0); % Big circle.
kernel = se.Neighborhood;kernel = kernel / sum(kernel(:)); % Normalize.
blurredMask = conv2(double(mask), ones(blurWindowWidth)/blurWindowWidth^2, 'same');% Find the non-zero areas of the blurred mask.
mask = blurredMask > 0;subplot(2, 2, 3);imshow(blurredMask);title('Mask', 'FontSize', fontSize, 'Interpreter', 'None');hold onaxis on;% Alter the hue, saturation, and value.
% Desired hue = 0.25.
hueImage(mask) = hueImage(mask) .* (1 - blurredMask(mask));satImage = satImage + 0.01 * blurredMask;valueImage = valueImage + 0.01 * 5 * blurredMask;% Clip to valid range of 0-1.
hueImage(hueImage>1)=1; hueImage(hueImage<0)=0;satImage(satImage>1)=1; satImage(satImage<0)=0;valueImage(valueImage>1)=1; valueImage(valueImage<0)=0;% Put back altered images into hsvImage so we can convert back to RGB.
hsvImage = cat(3, hueImage, satImage, valueImage);% Convert back to RGB color space.
newRGBImage = hsv2rgb(hsvImage);subplot(2, 2, 4);imshow(newRGBImage);title('New Image', 'FontSize', fontSize, 'Interpreter', 'None');hold on;rectangle('Position', noseBox, 'EdgeColor', 'b');% Set up figure properties:% Enlarge figure to full screen.set(gcf, 'Units', 'Normalized', 'OuterPosition', [0 0.05 1 0.95]);% Get rid of tool bar and pulldown menus that are along top of figure.% set(gcf, 'Toolbar', 'none', 'Menu', 'none');% Give a name to the title bar.set(gcf, 'Name', 'Demo by ImageAnalyst', 'NumberTitle', 'Off')% Bring up the new image full screen alone.
figure;imshow(newRGBImage);title('New Image', 'FontSize', fontSize, 'Interpreter', 'None');hold on;rectangle('Position', noseBox, 'EdgeColor', 'b');% Enlarge figure to full screen.set(gcf, 'Units', 'Normalized', 'OuterPosition', [0 0.05 1 0.95]);
Get a mask1 and mask2 and or them together.
mask = mask1 | mask2;Related Question
- Draw pixels within threshold interval
- How to correction hue values of image
- Show a ROI over the original image
- Increase RGB image saturation.
- How to separate the whole lip image into upper and lower part using code
- Extracting black pixels from a specific region of an image and overlaying it on another image
Best Answer