Which variable stores contour image ?

close all; 
clear all;
clc;

%Read the image, and capture the dimensions
img_orig = imread('C:\Users\Explorer\Documents\MATLAB\ASL_signs\A.jpg');

% % Create axes control.

% handleToAxes = axes();

% % Get the handle to the image in the axes.

% hImage = image(zeros(480,640,'uint8'));

% % Reset image magnification. Required if you ever displayed an image

% % in the axes that was not the same size as your webcam image.

% hold off;

% axis auto;

% axis on;

% % Enlarge figure to full screen.

% set(gcf, 'Units', 'Normalized', 'OuterPosition', [0 0 1 1]);

% annotation('textbox', [.2 .7 .3 .1],...

%            'String', 'Press Space Bar after placing your Hand in Bounding Box');

% % Turn on the live video.

% videoObject = videoinput('winvideo');

% preview(videoObject, hImage);

% hold on

% thisBB = [150 150 350 400]

% rect= rectangle('Position', [thisBB(1),thisBB(2),thisBB(3),thisBB(4)], 
'EdgeColor','g','LineWidth',2 )

% pause

% snap=getsnapshot(videoObject);
% 
% stoppreview(videoObject)

% close all;
% 
% cropped=imcrop(snap, thisBB)
% imshow(cropped)
% 
% 
% img_orig=cropped;

height = size(img_orig,1);

width = size(img_orig,2);

%Initialize the output images

out = img_orig;

bin = zeros(height,width);

%Convert the image from RGB to YCbCr

img_ycbcr = rgb2ycbcr(img_orig);

Cb = img_ycbcr(:,:,2);

Cr = img_ycbcr(:,:,3);

%Detect Skin

[r,c,v] = find(Cb>=77 & Cb<=127 & Cr>=133 & Cr<=173);

numind = size(r,1);

%Mark Skin Pixels

for i=1:numind

      out(r(i),c(i),:) = [0 0 255];

      bin(r(i),c(i)) = 1;

end

imshow(img_orig);

figure; imshow(out);

figure; imshow(bin);

%%Erode noise%%

imerode = imerode(bin, strel('square', 3));

figure,imshow(imerode);

%%Fill in holes to get fully connected skin regions%%

I = imfill(imerode, 'holes');

figure,imshow(I);
% imfill=~imfill;
% figure,imshow(imfill);
% 
% Active Contour by chan-vase

m = zeros(size(I,1),size(I,2));

m(50:200,50:200) = 1;

seg = chenvese(I,m,1000,0.2,'chan'); % ability on gray image

% Built-in Mask

seg = chenvese(I,'medium',3000,0.02,'chan'); % ability on gray image
%-- End

Answer 1

[Image Analyst]

First of all you can extract the biggest blob to get just the hand. I'm attaching a demo to help you with that.

Next, you can then use bwboundaries() if you want all the coordinates of the hand outer perimeter exactly, or you can use activecontour, a built-in function, instead of that file exchange submission. I have a demo for that (on my other computer), if you're interested.

If you want to build up an image from the coordinates given to you by bwboundaries you can easily do that with a for loop:

contourImage = false(size(bin));
for k = 1 : length(xCoordinates)
  row = int32(yCoordinates(k));
  column = int32(xCoordinates(k));
  contourImage(row, column) = true;
end

Answer 2

[Walter Roberson]

None of the code you show produces that plot. The plot is likely put up within the showphi() routine that you did not provide source for. The key inputs to that routine appear to be I and phi0 within the chenverse routine, provided that the 'chan' or 'vector' options are given to it (you provide 'chan'). The phi0 variable is then returned from chenvese, where it becomes your variable "seg"

[Explorer]

Okay, I am attaching its source code.

I have download it from

http://www.mathworks.com/matlabcentral/fileexchange/23445-chan-vese-active-contours-without-edges/all_files

[Walter Roberson]

There is no variable in the code that stores the image you have circled. The image you have circled is made by displaying the image, then "hold on", then using contour() of the value returned as "seg" from chenverse, using [0 0] as the contour level set. The same contour is drawn twice with two different colors and two different line widths - red in linewidth 4, green in linewidth 1.3.

[Explorer]

Thank you for answering Walter Roberson.

You answer is also accepted.