How to separate the object from the background from the image

These are the images sample that I requires to separate the object (in this case it is the letter 'A' ) with its background and store them for further processing so that it will form like this afterwards, which means I need to make the letter such that it could clearly seen the outline and the pixel occupied by it on the image pixels.

Note: it is sign language example.

Hope that someone could guide me what to do next or example code. Thank you,

Answer 1

[Image Analyst]

Try

background = grayImage == 255;
foreground = ~background;

[Tuck Wai Yip]

%create blank image
w = 150;
h = 150;
blankImage= 255*ones(w,h,3,'uint8');
%position of the letter in the empty cell
position_x = (w+1)/2;
position_y = (h+1)/2;
% varying the font size, start from 10 to 16
font_start = 25;
font_end = 31;
num_fontsA = font_start:2:font_end;
% get the number of fonts
numImagesA = length(num_fontsA)
% create a cell array with number of fonts to fill in the image in next step
A = cell(1, numImagesA);
% for loop to create letter 'A' 
% grayscale
% store into the cell array
for i=1:numImagesA
    for font_size = num_fontsA(i)
        img= insertText(blankImage,[position_x position_y],'A','Font','Times New Roman','FontSize',font_size,'TextColor','black','BoxColor','w','BoxOpacity',0,'AnchorPoint','Center');
        grayImage= rgb2gray(img);
        background = grayImage == 255;
        foreground = ~background;

Is these two lines above correct??

%         A{i} = img;
%         A{i}= imnoise(img, 'gaussian',0, 0.01);
        subplot(2,2,i);
        imshow(A{i});
        axis on;
        title("A with font size " + font_size);
%         title("A with font size " + font_size +" with noise 0.01 variance");
    end
end

How should I do to store the background and foreground variable into the grayImage variable?Did I use your code correctly?It is because I could not proceed with next step. Hope you could give me a little more guidance. Thank you. Have a nice day!

[Tuck Wai Yip]

It is because I need to compare the pixels detected by the thresholding algorithm, Sauvola for next step and calculate the (pixel detected by sauvola algorithm)/ (original pixel of A) for the zeta.

[Image Analyst]

I don't know what sauvola is, or means. Same for zeta.

The foreground and background are already saved into those variables. If you want them saved for after the loop, you can save them into a cell array or a 3-D array.

To count the number of "true" pixels in the thresholded images you can use nnz():

numForegroundPixels = nnz(foreground);
numBackgroundPixels = nnz(background);