How to find the gait energy image(GEI) in matlab from a sequence of gait images saved in a folder?

this is the gait sequence attached here

[Walter Roberson]

http://matlab.wikia.com/wiki/FAQ#How_can_I_process_a_sequence_of_files.3F

[ankit sharma]

I read somewhere that The grey-level GEI can be created by averaging the silhouettes of the sequence. It means it converts whole gait sequence into a grayscale image by averaging the gait images. But I don't know how to write the code for this. Please help.

[Walter Roberson]

Those images appear to already be grayscale to me. However, on the chance they are not, you could use rgb2gray() on the image.

Put all the images into a 3D array with the third dimension being the image number. Then take mean(The3DArray, 3) to take the mean between the images. Note that the result will be floating point not uint8 so you might want to uint8() the result if you plan to display it.

[ankit sharma]

No.. you are not getting me. Actually let's say i have 10 images in a folder, now i have to convert these images to a single image by averaging the images so that it have features of all 10 images. this is what we call gait energy image. And yeah..Thank you for replying sir

Answer 1

[Gautam]

Hello Ankit

An easy way to accomplish this task is to read all the images you have in the folder and append them into an array and then take the average along the 3rd dimension.

Assuming that all the images are of the same dimension, here’s the code that demonstrates this:

% Reading the images into an array 
folderPath = 'path/to/your/folder'; 
imageFiles = dir(fullfile(folderPath, '*.png')); 
imageArray = []; 

for k = 1:length(imageFiles) 
    imagePath = fullfile(folderPath, imageFiles(k).name); 
    img = imread(imagePath); 
    
    % Convert the image to grayscale if it's RGB 
    if size(img, 3) == 3 
        img = rgb2gray(img); 
    end 
    
    % Append the image to the array 
    if isempty(imageArray) 
        imageArray = img; 
    else 
        imageArray = cat(3, imageArray, img); 
    end 
end 

% Calculating the average image along the third dimension 

averageImage = mean(imageArray, 3); 
imshow(uint8(averageImage)); 

If your images are not of the same size, you can resize them using the “imresize” function

Here are some useful documents that you can refer to:

cat: https://www.mathworks.com/help/matlab/ref/double.cat.html

imresize: https://www.mathworks.com/help/matlab/ref/imresize.html

Answer 2

[Image Analyst]

See attached demo for averaging together all the images in a folder. It will probably work for grayscale images too.