How do I export image features matrix data to Excel for multiple images in the same folder?

I have 100 image files which I need to process (Images are in the same folder). The idea is to take one image, perform pre-processing (noise removal, binarization etc.) followed by features extraction.I've used Wavelets (db1) to extract approximation & directional coefficients (horizontal, vertical and diagonal)-4 features per image.I need to store this features matrix in Excel format.How do I automate the process for 100 image files, so that I get an Excel sheet containing 100x4 entries?

if true
  % clc;
%Code begins from here
clc;
clear all;
close all;
%Load current directory
myFolder = 'E:\BE Project\Devnagiri Character Recognition\test_images\trial';
if ~isdir(myFolder)
errorMessage = sprintf('Error: The following folder does not exist:\n%s', myFolder);
uiwait(warndlg(errorMessage));
return;
end
filePattern = fullfile(myFolder, '*.jpg');
jpegFiles = dir(filePattern);
for k = 1:length(jpegFiles)
baseFileName = jpegFiles(k).name;
fullFileName = fullfile(myFolder, baseFileName);
fprintf(1, 'Now reading %s\n', fullFileName);
imageArray = imread(fullFileName);
%imshow(imageArray);  % Display image.
%drawnow; % Force display to update immediately.
end
a=imageArray;
%Scale to 512x512 since images are of higher resolution
a=imresize(a, [512 512]);
%RGB to gray
if size(a,3)==3 
  b=rgb2gray(a);
end
figure;
imshow(a);
title('Original Image')
%Noise removal by median filter
f=medfilt2(b);
figure;
imshow(f);
title('Noise removal by median filter')
%Determine threshold by Otsu's method
th=graythresh(f);
g=im2bw(f,th);
figure;
imshow(g);
title('Binarized Image (Otsu Method)')
%Resize image for Wavelet Transformation
g=imresize(g, [128 128]);
figure;
imshow(g);
title('Resized Image')
%Find wavelet coefficients using 2D Wavelet Transform
[cA,cH,cV,cD]=dwt2(g,'db1');
disp('---WAVELET FEATURES---');
%Calculate max value for approximation coefficient
disp('Approximation Coefficient (Max Value) :');
ca_max=max(mean(double(cA)));
disp((ca_max));
%Calculate max value for horizontal coefficient
disp('Horizontal Coefficient (Max Value) :');
ch_max=max(mean(double(cH)));
disp((ch_max));
%Calculate max value for vertical coefficient
disp('Vertical Coefficient (Max Value) :');
cv_max=max(mean(double(cV)));
disp((cv_max));
%Calculate max value for diagonal coefficient
disp('Diagonal Coefficient (Max Value) :');
cd_max=max(mean(double(cD)));
disp(mean(cd_max));
%Obtain features in a matrix form
ft=cat(2,ca_max,ch_max,cv_max,cd_max);
%Export features matrix to Excel sheet
xlswrite('testdata.xlsx',ft);

end

[MARIA MALAKOPOULOU]

hello ! Can i ask you something ? Why you take the max value for all the coefficients?

Thanks in advance!

Answer 1

[Image Analyst]

Something like this:

numberOfResults = 42; % Whatever it is for a single image
numberOfImages = length(filenames); % Whatever...
allResults = zeros(numberOfImages, numberOfResults);
for k = 1 : numberOfImages
  % Read in image into variable called thisImage.
  % Analyze the image with function AnalyzeSingleImage and get results.
  thisImagesResults = AnalyzeSingleImage(thisImage);
  % Store results in allResults:
  allResults(k, :) = thisImagesResults;
end
xlswrite(excelFullFileName, allResults);

[Adwait]

Yes! It works. Thank you!

[Roopini N]

Hi. Can you please explain how to save the features of 100 images in excel sheet?

[Image Analyst]

That's what my answer does. Just set numberOfImages equal to 100, and write your custom function AnalyzeSingleImage() to compute the features that you want. Obviously I don't know what particular features you want - only you know that.

[Krishna Pavan]

Getting error at the line AnalyzeSingleImage. Its showing that the function or varaible is undefined

[Image Analyst]

Yes, of course you have to define it. Did you? You have to write it, not me. I have no idea what you want to do with your image. You can start your own question attaching your code and an image or two after you read this link.

[Devashish Tiwari]

I am asking, If I have particles in a single image, and there position i tracked. I saved an excel sheet ofr one image. But I have 100 different images, and want to save excel files for each image through single code? , AND ALSO TO COMBINE ALL THE CSV FILES AND SAVE IT, HOW TO DO SO?

[Image Analyst]

@Devashish Tiwari how are you tracking with a single image? Usually you have multiple images, either still images in separate files on disk, or all together in a video file.

If you have multiple videos you can make a function called "ProcessSingleVideo" and in there read all the frames for one video, find the particles and save their positions to a workbook.

I don't know why you'd want a new workbook for every still image or every frame.

[Devashish Tiwari]

Yeah Exactly sir, I have multiple images to do so. But, I actually wanted to know, from those multiple images, how do I call them, and how to save the tracked particles in each image. Also, How to save the excel sheets of each image?

But, to solve this problem, I needed the work of each image and then the for loop, so I started doing so.

[Image Analyst]

@Devashish Tiwari see the FAQ:

https://matlab.fandom.com/wiki/FAQ#How_can_I_process_a_sequence_of_files?

Answer 2

[Walter Roberson]

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

[Adwait]

I still do not get 100 entries for the modified code.It only processes the latest image.

[Walter Roberson]

Save the entries into a single common array. xlswrite() the array only after all 100 are done.

[Ragavi Thiyagarajan]

i am also have a same problem with exporting extracted features from matlab to excel.. can explain me to .how to save the entries in a single array?

Answer 3

[Braiki Marwa]

i trained two-class-classification (svmtrain) with 15 features for 18 images and i have different number of objects in a single image. I want to save single .mat file of features of these images?my problem is when i run this code i have just the variables of last image!!This is my code :

NbIm = size(names1,1);
n1 = 1;
n2 = NbIm;
for n=n1:n2
  %1- Read the original image
  %2- Processing : Segmentation
  %3- characterization :
  [B3,L3,N3] = bwboundaries(ICellules); (see picture)
  CC = bwconncomp(L3);
  BW=bwlabel(L3); stats1=regionprops(CC,'Area','Centroid','Eccentricity','Perimeter','ConvexArea','ConvexHull','ConvexImage','MajorAxisLength','MinorAxisLength','Orientation','Solidity','BoundingBox');
  
  for k=1:length(B3),
    V=[];glcm=[];
    V=Im_originale(BW==k);
    glcm = graycomatrix(V,'Offset',[2 0],'Symmetric', true);
    stats= graycoprops(glcm);
    Contrast_Cellule =stats.Contrast;
    Correlation_Cellule =stats.Correlation;
    Energy_Cellule =stats.Energy;
    Homogeneity_Cellule =stats.Homogeneity;
    Area_cellule = stats1(k).Area;
    Perimeter_cellule = stats1(k).Perimeter;
    Circularity_cellule= (4*pi*Area_cellule)/Perimeter_cellule^2;
    Centroid_cellule = stats1(k).Centroid;
    Compactness_cellule=Perimeter_cellule^2/(4*pi*Area_cellule);
    MajorAxis_cellule=stats1(k). MajorAxisLength;
    MinorAxis_cellule=stats1(k). MinorAxisLength;
    Orientation_cellule =stats1(k).Orientation;
    Eccentricity_cellule=stats1(k).Eccentricity;
    Solidity_cellule=stats1(k).Solidity;
    boundary3 = B3{k};
    [cc] = chaincode(boundary3);
    ai=cc.code;
    ai = ai.';
    output = calc_harmonic_coefficients(ai,30);
    Ampl=0.5*sqrt((output(1)^2)+(output(2)^2)+(output(3)^2)+(output(4)^2));
    Feat(k,:)=[Area_cellule,Perimeter_cellule,Circularity_cellule,Compactness_cellule, Solidity_cellule,Eccentricity_cellule,MajorAxis_cellule,MinorAxis_cellule, Centroid_cellule,Ampl,Contrast_Cellule,Correlation_Cellule,Energy_Cellule,Homogeneity_Cellule];
  end
end

[Image Analyst]

THis

for k=1:length(B3),

should be

for k = 1 : length(stats1)

Then you just need to index things, like Area_cellule(k) instead of just Area_cellule which will get overwritten on every loop iteration. By the way, you can get all the props in a single array before the loop, like

Area_cellule= [stats1.Area];

No need to assign it in a loop one at a time.

[Braiki Marwa]

Hi, thanks for your response...can you please explain more because i don't understand

[Image Analyst]

Actually I thought B3 was an image, but it's not, so your for loop line should also work as it.

For the line

Area_cellule = stats1(k).Area;

you're just taking the k'th area variable and assigning it to Area_cellule. So for k=1 (first iteration) Area_cellule = the first area. For k=2, Area_cellule = the second area. For the last iteration Area_cellule = the last area. And when the loop finally exits, Area_cellule is just a single number equal to the last area, NOT an array of all areas like you said you wanted. To get an array, you either have to do

Area_cellule*k( = stats1(k).Area;

inside the loop, or better, don't assign Area_cellule at all inside the loop and have this outside the loop:

Area_cellule = [stats1.Area];

Same for all the other properties of stats1 you're trying to make into individual arrays, like Perimeter_cellule etc.

Answer 4

[anuar ibrahim]

numberOfResults = 42; % Whatever it is for a single image
numberOfImages = length(filenames); % Whatever...
allResults = zeros(numberOfImages, numberOfResults);
for k = 1 : numberOfImages
  % Read in image into variable called thisImage.
  % Analyze the image with function AnalyzeSingleImage and get results.
  thisImagesResults = AnalyzeSingleImage(thisImage);
  % Store results in allResults:
  allResults(k, :) = thisImagesResults;
end
xlswrite(excelFullFileName, allResults);

can u show with the code please? i dont understand