Is my feature extraction using glcm is true or false? Please!!!

2 次查看（过去 30 天）

显示更早的评论

Yoon ThiriZaw 2018-6-24

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/407157-is-my-feature-extraction-using-glcm-is-true-or-false-please

评论： Image Analyst 2018-10-16

在 MATLAB Online 中打开

i am doing plant disease detection and classification. i do the following steps:

preprocessing using median filtering
image segmentation using color thresholder app in matlab
feature extraction using GLCM
classification using SVM

In this, i have done step 3 but i'm not certain it is true. So, i want to check up my code in feature extraction don't call function. How can i check up?(Eg. if i get energy=0.5, how to calculate to get 0.5 by handwritten without using mathlab function?)

My code is given in the following:

 % Title : Potato Leaf Disease Detection using SVM
clc
close all 
clear all
[filename, pathname] = uigetfile({'*.*';'*.bmp';'*.jpg';'*.gif'},
                                    'Pick a Leaf Image File');
I = imread([pathname,filename]);
I = imresize(I,[256,256]);
%figure, imshow(I); title('Input Leaf Image');
 %Preprocessing using median filtering
I1 = rgb2gray(I);
I2 = medfilt2(I1,[3 3]);
imshow(I2);title('Filtered Image');
%%Image Segmentation 
%Background Removing using Color Thresholder app
[bw,rgb] = background_removal(I);
%Masking Green_Pixels
mask = (rgb(:,:,2)>rgb(:,:,1))&(rgb(:,:,2)>rgb(:,:,3));
seg_img=bsxfun(@times,rgb,cast(imcomplement(mask),'like',rgb));
imshow(seg_img);
%%Feature Extraction
% Convert to grayscale if image is RGB
   img = rgb2gray(seg_img);
% Create the Gray Level Cooccurance Matrices (GLCMs)
glcms = graycomatrix(img);
%Evaluate 10 features from the disease affected region only
% Derive Statistics from GLCM
   stats = graycoprops(glcms,'Contrast Correlation Energy Homogeneity');
  Contrast = stats.Contrast;
  Correlation = stats.Correlation;
  Energy = stats.Energy;
  Homogeneity = stats.Homogeneity;
  Mean = mean2(seg_img);
  Standard_Deviation = std2(seg_img);
  Entropy = entropy(seg_img);
  RMS = mean2(rms(seg_img));
  %Skewness = skewness(img)
  Kurtosis = kurtosis(double(seg_img(:)));
  Skewness = skewness(double(seg_img(:)));
% Put the 10 features in an array
   feat_disease = [Contrast,Correlation,Energy,Homogeneity, Mean, Standard_Deviation, Entropy, RMS, Kurtosis, Skewness];