A Fast SVM-Based Tongue’s Colour Classification Aided by k-Means Clustering Identifiers and Colour Attributes as Computer-Assisted Tool for Tongue Diagnosis

Algorithm 1: Pseudocodes of training input setting in SVM.

width=200; height=200;

DataSet = cell([], 1);

%list and returns a character vector containing the full path to the file

for i=1:length(dir(fullfile(Dataset2,'*.png')))

      % Training set process

      k = dir(fullfile(Dataset2,'*.png'))

%Reading image and its information

      for j=1:length(k)

     tempImage = imread(horzcat(Dataset2,filesep,k{j}))

     imgInfo = imfinfo(horzcat(Dataset2,filesep,k{j}))

     %Image conversion to grayscale and using intensity as classification parameter in SVM

     if strcmp(imgInfo.ColorType,'grayscale')

         DataSet{j} = double(imresize(tempImage,[width height]))

     else

    DataSet{j}= double(imresize(rgb2gray(tempImage),[width height])); %we only use the colour intensity of grayscale picture to classify the images, we did measure the classification using hue (chromatic pixels), but tongue intensity provide better classifications.

Algorithm 1: Pseudocodes of training input setting in SVM.