My score is always zero, please help. I am new to matlab. My code is below
1 view (last 30 days)
Show older comments
trainingDirectory = fullfile(*);
testingDirectory = fullfile(*);
% |imageDatastore| recursively scans the directory tree containing the
% images. Folder names are automatically used as labels for each image.
trainingSet = imageDatastore(trainingDirectory, 'IncludeSubfolders', true, 'LabelSource', 'foldernames');
testingSet = imageDatastore(testingDirectory, 'IncludeSubfolders', true, 'LabelSource', 'foldernames');
%% Extract HOG features from the train set.
numOfTrainImages = numel(trainingSet.Files);
cellSize=[8 8];
trainingFeatures = [];
trainingLabels = [];
for i = 1:numOfTrainImages
img = readimage(trainingSet, i);
img = imbinarize(img);
img = ~bwmorph(img,'thin',Inf);
%[extractFeatures,visuals]= extractHOGFeatures(img);
trainingFeatures(i,:)= extractHOGFeatures(img,'CellSize',cellSize);
end
% Get labels for each image.
trainingLabels = trainingSet.Labels;
classifier = fitcsvm(trainingFeatures, trainingLabels);
%% Extract HOG features from the test set.
setLabels = testingSet.Labels;
numOfTestImages = numel(testingSet.Files);
testingFeatures = [];
for i = 1:numOfTestImages
img = readimage(testingSet, i);
img = imbinarize(img);
img = ~bwmorph(img,'thin',Inf);
%[extractFeatures,visuals]= extractHOGFeatures(img);
testingFeatures(i,:)= extractHOGFeatures(img,'CellSize',cellSize);
end
[label,bothscores] = predict(classifier,trainingFeatures);
score = bothscores(:,1);
msgbox(sprintf('%.6f',score));
2 Comments
Answers (0)
See Also
Categories
Find more on Feature Detection and Extraction in Help Center and File Exchange
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!