computer vision systems toolbox question

When I generated an executable file using mcc -m BowClassifierTest_executable, it succeeded, but when I run it in command window, it complains about one error as below. The source code is the all the way bottom.

C:\FP\DB2_orig>BoWClassifierTest_executable.exe "0.5"

Creating Bag-Of-Features from 10 image sets. -------------------------------------------- * Image set 1: 1. * Image set 2: 10. * Image set 3: 2. * Image set 4: 3. * Image set 5: 4. * Image set 6: 5. * Image set 7: 6. * Image set 8: 7. * Image set 9: 8. * Image set 10: 9.

• Extracting SURF features using the Grid selection method. The GridStep is [8 8] and the BlockWidth is [32 64 96 128].
• Extracting features from 6 images in image set 1...done. Extracted 84000 features.
• Extracting features from 6 images in image set 2...done. Extracted 84000 features.
• Extracting features from 6 images in image set 3...done. Extracted 84000 features.
• Extracting features from 6 images in image set 4...done. Extracted 84000 features.
• Extracting features from 6 images in image set 5...done. Extracted 84000 features.
• Extracting features from 6 images in image set 6...done. Extracted 84000 features.
• Extracting features from 6 images in image set 7...done. Extracted 84000 features.
• Extracting features from 6 images in image set 8...done. Extracted 84000 features.
• Extracting features from 6 images in image set 9...done. Extracted 84000 features.
• Extracting features from 6 images in image set 10...done. Extracted 84000 features.
• Keeping 80 percent of the strongest features from each image set.
• Using K-Means clustering to create a 500 word visual vocabulary.
• Number of features : 672000
• Number of clusters (K) : 500
• Clustering...done.
• Finished creating Bag-Of-Features

Training an image category classifier for 10 categories. -------------------------------------------------------- * Category 1: 1 * Category 2: 10 * Category 3: 2 * Category 4: 3 * Category 5: 4 * Category 6: 5 * Category 7: 6 * Category 8: 7 * Category 9: 8 * Category 10: 9

• Encoding features for category 1...done.
• Encoding features for category 2...done.
• Encoding features for category 3...done.
• Encoding features for category 4...done.
• Encoding features for category 5...done.
• Encoding features for category 6...done.
• Encoding features for category 7...done.
• Encoding features for category 8...done.
• Encoding features for category 9...done.
• Encoding features for category 10...done.

Undefined function 'fitcecoc' for input arguments of type 'classreg.learning.Fit Template'.

Error in imageCategoryClassifier/trainEcocClassifier (line 476)

Error in imageCategoryClassifier (line 436)

Error in imageCategoryClassifier.create (line 320)

Error in trainImageCategoryClassifier (line 82)

Error in BoWClassifierTest_executable (line 23)

MATLAB:UndefinedFunction

C:\FP\DB2_orig>

//////////////////////////////////////////////////////////////////////////

function BoWClassifierTest_executable(ratio)

if(isdeployed) ratio = str2num(ratio); end imgSets = imageSet(pwd,'recursive'); %% [trainingSets,testSets] = partition(imgSets,ratio,'randomize'); %% bag = bagOfFeatures(trainingSets,'Verbose',true); %% img = read(imgSets(1), 1); featureVector = encode(bag, img);

% Plot the histogram of visual word occurrences figure bar(featureVector) title('Visual word occurrences') xlabel('Visual word index') ylabel('Frequency of occurrence') %% opts = templateSVM('BoxConstraint', 1.1, 'KernelFunction', 'gaussian'); categoryClassifier = trainImageCategoryClassifier(trainingSets, bag, 'LearnerOptions', opts, 'Verbose',true );

%% confMatrix_train = evaluate(categoryClassifier, trainingSets);

%% confMatrix_test = evaluate(categoryClassifier, testSets);

save([ 'result_' num2str(ratio) '.mat']);

Answer 1

[Dima Lisin]

Hi Hae-Jong,

Does this code run in MATLAB? Do you have the Statistics Toolbox installed? If so, then you should contact Mathworks tech support.

[Hae-Jong]

Yes, it is installed. I will contact them directly. Thanks.