marcus's profile - activity

I am using OpenCV java to build a leaf classifier. I extract HOG features from two datasets, one containing 100 images of a target leaf and another containing 100 negative images, images are sized to 50x50 pixels for both datasets. The extracted HOG descriptors are feed into a SVM for training and the application then tests the classifier with a sample dataset containing images sized to the training set. Here is my code:

public static void main(String[] args)
{
    // load opencv library
    System.loadLibrary(Core.NATIVE_LIBRARY_NAME);

    // create new file to contain positive and negative images
    File images = null;
    // create String to hold absolute path of image file
    String imageAbsPathAsStr = "";
    // create an array of image file paths
    File[] imageFilePaths;

    // set size of leaf image data and labels for SVM
    final int leafFileSize = 100;
    // set size of negative image data
    final int negFileSize = 100;
    final int numFiles = leafFileSize + negFileSize;

    // set leaf/neg image width
    final int width = 64;
    // set leaf/neg image height
    final int height = 128;
    final int imageArea = width * height;

    // create matrix for gray scale leaf image
    Mat leafGrayMat = new Mat(1, 1, CvType.CV_32FC1);

    // create matrix for neg image
    Mat negGrayMat = new Mat(1, 1, CvType.CV_32FC1);

    // create matrix of SVMtrainingData
    MatOfFloat SVMtrainingData = new MatOfFloat(numFiles, imageArea, CvType.CV_32FC1);

    // create matrix of image labels
    Mat labels = new Mat(numFiles, 1, CvType.CV_32FC1);

    // create HOG descriptor
    HOGDescriptor hog = new HOGDescriptor();
    // display hog params
    //System.out.println("winSize: " + hog.get_winSize());
    //System.out.println("winSigma: " + hog.get_winSigma());
    //System.out.println("blockSize: " + hog.get_blockSize());
    //System.out.println("cellSize: " + hog.get_cellSize());
    //System.out.println("blockStride: " + hog.get_blockStride());
    //System.out.println("descriptorSize: " + hog.getDescriptorSize());
    //System.out.println("L2HysThrehold: " + hog.get_L2HysThreshold());

    // create HOG matrices
    MatOfFloat ders = new MatOfFloat(1, 1, CvType.CV_32FC1);
    MatOfPoint locs = new MatOfPoint();

    // try opening leaf image folder
    try
    {
        // initialise leaf images with file path to leaf image directory
        images = new File("Images//acer_campestre_100_images");

        // assign leaf image path names to imageFilePaths
        imageFilePaths = images.listFiles();

        // traverse leaf image file paths
        for(File path : imageFilePaths)
        {
            // get absolute path of leaf image file
            imageAbsPathAsStr = path.getAbsolutePath();

            // initialise gray leaf matrix with gray scale version of leaf image
            leafGrayMat = Highgui.imread(imageAbsPathAsStr, Highgui.CV_LOAD_IMAGE_GRAYSCALE);

            // resize leafGrayMat to HOG default size 64x128
            Imgproc.resize(leafGrayMat, leafGrayMat, new Size(64, 128));

            // reshape leafGrayMat from 2D to 1D
            leafGrayMat = leafGrayMat.reshape(0, 1);

            // compute HOG features winStride of 8 x 8 to match hog cellSize and padding to 64 x 128 to match hog winSize
            hog.compute(leafGrayMat, ders, new Size(8, 8), new Size(64, 128), locs);

            // push ders to SVM training data
            SVMtrainingData.push_back(ders);

            // update labels
            labels.push_back(Mat.ones(1, 1, CvType.CV_32FC1));
        }
    }
    catch(Exception e)
    {
        // display error
        e.printStackTrace();
    }

    // try opening negative image folder
    try
    {
        // initialise images with file path to negative image directory
        images = new File("Images//neg_images_100");

        // assign negative image path names to imageFilePaths
        imageFilePaths = images.listFiles();

        // traverse negative image file paths
        for(File path : imageFilePaths)
        {
            // get absolute path of negative image file
            imageAbsPathAsStr = path.getAbsolutePath();

            // initialise gray negative matrix with gray scale ...

I am using the Java implementation to build a SVM classifier to classify tree leaves. I get the following errors when I try to train the SVM:

OpenCV Error: Sizes of input arguments do not match () in cv::Mat::push_back, file ........\opencv\modules\core\src\matrix.cpp, line 650 CvException [org.opencv.core.CvException: cv::Exception: ........\opencv\modules\core\src\matrix.cpp:650: error: (-209) in function cv::Mat::push_back ] at org.opencv.core.Mat.n_push_back(Native Method) at org.opencv.core.Mat.push_back(Mat.java:1863) at mark.smart.csc7057.surfdetectorandsvm.SurfDetectorAndSVM.main(SurfDetectorAndSVM.java:126) OpenCV Error: Sizes of input arguments do not match () in cv::Mat::push_back, file ........\opencv\modules\core\src\matrix.cpp, line 650 CvException [org.opencv.core.CvException: cv::Exception: ........\opencv\modules\core\src\matrix.cpp:650: error: (-209) in function cv::Mat::push_back ] at org.opencv.core.Mat.n_push_back(Native Method) at org.opencv.core.Mat.push_back(Mat.java:1863) at mark.smart.csc7057.surfdetectorandsvm.SurfDetectorAndSVM.main(SurfDetectorAndSVM.java:167)

OpenCV Error: Bad argument (There is only a single class) in cvPreprocessCategoricalResponses, file ........\opencv\modules\ml\src\inner_functions.cpp, line 729 Exception in thread "main" CvException [org.opencv.core.CvException: cv::Exception: ........\opencv\modules\ml\src\inner_functions.cpp:729: error: (-5) There is only a single class in function cvPreprocessCategoricalResponses ] at org.opencv.ml.CvSVM.train_0(Native Method) at org.opencv.ml.CvSVM.train(CvSVM.java:270) at mark.smart.csc7057.surfdetectorandsvm.SurfDetectorAndSVM.main(SurfDetectorAndSVM.java:228)

I have read that a BOW trainer should be employed to cluster the surf descriptors, unfortunately this feature is currently not available with the java implementation. I would appreciate any guidance (with sample code if possible) to resolve this problem. The code I have used is as follows:

public static void main(String[] args) { System.loadLibrary(Core.NATIVE_LIBRARY_NAME);

File leafImages = null;

String leafImageAbsPathAsStr = "";

File[] leafImageFilePaths;

File negImages = null;

String negImageAbsPathAsStr = "";

File[] negImageFilePaths;

final int leafImageWidth = 50; final int leafImageHeight = 50;

final int size = 200;

Mat leafGrayMat;
Mat leafBinMat = new Mat();

Mat negGrayMat; Mat negBinMat = new Mat();

Mat SVMtrainingData = new Mat(size, 1, CvType.CV_32FC1);

Mat labels = new Mat(size, 1, CvType.CV_32FC1);

List<float> trainingLabels = new ArrayList<float>();

MatOfKeyPoint keyPoints = new MatOfKeyPoint(); MatOfKeyPoint descriptors = new MatOfKeyPoint();

FeatureDetector featureDetector = FeatureDetector.create(FeatureDetector.SURF);

DescriptorExtractor descriptorExtractor = DescriptorExtractor.create(DescriptorExtractor.SURF);

try { leafImages = new File("Images//acer_campestre_100_images");

leafImageFilePaths = leafImages.listFiles();

for(File path : leafImageFilePaths)
{
  leafImageAbsPathAsStr = path.getAbsolutePath();

  leafGrayMat = Highgui.imread(leafImageAbsPathAsStr, Highgui.CV_LOAD_IMAGE_GRAYSCALE);

  Imgproc.adaptiveThreshold(leafGrayMat, leafBinMat, 255, Imgproc.ADAPTIVE_THRESH_GAUSSIAN_C,    Imgproc.THRESH_BINARY, 55, 5);

  featureDetector.detect(leafBinMat, keyPoints);

  descriptorExtractor.compute(leafBinMat, keyPoints, descriptors);

  descriptors.convertTo(descriptors, CvType.CV_32FC1);

  SVMtrainingData.push_back(descriptors);

  trainingLabels.add(1.0f);
}

} catch(Exception e) { e.printStackTrace(); } try { negImages = new File("Images//neg_images_100");

   negImageFilePaths = negImages.listFiles();

   for(File path : negImageFilePaths)
   {
 negImageAbsPathAsStr = path.getAbsolutePath();

 negGrayMat = Highgui.imread(negImageAbsPathAsStr, Highgui.CV_LOAD_IMAGE_GRAYSCALE);

 Imgproc.adaptiveThreshold(negGrayMat, negBinMat, 255, Imgproc.ADAPTIVE_THRESH_GAUSSIAN_C, Imgproc.THRESH_BINARY, 55, 5);

 featureDetector.detect(leafBinMat, keyPoints);

 descriptorExtractor.compute(leafBinMat, keyPoints, descriptors);

 SVMtrainingData.push_back(descriptors);

 trainingLabels.add(-1.0f);
  }

} catch(Exception e) { e.printStackTrace(); } Float[] trainingLabelsArray = trainingLabels.toArray(new ... (more)