private void HsvHistButton_Click(object sender, EventArgs e)
{
int HBins = 50;
int SBins = 0;
int VBins = 0;
bool isCorrectValue = false;
if (HistDim == 1 && int.TryParse(HBinTextBox.Text, out HBins))
{
isCorrectValue = true;
}
else if (HistDim == 2 && int.TryParse(HBinTextBox.Text, out HBins) && int.TryParse(SBinTextBox.Text, out SBins))
{
isCorrectValue = true;
}
else
{
MessageBox.Show("數值不對");
}
if (wantExtractFeatureImage != null && isCorrectValue)
{
if (learningSys != null)
{
learningSys.SetLearningImage(wantExtractFeatureImage);
}
else
{
learningSys = new FeatureLearning(wantExtractFeatureImage);
}
templateHist = learningSys.CalHist(HistDim, HBins, SBins, VBins);
if (HistDim <= 2)
{
showTemplateHistImg = SystemToolBox.DrawHsvHistogram(templateHist);
ShowHistViewer(templateHistImgBox, showTemplateHistImg, "樣板影像");
}
else
{
MessageBox.Show("Dim = " + HistDim + ",can;t draw");
}
}
else
{
MessageBox.Show("圖片未載入");
}
}
private void loadImgButton_Click(object sender, EventArgs e)
{
string fileName = OpenLearningImgFile();
if (fileName != null)
{
loadImg = new Image <Bgr, byte>(fileName);
if (learningSys != null)
{
learningSys.SetLearningImage(fileName);
}
else
{
learningSys = new FeatureLearning(fileName);
}
loadImgBox.Image = loadImg.Resize(320, 240, Emgu.CV.CvEnum.INTER.CV_INTER_LINEAR);
}
}
private void extractFeatureButton_Click(object sender, EventArgs e)
{
if (wantExtractFeatureImage != null)
{
if (learningSys != null)
{
learningSys.SetLearningImage(wantExtractFeatureImage);
}
else
{
learningSys = new FeatureLearning(wantExtractFeatureImage);
}
surfData = learningSys.CalSURFFeature();
//Draw Feature
Image <Bgr, byte> drawKeyPointImg = SystemToolBox.DrawSURFFeature(surfData);
new ImageViewer(drawKeyPointImg, "擷取特徵點結果").Show();
}
}
public void Execute(Arguments arguments)
{
LoggedConsole.WriteLine("feature learning process...");
var inputDir = @"D:\Mahnoosh\Liz\Least_Bittern\";
var inputPath = Path.Combine(inputDir, "TrainSet\\one_min_recordings");
var trainSetPath = Path.Combine(inputDir, "TrainSet\\train_data");
// var testSetPath = Path.Combine(inputDir, "TestSet");
var configPath = @"D:\Mahnoosh\Liz\Least_Bittern\FeatureLearningConfig.yml";
var resultDir = Path.Combine(inputDir, "FeatureLearning");
Directory.CreateDirectory(resultDir);
// var outputMelImagePath = Path.Combine(resultDir, "MelScaleSpectrogram.png");
// var outputNormMelImagePath = Path.Combine(resultDir, "NormalizedMelScaleSpectrogram.png");
// var outputNoiseReducedMelImagePath = Path.Combine(resultDir, "NoiseReducedMelSpectrogram.png");
// var outputReSpecImagePath = Path.Combine(resultDir, "ReconstrcutedSpectrogram.png");
// var outputClusterImagePath = Path.Combine(resultDir, "Clusters.bmp");
// +++++++++++++++++++++++++++++++++++++++++++++++++patch sampling from 1-min recordings
var configFile = configPath.ToFileInfo();
if (configFile == null)
{
throw new FileNotFoundException("No config file argument provided");
}
else if (!configFile.Exists)
{
throw new ArgumentException($"Config file {configFile.FullName} not found");
}
var configuration = ConfigFile.Deserialize <FeatureLearningSettings>(configFile);
int patchWidth =
(configuration.MaxFreqBin - configuration.MinFreqBin + 1) / configuration.NumFreqBand;
var clusteringOutputList = FeatureLearning.UnsupervisedFeatureLearning(configuration, inputPath);
List <double[][]> allBandsCentroids = new List <double[][]>();
for (int i = 0; i < clusteringOutputList.Count; i++)
{
var clusteringOutput = clusteringOutputList[i];
// writing centroids to a csv file
// note that Csv.WriteToCsv can't write data types like dictionary<int, double[]> (problems with arrays)
// I converted the dictionary values to a matrix and used the Csv.WriteMatrixToCsv
// it might be a better way to do this
string pathToClusterCsvFile = Path.Combine(resultDir, "ClusterCentroids" + i.ToString() + ".csv");
var clusterCentroids = clusteringOutput.ClusterIdCentroid.Values.ToArray();
Csv.WriteMatrixToCsv(pathToClusterCsvFile.ToFileInfo(), clusterCentroids.ToMatrix());
// sorting clusters based on size and output it to a csv file
Dictionary <int, double> clusterIdSize = clusteringOutput.ClusterIdSize;
int[] sortOrder = KmeansClustering.SortClustersBasedOnSize(clusterIdSize);
// Write cluster ID and size to a CSV file
string pathToClusterSizeCsvFile = Path.Combine(resultDir, "ClusterSize" + i.ToString() + ".csv");
Csv.WriteToCsv(pathToClusterSizeCsvFile.ToFileInfo(), clusterIdSize);
// Draw cluster image directly from clustering output
List <KeyValuePair <int, double[]> > list = clusteringOutput.ClusterIdCentroid.ToList();
double[][] centroids = new double[list.Count][];
for (int j = 0; j < list.Count; j++)
{
centroids[j] = list[j].Value;
}
allBandsCentroids.Add(centroids);
List <double[, ]> allCentroids = new List <double[, ]>();
for (int k = 0; k < centroids.Length; k++)
{
// convert each centroid to a matrix in order of cluster ID
// double[,] cent = PatchSampling.ArrayToMatrixByColumn(centroids[i], patchWidth, patchHeight);
// OR: in order of cluster size
double[,] cent = MatrixTools.ArrayToMatrixByColumn(centroids[sortOrder[k]], patchWidth, configuration.PatchHeight);
// normalize each centroid
double[,] normCent = DataTools.normalise(cent);
// add a row of zero to each centroid
double[,] cent2 = PatchSampling.AddRow(normCent);
allCentroids.Add(cent2);
}
// concatenate all centroids
double[,] mergedCentroidMatrix = PatchSampling.ListOf2DArrayToOne2DArray(allCentroids);
// Draw clusters
var clusterImage = ImageTools.DrawMatrixWithoutNormalisation(mergedCentroidMatrix);
clusterImage.RotateFlip(RotateFlipType.Rotate270FlipNone);
var outputClusteringImage = Path.Combine(resultDir, "ClustersWithGrid" + i.ToString() + ".bmp");
clusterImage.Save(outputClusteringImage);
}
// extracting features
FeatureExtraction.UnsupervisedFeatureExtraction(configuration, allBandsCentroids, trainSetPath, resultDir);
LoggedConsole.WriteLine("Done...");
}
