private void addAllImagesToDBToolStripMenuItem_Click(object sender, EventArgs e)
{
FBD = new FolderBrowserDialog();
if (FBD.ShowDialog() == DialogResult.OK)
{
DirectoryInfo myFolder = new DirectoryInfo(FBD.SelectedPath);
foreach (string filename in Directory.GetFiles(FBD.SelectedPath))
{
bitmap = new Bitmap(filename);
hog = new HistogramsOfOrientedGradients();
hog.ProcessImage(bitmap);
human = new Human();
if (filename.Contains("image_human"))
{
human.IsHuman = 1;
}
else
{
human.IsHuman = 0;
}
line = AuxiliaryFunctions.ToOneLine(hog.Histograms);
byteArray = AuxiliaryFunctions.DoubleArrayToByte(line);
human.HOG = byteArray;
humanModel = new HumanModel();
humanModel.Insert(human);
}
}
}
/// <summary>
/// Extracts the hog accord.
/// </summary>
/// <param name="image">The image.</param>
/// <returns></returns>
public IList <double> ExtractHogAccord(Bitmap image)
{
var hog = new HistogramsOfOrientedGradients();
hog.ProcessImage(image);
var lined = hog.Histograms;
return(ToOneLine(lined));
}
public void MagnitudeDirectionTest()
{
byte[,] gradient = new byte[255, 255];
for (int i = 0; i < 255; i++)
{
for (int j = 0; j < 255; j++)
{
gradient[i, j] = (byte)j;
}
}
UnmanagedImage output;
new MatrixToImage().Convert(gradient, out output);
//ImageBox.Show(output);
var hog = new HistogramsOfOrientedGradients();
var result = hog.ProcessImage(output);
float[,] actualDir = hog.Direction;
Assert.AreEqual(255, actualDir.GetLength(0));
Assert.AreEqual(255, actualDir.GetLength(1));
for (int i = 0; i < 255; i++)
{
for (int j = 0; j < 255; j++)
{
Assert.AreEqual(0, actualDir[i, j]);
}
}
float[,] actualMag = hog.Magnitude;
Assert.AreEqual(255, actualMag.GetLength(0));
Assert.AreEqual(255, actualMag.GetLength(1));
for (int i = 0; i < 255; i++)
{
for (int j = 0; j < 255; j++)
{
if (i == 0 || j == 0 || i == 254 || j == 254)
{
Assert.AreEqual(0, actualMag[i, j]);
}
else
{
Assert.AreEqual(1, actualMag[i, j]);
}
}
}
}
private void addAllImagesToDBToolStripMenuItem_Click(object sender, EventArgs e)
{
humanList = new List <Human>();
if (FBD.ShowDialog() == DialogResult.OK)
{
DirectoryInfo myFolder = new DirectoryInfo(FBD.SelectedPath);
fileCount = Directory.GetFiles(FBD.SelectedPath).Count();
InitializeProgressBar();
foreach (string filename in Directory.GetFiles(FBD.SelectedPath))
{
bitmap = new Bitmap(filename);
hog = new HistogramsOfOrientedGradients();
hog.ProcessImage(bitmap);
human = new Human();
if (filename.Contains("image_human"))
{
human.IsHuman = 1;
}
else
{
human.IsHuman = -1;
}
line = AuxiliaryFunctions.ToOneLine(hog.Histograms);
byteArray = AuxiliaryFunctions.DoubleArrayToByte(line);
human.HOG = byteArray;
//XML file
humanList.Add(human);
index++;
if (index % (fileCount / 100) == 0)
{
progressValue++;
label1.Text = (progressValue + " %").ToString();
pb.Value = progressValue <= 100?progressValue:100;
Thread.Sleep(10);
}
}
if (!File.Exists("Database.xml"))
{
AuxiliaryFunctions.Serialize(humanList, "Database.xml");
}
else
{
humanList.AddRange(AuxiliaryFunctions.Deserialize <List <Human> >("Database.xml"));
AuxiliaryFunctions.Serialize(humanList, "Database.xml");
}
}
}
public void CloneTest()
{
var images = GetImages();
var hog = new HistogramsOfOrientedGradients();
var clone1 = (HistogramsOfOrientedGradients)hog.Clone();
List <double[]> features1 = hog.ProcessImage(images[0]);
Assert.AreEqual(features1.Count, 2352);
List <double[]> features2 = clone1.ProcessImage(images[0]);
Assert.AreEqual(features2.Count, 2352);
Assert.IsTrue(features1.ToArray().IsEqual(features2.ToArray()));
var clone2 = (HistogramsOfOrientedGradients)hog.Clone();
List <double[]> features3 = clone2.ProcessImage(images[0]);
Assert.AreEqual(features3.Count, 2352);
Assert.IsTrue(features1.ToArray().IsEqual(features3.ToArray()));
}
public static void OnePassOfWindow(System.Drawing.Image src, int width, int height)
{
Bitmap bmpImage = new Bitmap(src);
Rectangle cropRect = new Rectangle();
Bitmap newImage = new Bitmap(64, 128);
for (int i = 0; i < src.Height - height; i += height / 4)
{
for (int j = 0; j < src.Width - width; j += width / 4)
{
cropRect = new Rectangle(j, i, width, height);
newImage = bmpImage.Clone(cropRect, bmpImage.PixelFormat);
newImage = (Bitmap)ImageFunctions.ScaleImage(newImage, 64, 128);
HistogramsOfOrientedGradients hog = new HistogramsOfOrientedGradients();
hog.ProcessImage(newImage);
double[, ][] hogHistogram = hog.Histograms;
CompareHOG(hogHistogram);
}
}
}
public void MagnitudeDirectionTest()
{
byte[,] gradient = new byte[255, 255];
for (int i = 0; i < 255; i++)
for (int j = 0; j < 255; j++)
gradient[i, j] = (byte)j;
UnmanagedImage output;
new MatrixToImage().Convert(gradient, out output);
//ImageBox.Show(output);
HistogramsOfOrientedGradients hog = new HistogramsOfOrientedGradients();
var result = hog.ProcessImage(output);
float[,] actualDir = hog.Direction;
Assert.AreEqual(255, actualDir.GetLength(0));
Assert.AreEqual(255, actualDir.GetLength(1));
for (int i = 0; i < 255; i++)
for (int j = 0; j < 255; j++)
Assert.AreEqual(0, actualDir[i, j]);
float[,] actualMag = hog.Magnitude;
Assert.AreEqual(255, actualMag.GetLength(0));
Assert.AreEqual(255, actualMag.GetLength(1));
for (int i = 0; i < 255; i++)
{
for (int j = 0; j < 255; j++)
{
if (i == 0 || j == 0 || i == 254 || j == 254)
Assert.AreEqual(0, actualMag[i, j]);
else
Assert.AreEqual(1, actualMag[i, j]);
}
}
}
public static void OnePassOfWindow(System.Drawing.Image src, int width, int height, int step)
{
Bitmap bmpImage = new Bitmap(src);
cropRect = new Rectangle();
Bitmap newImage = new Bitmap(64, 128);
for (int i = 0; i < src.Height - height; i += step)
{
for (int j = 0; j < src.Width - width; j += step)
{
cropRect = new Rectangle(j, i, width, height);
newImage = bmpImage.Clone(cropRect, bmpImage.PixelFormat);
newImage = (Bitmap)ImageFunctions.ScaleImage(newImage, 64, 128);
HistogramsOfOrientedGradients hog = new HistogramsOfOrientedGradients();
hog.ProcessImage(newImage);
double[, ][] hogHistogram = hog.Histograms;
bool t = CompareHOG(hogHistogram);
if (t)
{
rectangleList.Add(cropRect);
newImage.Save(@"Output\image_" + Counter + ".png");
}
Counter += 1;
if (Counter % (ScanForm.countIter / 100) == 0)
{
progressValue++;
if (progressValue <= 100)
{
ScanForm.pb.Value = progressValue;
}
System.Threading.Thread.Sleep(10);
}
}
}
}
public void doc_test()
{
string localPath = TestContext.CurrentContext.TestDirectory;
#region doc_apply
// Let's load an example image, such as Lena,
// from a standard dataset of example images:
var images = new TestImages(path: localPath);
Bitmap lena = images["lena.bmp"];
// Create a new Histogram of Oriented Gradients with the default parameter values:
var hog = new HistogramsOfOrientedGradients(numberOfBins: 9, blockSize: 3, cellSize: 6);
// Use it to extract descriptors from the Lena image:
List <double[]> descriptors = hog.ProcessImage(lena);
// Now those descriptors can be used to represent the image itself, such
// as for example, in the Bag-of-Visual-Words approach for classification.
#endregion
Assert.AreEqual(784, descriptors.Count);
double sum = descriptors.Sum(x => x.Sum());
Assert.AreEqual(3359.1014569812564, sum, 1e-3);
}
/// <summary>
/// This methods computes the Bag-of-Visual-Words with the training images.
/// </summary>
///
private void btnBagOfWords_Click(object sender, EventArgs e)
{
int numberOfWords = (int)numWords.Value;
Stopwatch sw1 = Stopwatch.StartNew();
IBagOfWords <Bitmap> bow;
// Check if we will use SURF or FREAK as the feature detector
if (rbSurf.Checked)
{
// We will use SURF, so we can use a standard clustering
// algorithm that is based on Euclidean distances. A good
// algorithm for clustering codewords is the Binary Split
// variant of the K-Means algorithm.
// Create a Binary-Split clustering algorithm
BinarySplit binarySplit = new BinarySplit(numberOfWords);
// Create bag-of-words (BoW) with the given algorithm
BagOfVisualWords surfBow = new BagOfVisualWords(binarySplit);
// Compute the BoW codebook using training images only
bow = surfBow.Learn(originalTrainImages.Values.ToArray());
}
else if (rbFreak.Checked)
{
// We will use the FREAK detector. The features generated by FREAK
// are represented as bytes. While it is possible to transform those
// to standard double vectors, we will demonstrate how to use a non-
// Euclidean distance based algorithm to generate codewords for it.
// Note: Using Binary-Split with normalized FREAK features would
// possibly work better than the k-modes. This is just an example.
// Create a k-Modes clustering algorithm
var kmodes = new KModes <byte>(numberOfWords, new Hamming());
// Create a FREAK detector explicitly (if no detector was passed,
// the BagOfVisualWords would be using a SURF detector by default).
var freak = new FastRetinaKeypointDetector();
// Create bag-of-words (BoW) with the k-modes clustering and FREAK detector
var freakBow = new BagOfVisualWords <FastRetinaKeypoint, byte[]>(freak, kmodes);
// Compute the BoW codebook using training images only
bow = freakBow.Learn(originalTrainImages.Values.ToArray());
}
else
{
// We will use HOG, so we can use a standard clustering
// algorithm that is based on Euclidean distances. A good
// algorithm for clustering codewords is the Binary Split
// variant of the K-Means algorithm.
// Create a Binary-Split clustering algorithm
BinarySplit binarySplit = new BinarySplit(numberOfWords);
// Create a HOG detector explicitly (if no detector was passed,
// the BagOfVisualWords would be using a SURF detector by default).
var hog = new HistogramsOfOrientedGradients();
// Create bag-of-words (BoW) with the given algorithm
var hogBow = BagOfVisualWords.Create(hog, binarySplit);
// Compute the BoW codebook using training images only
bow = hogBow.Learn(originalTrainImages.Values.ToArray());
}
sw1.Stop();
// Now that we have already created and computed the BoW model, we
// will use it to extract representations for each of the images in
// both training and testing sets.
Stopwatch sw2 = Stopwatch.StartNew();
// Extract features for all images
foreach (ListViewItem item in listView1.Items)
{
// Get item image
Bitmap image = originalImages[item.ImageKey] as Bitmap;
// Get a feature vector representing this image
double[] featureVector = (bow as ITransform <Bitmap, double[]>).Transform(image);
// Represent it as a string so we can show it onscreen
string featureString = featureVector.ToString(DefaultArrayFormatProvider.InvariantCulture);
// Show it in the visual grid
if (item.SubItems.Count == 2)
{
item.SubItems[1].Text = featureString;
}
else
{
item.SubItems.Add(featureString);
}
// Retrieve the class labels, that we had stored in the Tag
int classLabel = (item.Tag as Tuple <double[], int>).Item2;
// Now, use the Tag to store the feature vector too
item.Tag = Tuple.Create(featureVector, classLabel);
}
sw2.Stop();
lbStatus.Text = "BoW constructed in " + sw1.Elapsed + "s. Features extracted in " + sw2.Elapsed + "s.";
btnSampleRunAnalysis.Enabled = true;
}