//:::::::::::::::::fin variables::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::
//:::::::::::::Morphological operations ::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::
private Image<Gray, Byte> openingOperation(Image<Gray, Byte> binaryFrame)
{
StructuringElementEx SElement;
SElement = new StructuringElementEx(3, 9, 1, 4, Emgu.CV.CvEnum.CV_ELEMENT_SHAPE.CV_SHAPE_RECT);
binaryFrame._MorphologyEx(SElement, Emgu.CV.CvEnum.CV_MORPH_OP.CV_MOP_OPEN, 1);
return binaryFrame;
} //end openingOperation()
} //end openingOperation()
private Image<Gray, Byte> closeOperation(Image<Gray, Byte> binaryFrame)
{
StructuringElementEx SElement;
SElement = new StructuringElementEx(3, 11, 1, 5, Emgu.CV.CvEnum.CV_ELEMENT_SHAPE.CV_SHAPE_RECT);
binaryFrame._MorphologyEx(SElement, Emgu.CV.CvEnum.CV_MORPH_OP.CV_MOP_CLOSE, 1);
return binaryFrame;
}
public override Image<Gray, byte> DetectSkin(Image<Bgr, byte> Img, IColor min, IColor max)
{
Image<Ycc, Byte> currentYCrCbFrame = Img.Convert<Ycc, Byte>();
Image<Gray, byte> skin = new Image<Gray, byte>(Img.Width, Img.Height);
skin = currentYCrCbFrame.InRange((Ycc)min,(Ycc) max);
StructuringElementEx rect_12 = new StructuringElementEx(12, 12, 6, 6, Emgu.CV.CvEnum.CV_ELEMENT_SHAPE.CV_SHAPE_RECT);
CvInvoke.cvErode(skin, skin, rect_12, 1);
StructuringElementEx rect_6 = new StructuringElementEx(6, 6, 3, 3, Emgu.CV.CvEnum.CV_ELEMENT_SHAPE.CV_SHAPE_RECT);
CvInvoke.cvDilate(skin, skin, rect_6, 2);
return skin;
}
public Image<Gray, Byte> GetContoursHard()
{
Image<Gray, Byte> cannyEdges = this.GrayscaleImage.Canny(this.trackBarThreshold.Value, this.trackBarThresholdLinking.Value);
StructuringElementEx element = new StructuringElementEx(3, 3, 1, 1, Emgu.CV.CvEnum.CV_ELEMENT_SHAPE.CV_SHAPE_CROSS);
CvInvoke.cvMorphologyEx(cannyEdges, cannyEdges, IntPtr.Zero, element, CV_MORPH_OP.CV_MOP_GRADIENT, 1);
this.Contours = cannyEdges.FindContours(Emgu.CV.CvEnum.CHAIN_APPROX_METHOD.CV_CHAIN_APPROX_SIMPLE, Emgu.CV.CvEnum.RETR_TYPE.CV_RETR_EXTERNAL);
return cannyEdges;
}
public override Image<Gray, byte> DetectSkin(Image<Bgr, byte> Img, IColor min, IColor max)
{
Image<Hsv, Byte> currentHsvFrame = Img.Convert<Hsv, Byte>();
Image<Gray, byte> skin = new Image<Gray, byte>(Img.Width, Img.Height);
skin = currentHsvFrame.InRange((Hsv)min, (Hsv)max);
StructuringElementEx rect_6 = new StructuringElementEx(3, 3,1, 1, Emgu.CV.CvEnum.CV_ELEMENT_SHAPE.CV_SHAPE_RECT);
CvInvoke.cvDilate(skin, skin, rect_6, 2);
return skin;
}
public Dictionary<Card, Point> LocateCards(Image<Bgr, Byte> table, Settings settings)
{
#region process image
//Convert the image to grayscale and filter out the noise
Image<Gray, Byte> gray = table.Convert<Gray, Byte>();
Gray cannyThreshold = new Gray(180);
Gray cannyThresholdLinking = new Gray(120);
Gray circleAccumulatorThreshold = new Gray(120);
Image<Gray, Byte> cannyEdges = gray.Canny(cannyThreshold, cannyThresholdLinking);
StructuringElementEx el = new StructuringElementEx(3, 3, 1, 1, CV_ELEMENT_SHAPE.CV_SHAPE_RECT);
cannyEdges = cannyEdges.MorphologyEx(el, CV_MORPH_OP.CV_MOP_CLOSE, 1);
#endregion
Contour<Point> contours = cannyEdges.FindContours(
CHAIN_APPROX_METHOD.CV_CHAIN_APPROX_SIMPLE, //was CV_CHAIN_APPROX_SIMPLE
RETR_TYPE.CV_RETR_TREE);
ContourNode tree = new ContourNode(contours);
Dictionary<Card, Point> cardlocs = new Dictionary<Card, Point>();
foreach (KeyValuePair<Card, CardContour> pair in GiveCards(tree))
{
ContourNode node = pair.Value.Node;
Card card = pair.Key;
PointF fcenter = node.Contour.GetMinAreaRect().center;
Point center = new Point((int)fcenter.X, (int)fcenter.Y);
cardlocs.Add(card, center);
}
#region draw
#if DEBUG
TreeViz.VizualizeTree(tree);
ContourAnalyzer.DrawContours(tree, table);
//ImageViewer.Show(table);
#endif
#endregion
return cardlocs;
}
public override Image<Gray, byte> DetectSkin(Image<Bgr, byte> Img, IColor min, IColor max)
{
//Code adapted from here
// http://blog.csdn.net/scyscyao/archive/2010/04/09/5468577.aspx
// Look at this paper for reference (Chinese!!!!!)
// http://www.chinamca.com/UploadFile/200642991948257.pdf
Image<Ycc, Byte> currentYCrCbFrame = Img.Convert<Ycc, Byte>();
Image<Gray, Byte> skin = new Image<Gray, Byte>(Img.Width, Img.Height);
int y, cr, cb, l, x1, y1, value;
int rows = Img.Rows;
int cols = Img.Cols;
Byte[,,] YCrCbData = currentYCrCbFrame.Data;
Byte[,,] skinData = skin.Data;
for (int i = 0; i < rows; i++)
for (int j = 0; j < cols; j++)
{
y = YCrCbData[i, j, 0];
cr = YCrCbData[i, j, 1];
cb = YCrCbData[i, j, 2];
cb -= 109;
cr -= 152;
x1 = (819 * cr - 614 * cb) / 32 + 51;
y1 = (819 * cr + 614 * cb) / 32 + 77;
x1 = x1 * 41 / 1024;
y1 = y1 * 73 / 1024;
value = x1 * x1 + y1 * y1;
if (y < 100)
skinData[i, j, 0] = (value < 700) ? (byte)255 : (byte)0;
else
skinData[i, j, 0] = (value < 850) ? (byte)255 : (byte)0;
}
StructuringElementEx rect_6 = new StructuringElementEx(6, 6, 3, 3, Emgu.CV.CvEnum.CV_ELEMENT_SHAPE.CV_SHAPE_RECT);
CvInvoke.cvErode(skin, skin, rect_6, 1);
CvInvoke.cvDilate(skin, skin, rect_6, 2);
return skin;
}
///////////////////////////////////////////////////////////////////////////////////////////
void processFrameAndUpdateGUI(object sender, EventArgs arg)
{
imgOriginal = capWebcam.QueryFrame(); // get next frame from the webcam
if (imgOriginal == null) // if we did not get a frame
{ // show error via message box
MessageBox.Show("unable to read from webcam" + Environment.NewLine + Environment.NewLine +
"exiting program");
Environment.Exit(0); // and exit program
}
imgBlurredBGR = imgOriginal.SmoothGaussian(5); // blur
imgProcessed = imgBlurredBGR.InRange(new Bgr(0, 0, 175), new Bgr(100, 100, 256)); // filter on color
imgProcessed = imgProcessed.SmoothGaussian(5); // blur again
StructuringElementEx structuringElementEx = new StructuringElementEx(5, 5, 1, 1, CV_ELEMENT_SHAPE.CV_SHAPE_RECT); // declare structuring element to use in dilate and erode
CvInvoke.cvDilate(imgProcessed, imgProcessed, structuringElementEx, 1); // close image (dilate, then erode)
CvInvoke.cvErode(imgProcessed, imgProcessed, structuringElementEx, 1); // closing "closes" (i.e. fills in) foreground gaps
CircleF[] circles = imgProcessed.HoughCircles(new Gray(100), new Gray(50), 2, imgProcessed.Height / 4, 10, 400)[0]; // fill variable circles with all circles in the processed image
foreach (CircleF circle in circles) // for each circle
{
if (txtXYRadius.Text != "") txtXYRadius.AppendText(Environment.NewLine); // if we are not on the first line in the text box then insert a new line char
txtXYRadius.AppendText("ball position = x " + circle.Center.X.ToString().PadLeft(4) + // print ball position and radius
", y = " + circle.Center.Y.ToString().PadLeft(4) + //
", radius = " + circle.Radius.ToString("###.000").PadLeft(7)); //
txtXYRadius.ScrollToCaret(); // scroll down in text box so most recent line added (at the bottom) will be shown
// draw a small green circle at the center of the detected object
CvInvoke.cvCircle(imgOriginal, new Point((int)circle.Center.X, (int)circle.Center.Y), 3, new MCvScalar(0, 255, 0), -1, LINE_TYPE.CV_AA, 0);
imgOriginal.Draw(circle, new Bgr(Color.Red), 3); // draw a red circle around the detected object
}
ibOriginal.Image = imgOriginal; // update image boxes on form
ibProcessed.Image = imgProcessed; //
}
public override Image<Gray, byte> DetectSkin(Image<Bgr, byte> Img, IColor min, IColor max)
{
Image<Ycc, Byte> currentYCrCbFrame = Img.Convert<Ycc, Byte>();
Image<Gray, Byte> skin = new Image<Gray, Byte>(Img.Width, Img.Height);
int y, cr, cb, l, x1, y1, value;
int rows = Img.Rows;
int cols = Img.Cols;
Byte[, ,] YCrCbData = currentYCrCbFrame.Data;
Byte[, ,] skinData = skin.Data;
for (int i = 0; i < rows; i++)
for (int j = 0; j < cols; j++)
{
y = YCrCbData[i, j, 0];
cr = YCrCbData[i, j, 1];
cb = YCrCbData[i, j, 2];
cb -= 109;
cr -= 152;
x1 = (819 * cr - 614 * cb) / 32 + 51;
y1 = (819 * cr + 614 * cb) / 32 + 77;
x1 = x1 * 41 / 1024;
y1 = y1 * 73 / 1024;
value = x1 * x1 + y1 * y1;
if (y < 100)
skinData[i, j, 0] = (value < 700) ? (byte)255 : (byte)0;
else
skinData[i, j, 0] = (value < 850) ? (byte)255 : (byte)0;
}
StructuringElementEx rect_6 = new StructuringElementEx(6, 6, 3, 3, Emgu.CV.CvEnum.CV_ELEMENT_SHAPE.CV_SHAPE_RECT);
CvInvoke.cvErode(skin, skin, rect_6, 1);
CvInvoke.cvDilate(skin, skin, rect_6, 2);
return skin;
}
public frmMain()
{
InitializeComponent();
Status = new frmStatus(); //okienko w którym będzie podgląd jak działa aplikacja
obraz1 = new Image<Bgr, byte>(new Size(640, 480));
tlo = new Image<Bgr, byte>(new Size(640, 480));
//inicjalizacja kamerki
kamerka = new Capture(0);
//wątek odczytu start
th_pobierzObraz = new Thread(pobierzObraz);
//wątek zliczania czasu
th_liczCzas = new Thread(liczCzas);
rect_12 = new StructuringElementEx(12, 12, 6, 6, Emgu.CV.CvEnum.CV_ELEMENT_SHAPE.CV_SHAPE_RECT);
rect_6 = new StructuringElementEx(6, 6, 3, 3, Emgu.CV.CvEnum.CV_ELEMENT_SHAPE.CV_SHAPE_RECT);
lNapis.Text = "";
}
private Image<Gray, Single> _testMorphological(Image<Gray, Single> img, int threshold, int maxGrayVal, int closingIteration, int cols, int rows, int anchorX, int anchorY, int shape)
{
img = img.Sobel(0, 1, 3);
StructuringElementEx element = new StructuringElementEx(cols, rows, anchorX, anchorY, Emgu.CV.CvEnum.CV_ELEMENT_SHAPE.CV_SHAPE_RECT); ;
if (shape == 1)
element = new StructuringElementEx(cols, rows, anchorX, anchorY, Emgu.CV.CvEnum.CV_ELEMENT_SHAPE.CV_SHAPE_CROSS);
else if (shape == 2)
element = new StructuringElementEx(cols, rows, anchorX, anchorY, Emgu.CV.CvEnum.CV_ELEMENT_SHAPE.CV_SHAPE_ELLIPSE);
img = img.MorphologyEx(element, Emgu.CV.CvEnum.CV_MORPH_OP.CV_MOP_CLOSE, closingIteration);
img = img.Rotate(90.0, new Gray(255), false);
img = img.MorphologyEx(element, Emgu.CV.CvEnum.CV_MORPH_OP.CV_MOP_CLOSE, closingIteration);
img = img.Rotate(-90.0, new Gray(255), false);
if (threshold >= 0 && threshold <= maxGrayVal)
{
img = img.ThresholdBinary(new Gray(threshold), new Gray(255));
}
else
{
MessageBox.Show("Threshold is not appropriate, please choose another!");
}
return img;
}
public void _testSobelParameters(Image<Gray, Single> img, int threshold, int maxGrayVal, int closingIteration, int cols, int rows, int anchorX, int anchorY, int shape)
{
int xOrder = 0, yOrder = 0, appetureSize = 1;
for (appetureSize = 3; appetureSize < 8; appetureSize += 2)
{
for (xOrder = 0; xOrder < appetureSize-1; xOrder++)
for (yOrder = 0; yOrder < appetureSize-1; yOrder++)
{
img = img.Sobel(xOrder, yOrder, appetureSize);
StructuringElementEx element;
if (shape == 0)
element = new StructuringElementEx(cols, rows, anchorX, anchorY, Emgu.CV.CvEnum.CV_ELEMENT_SHAPE.CV_SHAPE_RECT);
else if (shape == 1)
element = new StructuringElementEx(cols, rows, anchorX, anchorY, Emgu.CV.CvEnum.CV_ELEMENT_SHAPE.CV_SHAPE_CROSS);
else
element = new StructuringElementEx(cols, rows, anchorX, anchorY, Emgu.CV.CvEnum.CV_ELEMENT_SHAPE.CV_SHAPE_ELLIPSE);
img = img.MorphologyEx(element, Emgu.CV.CvEnum.CV_MORPH_OP.CV_MOP_CLOSE, closingIteration);
img = img.Rotate(90.0, new Gray(255), false);
img = img.MorphologyEx(element, Emgu.CV.CvEnum.CV_MORPH_OP.CV_MOP_CLOSE, closingIteration);
img = img.Rotate(-90.0, new Gray(255), false);
if (threshold >= 0 && threshold <= maxGrayVal)
{
img = img.ThresholdBinary(new Gray(threshold), new Gray(255));
}
else
{
MessageBox.Show("Threshold is not appropriate, please choose another!");
}
img.Bitmap.Save(@"Sobel\" + xOrder + " " + yOrder + " " + appetureSize + ".png");
}
}
}
/// <summary>
///
/// </summary>
/// <param name="img">Input Image</param>
/// <param name="threshold">Threshold value (with 8-bit image is from 0 to 255)</param>
/// <param name="maxGrayVal">Maximum Gray Value</param>
/// <param name="closingIteration">number of Iterations</param>
/// <returns>Processed Image</returns>
public Image<Gray, Single> _imageProcessing(Image<Gray, Single> img, int threshold, int maxGrayVal, int closingIteration)
{
img = img.Sobel(0, 1, 3);
StructuringElementEx element = new StructuringElementEx(3, 3, -1, -1, Emgu.CV.CvEnum.CV_ELEMENT_SHAPE.CV_SHAPE_ELLIPSE);
img = img.MorphologyEx(element, Emgu.CV.CvEnum.CV_MORPH_OP.CV_MOP_CLOSE, closingIteration);
img = img.Rotate(-90.0, new Gray(255), false);
img = img.MorphologyEx(element, Emgu.CV.CvEnum.CV_MORPH_OP.CV_MOP_CLOSE, closingIteration);
img = img.Rotate(90.0, new Gray(255), false);
if (threshold >= 0 && threshold <= maxGrayVal)
{
img = img.ThresholdBinary(new Gray(threshold), new Gray(maxGrayVal));
}
else
{
//MessageBox.Show("Threshold is not appropriate, please choose another!");
throw new ArgumentOutOfRangeException("Threshold is not appropriate, please choose another threshold value!");
}
return img;
}
public void testClosingParameters(Image<Gray, Single> inputImg)
{
int rows, colums, anchorX, anchorY, shape, closingIteration, threshold;
int count = 1;
Image<Gray, float> img = inputImg;
for (closingIteration = 6; closingIteration < 7; closingIteration++)
{
for (shape = 0; shape < 1; shape++)
{
for (rows = 5; rows < 7; rows++)
for (colums = 5; colums < 7; colums++)
{
for (anchorX = 0; anchorX < colums; anchorX++)
for (anchorY = 0; anchorY < rows; anchorY++)
{
for (threshold = 80; threshold < 180; threshold += 20)
{
img = inputImg.Sobel(0, 1, 3);
img = inputImg.Sobel(1, 0, 3);
StructuringElementEx element = new StructuringElementEx(colums, rows, anchorX, anchorY, Emgu.CV.CvEnum.CV_ELEMENT_SHAPE.CV_SHAPE_RECT); ;
if (shape == 1)
element = new StructuringElementEx(colums, rows, anchorX, anchorY, Emgu.CV.CvEnum.CV_ELEMENT_SHAPE.CV_SHAPE_CROSS);
else if (shape == 2)
element = new StructuringElementEx(colums, rows, anchorX, anchorY, Emgu.CV.CvEnum.CV_ELEMENT_SHAPE.CV_SHAPE_ELLIPSE);
img = img.MorphologyEx(element, Emgu.CV.CvEnum.CV_MORPH_OP.CV_MOP_CLOSE, closingIteration);
img = img.Rotate(90.0, new Gray(255), false);
img = img.MorphologyEx(element, Emgu.CV.CvEnum.CV_MORPH_OP.CV_MOP_CLOSE, closingIteration);
img = img.Rotate(-90.0, new Gray(255), false);
if (threshold >= 0 && threshold <= 255)
{
img = img.ThresholdBinary(new Gray(threshold), new Gray(255));
}
else
{
MessageBox.Show("Threshold is not appropriate, please choose another!");
}
string str_shape;
if (shape == 0)
str_shape = "RECTANGLE";
else if (shape == 1)
str_shape = "CROSS";
else str_shape = "ELLIPSE";
img.Bitmap.Save(@"Result\" + closingIteration + "_" + str_shape + "_" + rows + "_" + colums + "_" + anchorX + "_" + anchorY + "_" + threshold + ".bmp");
count++;
}
}
}
}
}
MessageBox.Show("Done " + count + " images saved!");
}
/// <summary>
/// LocateCards works by analyzing the contours in the image.
/// For instance, the Diamond in Set is a polygon with exactly 4 vertices.
/// The Oval has no such features yet.
/// The Squiggle is not convex, but concave and has edges in a 'right bend', instead of only 'left bends'
///
/// All these shapes are inside the contour of a (white) card, which is a rounded square.
/// Cards may also be the (only) exterior boundaries
/// </summary>
/// <param name="table">An image displaying the table with the Set cards</param>
/// <returns>A dict locating which cards are present where in the image</returns>
public Dictionary<Card, Point> LocateCards(Image<Bgr, Byte> table, Settings settings)
{
classifier = new BgrHsvClassifier();
classifier.Train();
#region process image
//Convert the image to grayscale and filter out the noise
Image<Gray, Byte> gray = table.Convert<Gray, Byte>();
Gray cannyThreshold = new Gray(50); //180
Gray cannyThresholdLinking = new Gray(30); //120
Gray circleAccumulatorThreshold = new Gray(100); //120
#region old
Image<Gray, Byte> cannyEdges = gray.Canny(cannyThreshold, cannyThresholdLinking);
if (settings.debuglevel >= 3)
{
ImageViewer.Show(cannyEdges, "cannyEdges before Closing");
}
#endregion
//#region new
//Image<Gray, Byte> thresholded = new Image<Gray, byte>(gray.Size);
//CvInvoke.cvAdaptiveThreshold(gray.Ptr, thresholded.Ptr,
// 255,
// ADAPTIVE_THRESHOLD_TYPE.CV_ADAPTIVE_THRESH_GAUSSIAN_C,
// THRESH.CV_THRESH_BINARY_INV, 9, 5);
//StructuringElementEx el1 = new StructuringElementEx(3, 3, 1, 1, CV_ELEMENT_SHAPE.CV_SHAPE_RECT);
//thresholded = thresholded.Erode(1);//thresholded.MorphologyEx(el1, CV_MORPH_OP.CV_MOP_CLOSE, 1);//
//Image<Gray, Byte> cannyEdges = thresholded;//.Canny(new Gray(1), new Gray(10));
//#endregion
//StructuringElementEx el = new StructuringElementEx(5, 5, 2, 2, CV_ELEMENT_SHAPE.CV_SHAPE_RECT);
StructuringElementEx el = new StructuringElementEx(3, 3, 1, 1, CV_ELEMENT_SHAPE.CV_SHAPE_RECT);
cannyEdges = cannyEdges.MorphologyEx(el, CV_MORPH_OP.CV_MOP_CLOSE, 1);
if (settings.debuglevel >= 3)
{
ImageViewer.Show(cannyEdges, "cannyEdges after Closing");
}
#endregion
Contour<Point> contours = cannyEdges.FindContours(
CHAIN_APPROX_METHOD.CV_CHAIN_APPROX_SIMPLE, //was CV_CHAIN_APPROX_SIMPLE
RETR_TYPE.CV_RETR_TREE);
ContourNode tree = new ContourNode(contours);
FilterTree(tree);
#region debug
if (settings.debuglevel >= 3)
{
var debug = table.Clone();
DrawContours(tree, debug);
ImageViewer.Show(debug, "Contours after filtering");
}
#endregion
AssignShapes(tree);
AssignImages(tree, table, true);
#region debug
if (settings.debuglevel >= 3)
{
var debug1 = table.Clone();
DrawContours(tree, debug1);
ImageViewer.Show(debug1);
}
#endregion
FilterTree(tree);
#region debug
if (settings.debuglevel >= 3)
{
var debug2 = table.Clone();
DrawContours(tree, debug2);
ImageViewer.Show(debug2);
}
#endregion
AssignColors(tree, table, settings);
#region debug
if (settings.debuglevel >= 3)
{
TreeViz.VizualizeTree(tree);
}
#endregion
AssignFills(tree);
Dictionary<Card, Point> cardlocs = new Dictionary<Card, Point>();
foreach (KeyValuePair<Card, ContourNode> pair in GiveCards(tree))
{
ContourNode node = pair.Value;
Card card = pair.Key;
PointF fcenter = node.Contour.GetMinAreaRect().center;
Point center = new Point((int)fcenter.X, (int)fcenter.Y);
cardlocs.Add(card, center);
}
#region debug
if (settings.debuglevel >= 1)
{
TreeViz.VizualizeTree(tree);
}
if (settings.debuglevel >= 2)
{
DrawContours(tree, table);
ImageViewer.Show(table);
}
#endregion
return cardlocs;
}
private Image<Gray, Byte> erodeDilateImage(Image<Gray, Byte> img)
{
if (erodeDimensionTB.Text != "" & erodeDimensionTB.Text != "0" & erodeOffsetTB.Text != "" & erodeOffsetTB.Text != "0" )
{
erodeDimension = Convert.ToInt32(erodeDimensionTB.Text);
erodeOffset = Convert.ToInt32(erodeOffsetTB.Text);
//if (erodeDimension != 0 & erodeOffset != 0)
//{
if (erodeDimension > erodeOffset)
{
StructuringElementEx rectErode = new StructuringElementEx(erodeDimension, erodeDimension, erodeOffset, erodeOffset, Emgu.CV.CvEnum.CV_ELEMENT_SHAPE.CV_SHAPE_RECT);
CvInvoke.cvErode(img, img, rectErode, 1);
}
//}
}
if (dilateDimensionTB.Text != "" & dilateDimensionTB.Text != "0" & dilateOffsetTB.Text != "" & dilateOffsetTB.Text != "0")
{
dilateDimension = Convert.ToInt32(dilateDimensionTB.Text);
dilateOffset = Convert.ToInt32(dilateOffsetTB.Text);
//if (dilateDimension != 0 & dilateOffset != 0)
//{
if (dilateDimension > dilateOffset)
{
StructuringElementEx rectDilate = new StructuringElementEx(dilateDimension, dilateDimension, dilateOffset, dilateOffset, Emgu.CV.CvEnum.CV_ELEMENT_SHAPE.CV_SHAPE_RECT);
CvInvoke.cvDilate(img, img, rectDilate, 2);
}
//}
}
return img;
}
private Image<Gray, Single> _testMorphological(Image<Gray, Single> img, int threshold, int maxGrayVal, int closingIteration, int cols, int rows, int anchorX, int anchorY, int shape)
{
int xOrder = Int32.Parse(txtXorder.Text), yOrder = Int32.Parse(txtYorder.Text),
appetureSize = Int32.Parse(txtAppetureSize.Text);
//img = img.Sobel(0, 1, 5);
//img = img.Sobel(xOrder, yOrder, appetureSize);
img = sobel_Filter(img);
StructuringElementEx element;
if(shape==0)
element = new StructuringElementEx(cols, rows, anchorX, anchorY, Emgu.CV.CvEnum.CV_ELEMENT_SHAPE.CV_SHAPE_RECT);
else if (shape == 1)
element = new StructuringElementEx(cols, rows, anchorX, anchorY, Emgu.CV.CvEnum.CV_ELEMENT_SHAPE.CV_SHAPE_CROSS);
else
element = new StructuringElementEx(cols, rows, anchorX, anchorY, Emgu.CV.CvEnum.CV_ELEMENT_SHAPE.CV_SHAPE_ELLIPSE);
img = img.MorphologyEx(element, Emgu.CV.CvEnum.CV_MORPH_OP.CV_MOP_CLOSE, closingIteration);
img = img.Rotate(90.0, new Gray(255), false);
img = img.MorphologyEx(element, Emgu.CV.CvEnum.CV_MORPH_OP.CV_MOP_CLOSE, closingIteration);
img = img.Rotate(-90.0, new Gray(255), false);
if (threshold >= 0 && threshold <= maxGrayVal)
{
img = img.ThresholdBinary(new Gray(threshold), new Gray(255));
}
else
{
MessageBox.Show("Threshold is not appropriate, please choose another!");
}
//img.Bitmap.Save(@"Sobel\" + xOrder + " " + yOrder + " " + appetureSize + ".png");
return img;
}
public void TestMorphEx()
{
StructuringElementEx element1 = new StructuringElementEx(3, 3, 1, 1, Emgu.CV.CvEnum.CV_ELEMENT_SHAPE.CV_SHAPE_CROSS);
StructuringElementEx element2 = new StructuringElementEx(new int[3, 3] { { 0, 1, 0 }, { 1, 0, 1 }, { 0, 1, 0 } }, 1, 1);
Image<Bgr, Byte> tmp = new Image<Bgr, byte>(100, 100);
Image<Bgr, Byte> tmp2 = tmp.MorphologyEx(element1, Emgu.CV.CvEnum.CV_MORPH_OP.CV_MOP_GRADIENT, 1);
Image<Bgr, Byte> tmp3 = tmp.MorphologyEx(element2, Emgu.CV.CvEnum.CV_MORPH_OP.CV_MOP_BLACKHAT, 1);
}
// Cherche les contours et bounding boxes de la peau sur une image fournie
// Cette partie a été développée par nous-même
// Elle détecte et sépare les parties de peau de l'image fournie à la classe, d'après les couleurs HSV
// On va ensuite eroder et dilater les pixels restants, afin d'obtenir une image "plus nette" et réduire le bruit et les imperfections
// On va ensuite rechercher tous les contours dans l'image obtenur et mettre le plus grand de côté afin de pouvoir le traiter plus tard
public void FindSkinContours()
{
// Converti les couleurs de l'image en HSV
Image<Hsv, Byte> hsvImg = imgOrg.Convert<Hsv, Byte>();
// Filtre les pixels de l'image afin de ne garder que ceux qui se rapprochent de la couleur de la peau
// Nous avons trouvé ces valeurs sur Internet et les avons un peu adaptées pour notre utilisation
imgSkin = hsvImg.InRange(new Hsv(0, 48, 80), new Hsv(20, 255, 255));
imgSkin = imgSkin.ThresholdBinary(new Gray(200), new Gray(255));
// On erode et dilate pour éliminer les imperfections
// Nous avons trouvé ces valeurs par "tattonement" en essayant d'avoir un contour de main le plus net possible
StructuringElementEx erodeStrctEl = new StructuringElementEx(4, 4, 2, 2, Emgu.CV.CvEnum.CV_ELEMENT_SHAPE.CV_SHAPE_RECT);
CvInvoke.cvErode(imgSkin, imgSkin, erodeStrctEl, 1);
StructuringElementEx dilateStrctEl = new StructuringElementEx(6, 6, 3, 3, Emgu.CV.CvEnum.CV_ELEMENT_SHAPE.CV_SHAPE_RECT);
CvInvoke.cvDilate(imgSkin, imgSkin, dilateStrctEl, 3);
// Boucle sur tous les contours trouvés dans l'image
for (Contour<Point> contours = imgSkin.FindContours(Emgu.CV.CvEnum.CHAIN_APPROX_METHOD.CV_CHAIN_APPROX_SIMPLE, Emgu.CV.CvEnum.RETR_TYPE.CV_RETR_TREE, contoursStorage); contours != null; contours = contours.HNext)
{
// Si un contour est plus grand que 20x20 pixels, on le traite
if (contours.BoundingRectangle.Width > 20 && contours.BoundingRectangle.Height > 20)
{
// Récupère la bounding box autour du contour
Rectangle rect = contours.BoundingRectangle;
// On agrandi la bourning box et on vérifie qu'elle ne sorte pas de l'image
rect.X = rect.X - 10;
rect.X = (rect.X < 0) ? 0 : rect.X;
rect.Y = rect.Y - 10;
rect.Y = (rect.Y < 0) ? 0 : rect.Y;
rect.Height = (rect.Height + 20);
rect.Width = (rect.Width + 20);
// Ajout de la bounding box et du contour aux listes
boundingBoxes.Add(rect);
contoursList.Add(contours);
}
}
// Si des contours ont été trouvés, on cherche le plus grand
if(boundingBoxes.Count > 0)
{
FindBiggestBoundingBox();
FindBiggestContour();
isHandDetected = true;
}
else
{
// Sinon, c'est que rien n'a été détecté
isHandDetected = false;
fingerNum = 0;
}
}
private GrayImage removeGradient(GrayImage image)
{
if (!preprocessorRemoveGrading)
return image;
//TODO: Test if morf improve
GrayImage grayImage = image.Copy();
StructuringElementEx element = new StructuringElementEx(1, 1, 0, 0, CV_ELEMENT_SHAPE.CV_SHAPE_ELLIPSE);
element = new StructuringElementEx(2, 2, 0, 0, CV_ELEMENT_SHAPE.CV_SHAPE_ELLIPSE);
grayImage._MorphologyEx(element, CV_MORPH_OP.CV_MOP_CLOSE, 1);
saveDebugImage(grayImage, "after Morph");
element.Dispose();
//grayImage._ThresholdBinary(new Gray(120), new Gray(255));
GrayImage paddedImage = new GrayImage(350, 350);
CvInvoke.cvCopyMakeBorder(grayImage, paddedImage, new Point(25, 25), BORDER_TYPE.CONSTANT, new MCvScalar(0));
//grayImage.Dispose();
grayImage = paddedImage;
saveDebugImage(grayImage, "Binary image (larger)");
for (var contour = grayImage.FindContours(CHAIN_APPROX_METHOD.CV_CHAIN_APPROX_SIMPLE, RETR_TYPE.CV_RETR_CCOMP); contour != null; contour = contour.HNext)
{
Point[] points = contour.ToArray();
MCvBox2D box = PointCollection.MinAreaRect(Array.ConvertAll(points, item => (PointF)item));
if (box.size.Height < 5 || box.size.Width < 5)
grayImage.FillConvexPoly(points, new Gray(0));
}
grayImage._ThresholdBinaryInv(new Gray(128), new Gray(255));
for (var contour = grayImage.FindContours(CHAIN_APPROX_METHOD.CV_CHAIN_APPROX_SIMPLE, RETR_TYPE.CV_RETR_CCOMP); contour != null; contour = contour.HNext)
{
Point[] points = contour.ToArray();
MCvBox2D box = PointCollection.MinAreaRect(Array.ConvertAll(points, item => (PointF)item));
//Console.WriteLine("hight: " + box.size.Height.ToString() + " Witdh: " + box.size.Width.ToString());
if (box.size.Height < 5 || box.size.Width < 5)
grayImage.FillConvexPoly(points, new Gray(0));
}
grayImage._ThresholdBinaryInv(new Gray(128), new Gray(255));
saveDebugImage(grayImage, "Grading removed");
return grayImage.GetSubRect(new Rectangle(25, 25, 300, 300));
}
private void cogian()
{
Image<Gray, Byte> eroded = new Image<Gray, byte>(grayImg.Size);
Image<Gray, Byte> temp = new Image<Gray, byte>(grayImg.Size);
Image<Gray, Byte> skel = new Image<Gray, byte>(grayImg.Size);
//skel.SetValue(0);
// CvInvoke.cvThreshold(grayImg, grayImg, 127, 256, 0);
StructuringElementEx element = new StructuringElementEx(10, 10, 1, 1, Emgu.CV.CvEnum.CV_ELEMENT_SHAPE.CV_SHAPE_CROSS);
CvInvoke.cvErode(grayImg, eroded, element, 1);
CvInvoke.cvDilate(eroded, temp, element, 1);
temp = grayImg.Sub(temp);
skel = skel | temp;
grayImg = eroded;
pictureBox3.Image = grayImg.ToBitmap();
}
private Image<Gray, Byte> detectSkin(Image<Bgr, Byte> Img)
{
Image<Ycc, Byte> currentYCrCbFrame = Img.Convert<Ycc, Byte>();
Image<Gray, byte> skin = new Image<Gray, byte>(Img.Width, Img.Height);
skin = currentYCrCbFrame.InRange(new Ycc(0, 131, 80), new Ycc(255, 185, 135));
StructuringElementEx rect_12 = new StructuringElementEx(12, 12, 6, 6, Emgu.CV.CvEnum.CV_ELEMENT_SHAPE.CV_SHAPE_RECT);
CvInvoke.cvErode(skin, skin, rect_12, 1);
StructuringElementEx rect_6 = new StructuringElementEx(6, 6, 3, 3, Emgu.CV.CvEnum.CV_ELEMENT_SHAPE.CV_SHAPE_RECT);
CvInvoke.cvDilate(skin, skin, rect_6, 2);
return skin;
}
private Image<Gray, Single> morfologyEx(Image<Gray, Single> img)
{
StructuringElementEx element = new StructuringElementEx(5, 5, 3, 3, Emgu.CV.CvEnum.CV_ELEMENT_SHAPE.CV_SHAPE_RECT);
img = img.MorphologyEx(element, Emgu.CV.CvEnum.CV_MORPH_OP.CV_MOP_CLOSE, closingIteration);
return img;
}
/// <summary>
///
/// </summary>
/// <param name="img">Input Image</param>
/// <param name="threshold">Threshold value (with 8-bit image is from 0 to 255)</param>
/// <param name="maxGrayVal">Maximum Gray Value</param>
/// <param name="closingIteration">number of Iterations</param>
/// <returns></returns>
private Image<Gray, Single> _imageProcessing(Image<Gray, Single> img, int threshold, int maxGrayVal, int closingIteration)
{
img = img.Sobel(0, 1, 4);
StructuringElementEx element = new StructuringElementEx(4, 4, 1, 1, Emgu.CV.CvEnum.CV_ELEMENT_SHAPE.CV_SHAPE_RECT);
//MessageBox.Show((int)Emgu.CV.CvEnum.CV_ELEMENT_SHAPE.CV_SHAPE_ELLIPSE + "");
img = img.MorphologyEx(element, Emgu.CV.CvEnum.CV_MORPH_OP.CV_MOP_CLOSE, closingIteration);
img = img.Rotate(90.0, new Gray(maxGrayValue), false);
img = img.MorphologyEx(element, Emgu.CV.CvEnum.CV_MORPH_OP.CV_MOP_CLOSE, closingIteration);
img = img.Rotate(-90.0, new Gray(maxGrayValue), false);
if (threshold >= 0 && threshold <= maxGrayVal)
{
img = img.ThresholdBinary(new Gray(threshold), new Gray(maxGrayValue));
}
else
{
MessageBox.Show("Threshold is not appropriate, please choose another!");
}
return img;
}
public double MatchIteration(Matrix X, Matrix Y, Matrix V1, Matrix V2, Matrix t1, Matrix t2)
{
timer.Clear();
double timeused = 0;
timer.Restart();
var tk = t1.Clone(); // tk=t1;
int w = 4;
int ndum = (int)(nsamp * ndum_frac);
nsamp1 = nsamp2 = nsamp;
#region demo2迭代
Matrix Xk = X.Clone();
int N1 = V1.Rows, N2 = V2.Columns;
if (display_flag) {
Draw(X, Y, V1, V2, @"D:\Play Data\Iteration\原图.bmp", "原始图像和采样");
//DrawGradient(X, Y, t1, t2, N2, N1, @"D:\Play Data\Iteration\原图梯度.bmp", "原始图像切向量");
}
int k = 0;
var out_vec_1 = Utils.InitArray<bool>(nsamp1, false);//out_vec_1=zeros(1,nsamp1);
var out_vec_2 = Utils.InitArray<bool>(nsamp2, false);//out_vec_2=zeros(1,nsamp2);
double ori_weight = 0.1;
double tan_eps = 1.0;
bool affine_start_flag = true;
bool polarity_flag = true;
double matchcost = double.MaxValue;
double sc_cost = 0, aff_cost = 0, E = 0;
Matrix cx = null, cy = null; // cx, cy是插值线性方程组的解的两列
Matrix axt = null, wxt = null, ayt = null, wyt = null, d2 = null, U = null,
X2 = null, Y2 = null, X2b = null, X3b = null, Y3 = null;
double mean_dist_1 = 0, mean_dist_2 = 0;
var min1 = new[] { new { Val = 0.0, Idx = 0 } };
var min2 = min1;
#region 用于打网格的坐标
Matrix coordX = null, coordY = null;
int coordMargin = (int)(N1 * coordMarginRate);
MatrixUtils.CreateGrid(N1 + coordMargin * 2, N2 + coordMargin * 2, out coordX, out coordY);
coordX = coordX.Each(v => v - coordMargin * 2);
coordY = coordY.Each(v => v - coordMargin * 2);
//int MM = N1 * N2 / 25; // M=length(x);
#endregion
timeused += timer.StopAndSay("初始化");
while (k < n_iter) {
Debug("Iter={0}", k);
#region 计算两个形状上下文
timer.Restart();
// [BH1,mean_dist_1]=sc_compute(Xk',zeros(1,nsamp),mean_dist_global,nbins_theta,nbins_r,r_inner,r_outer,out_vec_1);
var BH1 = ComputeSC(Xk.Transpose(), Zeros(1, nsamp), mean_dist_global, out mean_dist_1, out_vec_1);
//var BH1 = ComputeSC(Xk.Transpose(), t1.Transpose(), mean_dist_global, out mean_dist_1, out_vec_1);
// [BH2,mean_dist_2]=sc_compute(Y',zeros(1,nsamp),mean_dist_global,nbins_theta,nbins_r,r_inner,r_outer,out_vec_2);
var BH2 = ComputeSC(Y.Transpose(), Zeros(1, nsamp), mean_dist_global, out mean_dist_2, out_vec_2);
//var BH2 = ComputeSC(Y.Transpose(), t2.Transpose(), mean_dist_global, out mean_dist_2, out_vec_2);
timeused += timer.StopAndSay("计算两个形状上下文");
Debug("Mean_dist_1:{0:F4}", mean_dist_1);
Debug("Mean_dist_2:{0:F4}", mean_dist_2);
#endregion
#region 计算lambda_o和beta_k
double lambda_o;
if (affine_start_flag) {
if (k == 0)
lambda_o = 1000;
else
lambda_o = beta_init * Math.Pow(r, k - 1); // lambda_o=beta_init*r^(k-2);
} else {
lambda_o = beta_init * Math.Pow(r, k); // lambda_o=beta_init*r^(k-1);
}
double beta_k = mean_dist_2 * mean_dist_2 * lambda_o;
#endregion
#region 计算代价矩阵
timer.Restart();
var costmat_shape = HistCost(BH1, BH2); // costmat_shape = hist_cost_2(BH1, BH2);
// theta_diff=repmat(tk,1,nsamp)-repmat(t2',nsamp,1);
var theta_diff = tk.RepMat(1, nsamp) - t2.Transpose().RepMat(nsamp, 1);
Matrix costmat_theta;
if (polarity_flag) {
// costmat_theta=0.5*(1-cos(theta_diff));
//costmat_theta = 0.5 * (Ones(costmat_shape.Rows, costmat_shape.Columns) - theta_diff.Each(v => Math.Cos(v)));
costmat_theta = theta_diff.Each(v => 0.5 * (1 - Math.Cos(v)));
} else {
// costmat_theta=0.5*(1-cos(2*theta_diff));
//costmat_theta = 0.5 * (Ones(costmat_shape.Rows, costmat_shape.Columns) - theta_diff.Each(v => Math.Cos(2 * v)));
costmat_theta = theta_diff.Each(v => 0.5 * (1 - Math.Cos(2 * v)));
}
// costmat=(1-ori_weight)*costmat_shape+ori_weight*costmat_theta;
var costmat = (1 - ori_weight) * costmat_shape + ori_weight * costmat_theta;
int nptsd = nsamp + ndum; // nptsd=nsamp+ndum;
var costmat2 = new DenseMatrix(nptsd, nptsd, eps_dum); // costmat2=eps_dum*ones(nptsd,nptsd);
costmat2.SetSubMatrix(0, nsamp, 0, nsamp, costmat); // costmat2(1:nsamp,1:nsamp)=costmat;
timeused += timer.StopAndSay("计算代价矩阵");
#endregion
#region 匈牙利算法
timer.Restart();
var costmat_int = new int[nptsd, nptsd];
for (int i = 0; i < nptsd; ++i) {
for (int j = 0; j < nptsd; ++j) {
costmat_int[i, j] = (int)(costmat2[i, j] * 10000);
}
}
var km = new KM(nptsd, costmat_int);
km.Match(false);
matchcost = km.MatchResult / 10000.0;
int[] cvec = km.MatchPair; // cvec=hungarian(costmat2);
timeused += timer.StopAndSay("匈牙利算法");
#endregion
#region 计算野点标记向量，重排匹配点
timer.Restart();
int[] cvec2 = cvec.Select((v, i) => new { Val = v, Idx = i })
.OrderBy(v => v.Val)
.Select(v => v.Idx)
.ToArray();// [a,cvec2]=sort(cvec);
out_vec_1 = cvec2.Take(nsamp1).Select(v => v > nsamp2).ToArray(); // out_vec_1=cvec2(1:nsamp1)>nsamp2;
out_vec_2 = cvec.Take(nsamp2).Select(v => v > nsamp1).ToArray(); // out_vec_2=cvec(1:nsamp2)>nsamp1;
//X2 = NaNs(nptsd, 2); // X2=NaN*ones(nptsd,2);
//X2.SetSubMatrix(0, nsamp1, 0, X2.Columns, Xk); // X2(1:nsamp1,:)=Xk;
//X2 = X2.SortRowsBy(cvec); // X2=X2(cvec,:);
X2b = NaNs(nptsd, 2); // X2b=NaN*ones(nptsd,2);
X2b.SetSubMatrix(0, nsamp1, 0, X2b.Columns, X); // X2b(1:nsamp1,:)=X;
X2b = X2b.SortRowsBy(cvec); // X2b=X2b(cvec,:);
Y2 = NaNs(nptsd, 2); // Y2=NaN*ones(nptsd,2);
Y2.SetSubMatrix(0, nsamp2, 0, Y2.Columns, Y); // Y2(1:nsamp2,:)=Y;
var ind_good = X2b.GetColumn(1).Take(nsamp).FindIdxBy(v => !double.IsNaN(v)); // ind_good=find(~isnan(X2b(1:nsamp,1)));
int n_good = ind_good.Length; // n_good=length(ind_good);
X3b = X2b.FilterRowsBy(ind_good);// X3b=X2b(ind_good,:);
Y3 = Y2.FilterRowsBy(ind_good); // Y3=Y2(ind_good,:);
timeused += timer.StopAndSay("计算野点标记向量，重排匹配点");
#endregion
#region figure 2
if (display_flag) {
//figure(2)
//plot(X2(:,1),X2(:,2),'b+',Y2(:,1),Y2(:,2),'ro')
//hold on
//h=plot([X2(:,1) Y2(:,1)]',[X2(:,2) Y2(:,2)]','k-');
//if display_flag
//% set(h,'linewidth',1)
//quiver(Xk(:,1),Xk(:,2),cos(tk),sin(tk),0.5,'b') // 画箭头
//quiver(Y(:,1),Y(:,2),cos(t2),sin(t2),0.5,'r')
DrawGradient(Xk, Y, tk, t2, N2, N1,
String.Format(@"D:\Play Data\Iteration\梯度\{0}.bmp", k),
String.Format("Iter={0}梯度方向\n匹配点数{1}", k, n_good));
//end
//hold off
//axis('ij')
//title([int2str(n_good) ' correspondences (warped X)'])
//axis([1 N2 1 N1])
//drawnow
}
#endregion
#region figure 3 显示未变形图的匹配关系
if (display_flag) {
//% show the correspondences between the untransformed images
//figure(3)
//plot(X(:,1),X(:,2),'b+',Y(:,1),Y(:,2),'ro')
//ind=cvec(ind_good);
//hold on
//plot([X2b(:,1) Y2(:,1)]',[X2b(:,2) Y2(:,2)]','k-')
//hold off
//axis('ij')
//title([int2str(n_good) ' correspondences (unwarped X)'])
//axis([1 N2 1 N1])
//drawnow
Draw(X, Y, cvec, null, N2, N1, String.Format(@"D:\Play Data\Iteration\匹配\{0}.bmp", k),
String.Format("Iter={0}\n匹配代价{1},匹配数{2}", k, matchcost, n_good));
}
#endregion
#region 求解变换矩阵
timer.Restart();
Bookstein(X3b, Y3, beta_k, ref cx, ref cy, ref E); // [cx,cy,E]=bookstein(X3b,Y3,beta_k);
timeused += timer.StopAndSay("求解变换矩阵");
#endregion
#region 通过解出来的变换对点和梯度进行变换
timer.Restart();
// % calculate affine cost
var A = MatrixUtils.RankHorizon(
cx.GetSubMatrix(n_good + 1, 2, 0, 1), cy.GetSubMatrix(n_good + 1, 2, 0, 1)
);//A=[cx(n_good+2:n_good+3,:) cy(n_good+2:n_good+3,:)];
var s = new Svd(A, true).S(); // s=svd(A);
aff_cost = Math.Log(s[0] / s[1]); // aff_cost=log(s(1)/s(2));
// % calculate shape context cost
min1 = costmat.GetColumns().Select(col => {
int minwhere = 0;
for (int i = 1; i < col.Count; ++i) {
if (col[i] < col[minwhere]) minwhere = i;
}
return new { Val = col[minwhere], Idx = minwhere };
}).ToArray();// [a1,b1]=min(costmat,[],1);
min2 = costmat.GetRows().Select(row => {
int minwhere = 0;
for (int i = 1; i < row.Count; ++i) {
if (row[i] < row[minwhere]) minwhere = i;
}
return new { Val = row[minwhere], Idx = minwhere };
}).ToArray(); // [a2,b2]=min(costmat,[],2);}
sc_cost = Math.Max(min1.Average(a => a.Val), min2.Average(a => a.Val)); // sc_cost=max(mean(a1),mean(a2));
// % warp each coordinate
axt = cx.GetSubMatrix(n_good, 3, 0, 1).Transpose(); // axt是cx中的最后三个，即a的x分量
wxt = cx.GetSubMatrix(0, n_good, 0, 1).Transpose(); // wxt是cs中的前n个，即w的x分量
ayt = cy.GetSubMatrix(n_good, 3, 0, 1).Transpose();
wyt = cy.GetSubMatrix(0, n_good, 0, 1).Transpose();
d2 = Dist2(X3b, X).Each(v => v > 0 ? v : 0); // d2=max(dist2(X3b,X),0);
U = d2.PointMultiply(d2.Each(v => Math.Log(v + Epsilon))); // U=d2.*log(d2+eps);
Debug("MatchCost:{0:F4}\taff_cost:{1:F4}\tsc_cost:{2:F4}\tE:{3:F8}", matchcost, aff_cost, sc_cost, E);
var Z = Transformation(X, U, axt, wxt, ayt, wyt);
//% apply the warp to the tangent vectors to get the new angles
var Xtan = X + tan_eps * MatrixUtils.RankHorizon(t1.Each(Math.Cos), t1.Each(Math.Sin)); // Xtan=X+tan_eps*[cos(t1) sin(t1)];
d2 = Dist2(X3b, Xtan).Each(v => v > 0 ? v : 0); // d2=max(dist2(X3b,Xtan),0);
U = d2.PointMultiply(d2.Each(v => Math.Log(v + Epsilon))); // U=d2.*log(d2+eps);
//Transformation(Xtan, U, axt, wxt, ayt, wyt, out fx, out fy);
//var Ztan = MatrixUtils.RankVertical(fx, fy).Transpose(); // Ztan=[fx; fy]';
var Ztan = Transformation(Xtan, U, axt, wxt, ayt, wyt);
for (int i = 0; i < nsamp; ++i) {
tk[i, 0] = Math.Atan2(Ztan[i, 1] - Z[i, 1], Ztan[i, 0] - Z[i, 0]);
}//tk=atan2(Ztan(:,2)-Z(:,2),Ztan(:,1)-Z(:,1));
timeused += timer.StopAndSay("通过解出来的变换对点和梯度进行变换");
#endregion
#region figure 4 显示变形后的点集
if (display_flag) {
//figure(4)
//plot(Z(:,1),Z(:,2),'b+',Y(:,1),Y(:,2),'ro');
//axis('ij')
//title(['k=' int2str(k) ', \lambda_o=' num2str(lambda_o) ', I_f=' num2str(E) ', aff.cost=' num2str(aff_cost) ', SC cost=' num2str(sc_cost)])
//axis([1 N2 1 N1])
//% show warped coordinate grid
//fx_aff=cx(n_good+1:n_good+3)'*[ones(1,M); x'; y'];
//d2=dist2(X3b,[x y]);
//fx_wrp=cx(1:n_good)'*(d2.*log(d2+eps));
//fx=fx_aff+fx_wrp;
//fy_aff=cy(n_good+1:n_good+3)'*[ones(1,M); x'; y'];
//fy_wrp=cy(1:n_good)'*(d2.*log(d2+eps));
//fy=fy_aff+fy_wrp;
//hold on
//plot(fx,fy,'k.','markersize',1)
//hold off
//drawnow
d2 = Dist2(X3b, MatrixUtils.RankHorizon(coordX, coordY));//d2=dist2(X3b,[x y]);
U = d2.PointMultiply(d2.Each(v => Math.Log(v + Epsilon)));
//Transformation(MatrixUtils.RankHorizon(coordX, coordY), U, axt, wxt, ayt, wyt, out fx, out fy);
//var coordsT = MatrixUtils.RankVertical(fx, fy).Transpose();
var coordsT = Transformation(MatrixUtils.RankHorizon(coordX, coordY), U, axt, wxt, ayt, wyt);
Draw(Z, Y, null, coordsT, N2, N1, String.Format(@"D:\Play Data\Iteration\变换\{0}.bmp", k),
String.Format("Iter={0}\nλo={1:F4},If={2:F4},aff_cost{3:F4},sc_cost{4:F4}", k, lambda_o, E, aff_cost, sc_cost));
}
#endregion
Xk = Z.Clone();
++k;
}
#endregion
#region 迭代完成后的代价计算
#region 我来尝试计算Dsc
// Xk是Q变换后的结果，而Y是模板图形P
/*
* Dsc = Avg_each_p_in_P(argmin(q in Q, C(p, T(q))) + Avg_each_q_in_Q(argmin(p in P, C(p, T(q)))
* */
double mean_dist_final_1;
var scQ = ComputeSC(Xk.Transpose(), Zeros(1, nsamp), mean_dist_global, out mean_dist_final_1, out_vec_1);
//var scQ = ComputeSC(Xk.Transpose(), Zeros(1, nsamp), mean_dist_1, out mean_dist_final_1, out_vec_1);
//var scQ = ComputeSC(Xk.Transpose(), t1.Transpose(), mean_dist_1, out mean_dist_final_1, out_vec_1);
double mean_dist_final_2;
var scP = ComputeSC(Y.Transpose(), Zeros(1, nsamp), mean_dist_global, out mean_dist_final_2, out_vec_2);
//var scP = ComputeSC(Y.Transpose(), Zeros(1, nsamp), mean_dist_2, out mean_dist_final_2, out_vec_2);
//var scP = ComputeSC(Y.Transpose(), t2.Transpose(), mean_dist_2, out mean_dist_final_2, out_vec_2);
var costmat_final = HistCost(scQ, scP);
double distance_sc = costmat_final.GetRows().Select(row => row.Min()).Average()
+ costmat_final.GetColumns().Select(col => col.Min()).Average();
Debug("distance_sc:{0}", distance_sc);
#endregion
#region 图像变换和插值
timer.Restart();
//[x,y]=meshgrid(1:N2,1:N1);
//x=x(:);y=y(:);
Matrix x = null, y = null;
MatrixUtils.CreateGrid(N1, N2, out x, out y);
//int M = N1 * N2; // M=length(x);
d2 = Dist2(X3b, MatrixUtils.RankHorizon(x, y));//d2=dist2(X3b,[x y]);
U = d2.PointMultiply(d2.Each(v => Math.Log(v + Epsilon)));
//Transformation(MatrixUtils.RankHorizon(x, y), U, axt, wxt, ayt, wyt, out fx, out fy);
var fxy = Transformation(MatrixUtils.RankHorizon(x, y), U, axt, wxt, ayt, wyt);
//disp('computing warped image...')
//V1w=griddata(reshape(fx,N1,N2),reshape(fy,N1,N2),V1,reshape(x,N1,N2),reshape(y,N1,N2));
Matrix V1w = Interpolation(
fxy.GetSubMatrix(0, fxy.Rows, 0, 1).Reshape(N1, N2),
fxy.GetSubMatrix(0, fxy.Rows, 1, 1).Reshape(N1, N2),
V1
);
#region 这个山寨插值方法会造成图像裂缝，用闭运算来尝试修补
Image<Gray, Byte> img = new Image<Gray, byte>(N2, N1);
for (int i = 0; i < N2; ++i) {
for (int j = 0; j < N1; ++j) {
img[i, j] = new Gray(V1w[i, j] * 255);
}
}
var see = new StructuringElementEx(new int[,] { { 1, 1, 1 }, { 1, 1, 1 }, { 1, 1, 1 } }, 1, 1);
//img = img.MorphologyEx(see, Emgu.CV.CvEnum.CV_MORPH_OP.CV_MOP_CLOSE, 1);
img = img.Dilate(1).Erode(1);
for (int i = 0; i < N2; ++i) {
for (int j = 0; j < N1; ++j) {
V1w[i, j] = img[i, j].Intensity / 255;
}
}
img.Dispose();
#endregion
timeused += timer.StopAndSay("图像变换和插值");
#endregion
//fz=find(isnan(V1w));
//V1w(fz)=0;
var ssd = (V2 - V1w).Each(v => v * v);//ssd=(V2-V1w).^2; %%%%%%SSD在这里
var ssd_global = ssd.SumAll();//ssd_global=sum(ssd(:));
Debug("ssd_global:{0}", ssd_global);
#region figure 5
if (display_flag) {
// figure(5)
// subplot(2,2,1)
// im(V1)
// subplot(2,2,2)
// im(V2)
// subplot(2,2,4)
// im(V1w)
// title('V1 after warping')
// subplot(2,2,3)
// im(V2-V1w)
// h=title(['SSD=' num2str(ssd_global)]);
// colormap(cmap)
}
#endregion
#region 窗口SSD比较
timer.Restart();
//%%%
//%%% windowed SSD comparison
//%%%
var wd = 2 * w + 1;//wd=2*w+1;
var win_fun = MatrixUtils.GaussianKernal(wd); //win_fun=gaussker(wd);
//% extract sets of blocks around each coordinate
//% first do 1st shape; need to use transformed coords.
var win_list_1 = Zeros(nsamp, wd * wd);//win_list_1=zeros(nsamp,wd^2);
for (int qq = 0; qq < nsamp; ++qq) {
int row_qq = (int)Xk[qq, 1],// row_qq=round(Xk(qq,2));
col_qq = (int)Xk[qq, 0];// col_qq=round(Xk(qq,1));
row_qq = Math.Max(w + 1, Math.Min(N1 - w - 1, row_qq));// row_qq=max(w+1,min(N1-w,row_qq));
col_qq = Math.Max(w + 1, Math.Min(N2 - w - 1, col_qq));// col_qq=max(w+1,min(N2-w,col_qq));
// tmp=V1w(row_qq-w:row_qq+w,col_qq-w:col_qq+w);
var tmp = V1w.GetSubMatrix(row_qq - w, w * 2 + 1, col_qq - w, w * 2 + 1);
tmp = win_fun.PointMultiply(tmp);// tmp=win_fun.*tmp;
// win_list_1(qq,:)=tmp(:)';
win_list_1.SetSubMatrix(qq, 1, 0, win_list_1.Columns, tmp.Reshape(1, tmp.Rows * tmp.Columns));
}
//% now do 2nd shape
var win_list_2 = Zeros(nsamp, wd * wd);//win_list_2=zeros(nsamp,wd^2);
for (int qq = 0; qq < nsamp; ++qq) {
int row_qq = (int)Y[qq, 1],// row_qq = round(Y(qq, 2));
col_qq = (int)Y[qq, 0];// col_qq = round(Y(qq, 1));
row_qq = Math.Max(w + 1, Math.Min(N1 - w - 1, row_qq));// row_qq=max(w+1,min(N1-w,row_qq));
col_qq = Math.Max(w + 1, Math.Min(N2 - w - 1, col_qq));// col_qq=max(w+1,min(N2-w,col_qq));
// tmp=V2(row_qq-w:row_qq+w,col_qq-w:col_qq+w)
var tmp = V2.GetSubMatrix(row_qq - w, w * 2 + 1, col_qq - w, w * 2 + 1);
tmp = win_fun.PointMultiply(tmp);// tmp=win_fun.*tmp;
win_list_2.SetSubMatrix(qq, 1, 0, win_list_2.Columns, tmp.Reshape(1, tmp.Rows * tmp.Columns));// win_list_2(qq,:)=tmp(:)';
}
var ssd_all = Dist2(win_list_1, win_list_2).Each(Math.Sqrt);//ssd_all=sqrt(dist2(win_list_1,win_list_2));
timeused += timer.StopAndSay("窗口SSD比较");
#endregion
#region 最后的KNN，不知道干嘛用
timer.Restart();
//%%%%%%% KNN在此
//% loop over nearest neighbors in both directions, project in
//% both directions, take maximum
double cost_1 = 0, cost_2 = 0;
//List<double> cost_1 = new List<double>(), cost_2 = new List<double>();
for (int qq = 0; qq < nsamp; ++qq) {
cost_1 += ssd_all[qq, min2[qq].Idx];// cost_1=cost_1+ssd_all(qq,b2(qq));
cost_2 += ssd_all[min1[qq].Idx, qq];// cost_2=cost_2+ssd_all(b1(qq),qq);
//cost_1.Add(ssd_all[qq, min2[qq].Idx]);
//cost_2.Add(ssd_all[min1[qq].Idx, qq]);
}
var ssd_local = (1.0 / nsamp) * Math.Max(cost_1, cost_2);
var ssd_local_avg = (1.0 / nsamp) * 0.5 * (cost_1 + cost_2);
//var ssd_local = (1.0 / nsamp) * Math.Max(cost_1.Average(), cost_2.Average());//ssd_local=(1/nsamp)*max(mean(cost_1),mean(cost_2));
//var ssd_local_avg = (1.0 / nsamp) * 0.5 * (cost_1.Average() + cost_2.Average());//ssd_local_avg=(1/nsamp)*0.5*(mean(cost_1)+mean(cost_2));
Debug("ssd_local:{0}", ssd_local);
Debug("ssd_local_avg:{0}", ssd_local_avg);
timeused += timer.StopAndSay("计算ssd_local");
#region 最后的组合图
//if display_flag
//% set(h,'string',['local SSD=' num2str(ssd_local) ', avg. local SSD=' num2str(ssd_local_avg)])
// set(h,'string',['local SSD=' num2str(ssd_local)])
//end
if (display_flag) {
Draw(V1, @"D:\Play Data\Iteration\结果\0-V1.bmp", "V1");
Draw(V2, @"D:\Play Data\Iteration\结果\1-V2.bmp", "V2");
Draw(V1w, @"D:\Play Data\Iteration\结果\2-V1w.bmp", "V1 after warping");
Draw(V2 - V1w, @"D:\Play Data\Iteration\结果\3-V2-V1w.bmp",
String.Format("local SSD={0:F8}", ssd_local_avg));
}
#endregion
#endregion
#endregion
var distance = 1.6 * ssd_local_avg + distance_sc + 0.3 * E; // 不知道最后的距离公式到底是什么
Debug("distance={0:F8}", distance);
return distance;
}
