/// <summary>
/// 计算文件名符合特定格式的文件名的图像序列的孔隙率
/// 默认情况下，白色是孔隙相，黑色是固体相，此时不需要对图像进行反相
/// example :
/// ComputeParameters.ComputePorosity(@".\result\", "{0:D4}.bmp", 10, 21, ref porosity);
/// </summary>
/// /// <param name="folder">文件夹名称</param>
/// <param name="pattern">文件名的格式</param>
/// <param name="startIndex">起始index</param>
/// <param name="endIndex">末尾index</param>
/// <param name="porosity">孔隙率</param>
/// <param name="needReverse">是否需要反相</param>
/// <returns></returns>
public static bool ComputePorosity(string folder, string pattern, int startIndex, int endIndex, ref double porosity, bool needReverse = false)
{
bool res = true;
string fn = "";
porosity = 0.0;
Matrix <double> pMat = new Matrix <double>(endIndex - startIndex + 1, 1);
Mat img;
for (int i = startIndex; i <= endIndex; i++)
{
fn = string.Format(folder + pattern, i);
img = CvInvoke.Imread(fn, Emgu.CV.CvEnum.LoadImageType.Grayscale);
if (img.IsEmpty)
{
res = false;
break;
}
if (needReverse)
{
CvInvoke.BitwiseNot(img, img);
}
pMat[i - startIndex, 0] = CvInvoke.CountNonZero(img) * 1.0 / (img.Cols * img.Rows);
porosity += pMat[i - startIndex, 0];
}
if (res)
{
DataReadWriteHelper.RecordInfo("porosity.txt", PackingSystemSetting.ResultDir, pMat, false);
}
return(res);
}
public static void FindMatch(Mat modelImage, Mat observedImage, out long matchTime, out VectorOfKeyPoint modelKeyPoints, out VectorOfKeyPoint observedKeyPoints, VectorOfVectorOfDMatch matches, out Mat mask, out Mat homography)
{
int k = 2;
double uniquenessThreshold = 0.80;
double hessianThresh = 100;
Stopwatch watch;
homography = null;
modelKeyPoints = new VectorOfKeyPoint();
observedKeyPoints = new VectorOfKeyPoint();
using (UMat uModelImage = modelImage.GetUMat(AccessType.Read))
using (UMat uObservedImage = observedImage.GetUMat(AccessType.Read))
{
SURF surfCPU = new SURF(hessianThresh);
SIFT siftCPU = new SIFT();
//extract features from the object image
UMat modelDescriptors = new UMat();
//surfCPU.DetectAndCompute(uModelImage, null, modelKeyPoints, modelDescriptors, false);
siftCPU.DetectAndCompute(uModelImage, null, modelKeyPoints, modelDescriptors, false);
watch = Stopwatch.StartNew();
// extract features from the observed image
UMat observedDescriptors = new UMat();
//surfCPU.DetectAndCompute(uObservedImage, null, observedKeyPoints, observedDescriptors, false);
siftCPU.DetectAndCompute(uObservedImage, null, observedKeyPoints, observedDescriptors, false);
BFMatcher matcher = new BFMatcher(DistanceType.L2);
matcher.Add(modelDescriptors);
matcher.KnnMatch(observedDescriptors, matches, k, null);
mask = new Mat(matches.Size, 1, DepthType.Cv8U, 1);
mask.SetTo(new MCvScalar(255));
Features2DToolbox.VoteForUniqueness(matches, uniquenessThreshold, mask);
//Features2DToolbox.VoteForUniqueness(matches, 1, mask);
int nonZeroCount = CvInvoke.CountNonZero(mask);
if (nonZeroCount >= 4)
{
nonZeroCount = Features2DToolbox.VoteForSizeAndOrientation(modelKeyPoints, observedKeyPoints,
matches, mask, 1.5, 20);
if (nonZeroCount >= 4)
{
homography = Features2DToolbox.GetHomographyMatrixFromMatchedFeatures(modelKeyPoints,
observedKeyPoints, matches, mask, 2);
}
}
watch.Stop();
}
matchTime = watch.ElapsedMilliseconds;
}
public static void FindMatch(
Mat modelImage,
Mat observedImage,
out VectorOfKeyPoint modelKeyPoints,
out VectorOfKeyPoint observedKeyPoints,
VectorOfVectorOfDMatch matches,
out Mat mask,
out Mat homography)
{
int k = 9;
double uniquenessThreshold = 0.80;
Stopwatch watch;
homography = null;
modelKeyPoints = new VectorOfKeyPoint();
observedKeyPoints = new VectorOfKeyPoint();
using (UMat uModelImage = modelImage.GetUMat(AccessType.Read))
using (UMat uObservedImage = observedImage.GetUMat(AccessType.Read))
{
KAZE featureDetector = new KAZE();
//extract features from the object image
Mat modelDescriptors = new Mat();
featureDetector.DetectAndCompute(uModelImage, null, modelKeyPoints, modelDescriptors, false);
watch = Stopwatch.StartNew();
// extract features from the observed image
Mat observedDescriptors = new Mat();
featureDetector.DetectAndCompute(uObservedImage, null, observedKeyPoints, observedDescriptors, false);
using (Emgu.CV.Flann.LinearIndexParams ip = new Emgu.CV.Flann.LinearIndexParams())
using (Emgu.CV.Flann.SearchParams sp = new SearchParams())
using (DescriptorMatcher matcher = new FlannBasedMatcher(ip, sp))
{
matcher.Add(modelDescriptors);
matcher.KnnMatch(observedDescriptors, matches, k, null);
mask = new Mat(matches.Size, 1, DepthType.Cv8U, 1);
mask.SetTo(new MCvScalar(255));
Features2DToolbox.VoteForUniqueness(matches, uniquenessThreshold, mask);
int nonZeroCount = CvInvoke.CountNonZero(mask);
if (nonZeroCount >= 4)
{
nonZeroCount = Features2DToolbox.VoteForSizeAndOrientation(modelKeyPoints, observedKeyPoints,
matches, mask, 1.5, 20);
if (nonZeroCount >= 4)
{
homography = Features2DToolbox.GetHomographyMatrixFromMatchedFeatures(modelKeyPoints,
observedKeyPoints, matches, mask, 2);
}
}
}
watch.Stop();
}
}
private static void ComputeHomographyAndValidate(ref VectorOfKeyPoint trackedFeatures, ref VectorOfKeyPoint bootstrapKp, out Matrix <double> homographyMatrix)
{
//verify features with a homography
var inlierMask = new VectorOfByte();
var homography = new Mat();
if (trackedFeatures.Size > 4)
{
CvInvoke.FindHomography(Utils.GetPointsVector(trackedFeatures), Utils.GetPointsVector(bootstrapKp), homography, HomographyMethod.Ransac, RansacThreshold,
inlierMask);
}
homographyMatrix = new Matrix <double>(homography.Rows, homography.Cols, homography.DataPointer);
int inliersNum = CvInvoke.CountNonZero(inlierMask);
if (inliersNum != trackedFeatures.Size && inliersNum >= 4 && !homography.IsEmpty)
{
Utils.KeepVectorsByStatus(ref trackedFeatures, ref bootstrapKp, inlierMask);
}
else if (inliersNum < 10)
{
throw new Exception("Not enough features survived homography.");
}
}
public static Bitmap Skelatanize(Bitmap image)
{
Image <Gray, byte> imgOld = new Image <Gray, byte>(image);
Image <Gray, byte> img2 = (new Image <Gray, byte>(imgOld.Width, imgOld.Height, new Gray(255))).Sub(imgOld);
Image <Gray, byte> eroded = new Image <Gray, byte>(img2.Size);
Image <Gray, byte> temp = new Image <Gray, byte>(img2.Size);
Image <Gray, byte> skel = new Image <Gray, byte>(img2.Size);
skel.SetValue(0);
CvInvoke.Threshold(img2, img2, 127, 256, 0);
var element = CvInvoke.GetStructuringElement(ElementShape.Cross, new Size(3, 3), new Point(-1, -1));
bool done = false;
while (!done)
{
CvInvoke.Erode(img2, eroded, element, new Point(-1, -1), 1, BorderType.Reflect, default(MCvScalar));
CvInvoke.Dilate(eroded, temp, element, new Point(-1, -1), 1, BorderType.Reflect, default(MCvScalar));
CvInvoke.Subtract(img2, temp, temp);
CvInvoke.BitwiseOr(skel, temp, skel);
eroded.CopyTo(img2);
if (CvInvoke.CountNonZero(img2) == 0)
{
done = true;
}
}
return(skel.Bitmap);
}
private static int[] GetAdjust(Image <Gray, byte> ImgCap, Image <Gray, byte> ImgGerber, int RangeX, int RangeY)
{
int x_ok = 0;
int y_ok = 0;
double diff = 2448 * 2018;
for (int x = -RangeX; x < RangeX; x++)
{
for (int y = -RangeY; y < RangeY; y++)
{
using (Image <Gray, byte> imgTransform = ImageProcessingUtils.ImageTransformation(ImgCap.Copy(), x, y))
{
CvInvoke.AbsDiff(imgTransform, ImgGerber, imgTransform);
int count = CvInvoke.CountNonZero(imgTransform);
if (count < diff)
{
diff = count;
x_ok = x;
y_ok = y;
}
}
}
}
return(new int[] { x_ok, y_ok });
}
private static void GetCenterPointForDatum(clsPoint pt, double[,] model, ARParam arParams, int[] vp, Image <Gray, byte> grayImage, ref Emgu.CV.Util.VectorOfPointF centerPoints)
{
var cpt = ModelToImageSpace(arParams, model, pt);
var halfSquare = GetSquareForDatum(arParams, model, pt);
if (halfSquare < 8)
{
return;
}
if (cpt.x - halfSquare < 0 || cpt.x + halfSquare > vp[2] || cpt.y - halfSquare <0 || cpt.y + halfSquare> vp[3])
{
return;
}
var rect = new Rectangle((int)cpt.x - halfSquare, (int)cpt.y - halfSquare, 2 * halfSquare, 2 * halfSquare);
var region = new Mat(grayImage.Mat, rect);
var binaryRegion = region.Clone();
double otsuThreshold = CvInvoke.Threshold(region, binaryRegion, 0.0, 255.0, Emgu.CV.CvEnum.ThresholdType.Otsu);
int nonzero = CvInvoke.CountNonZero(binaryRegion);
var square = 4 * halfSquare * halfSquare;
if (nonzero > square * 0.2f && nonzero < square * 0.8f)
{
centerPoints.Push(new PointF[] { new PointF((float)cpt.X, (float)cpt.Y) });
}
}
private void FindMatch(Mat observedImage)
{
int k = 2;
mask = new Mat();
homography = null;
matches = new VectorOfVectorOfDMatch();
uObservedImage = observedImage.GetUMat(AccessType.ReadWrite);
// extract features from the observed image
ORBCPU.DetectAndCompute(uObservedImage, null, observedKeyPoints, observedDescriptors, false);
matcher = new BFMatcher(DistanceType.L2);
matcher.Add(objDescriptors);
if (objDescriptors.Size.Height > 3 && observedDescriptors.Size.Height > 3)
{
matcher.KnnMatch(observedDescriptors, matches, k, null);
mask = new Mat(matches.Size, 1, DepthType.Cv8U, 1);
mask.SetTo(new MCvScalar(255));
Features2DToolbox.VoteForUniqueness(matches, 0.8, mask);
int nonZeroCount = CvInvoke.CountNonZero(mask);
if (nonZeroCount >= 4)
{
//nonZeroCount = Features2DToolbox.VoteForSizeAndOrientation(objKeyPoints, observedKeyPoints,
//matches, mask, 1, 2);
if (nonZeroCount >= 4)
{
homography = Features2DToolbox.GetHomographyMatrixFromMatchedFeatures(objKeyPoints,
observedKeyPoints, matches, mask, 3);
}
}
}
}
public static void GetMatches(VectorOfKeyPoint imageKeypoints, IInputArray imageDescriptors, VectorOfKeyPoint patternKeypoints, IInputArray patternDescriptors, out VectorOfVectorOfDMatch matches, out Mat homography)
{
int k = 2;
double uniquenessThreshold = 0.8;
homography = null;
matches = new VectorOfVectorOfDMatch();
var matcher = new BFMatcher(DistanceType.L2);
matcher.Add(patternDescriptors);
matcher.KnnMatch(imageDescriptors, matches, k, null);
var mask = new Mat(matches.Size, 1, DepthType.Cv8U, 1);
mask.SetTo(new MCvScalar(255));
Features2DToolbox.VoteForUniqueness(matches, uniquenessThreshold, mask);
int nonZeroCount = CvInvoke.CountNonZero(mask);
if (nonZeroCount >= 4)
{
nonZeroCount = Features2DToolbox.VoteForSizeAndOrientation(patternKeypoints, imageKeypoints, matches, mask, 1.5, 20);
if (nonZeroCount >= 4)
{
homography = Features2DToolbox.GetHomographyMatrixFromMatchedFeatures(patternKeypoints, imageKeypoints, matches, mask, 2);
}
}
}
/// <summary>
/// 计算文件夹中的所有的bmp文件组成的图像序列的孔隙率
/// 默认情况下，白色是孔隙相，黑色是固体相，此时不需要对图像进行反相
/// example :
/// ComputeParameters.ComputePorosity(dlg.SelectedPath, ref porosity, true)
/// </summary>
/// <param name="folder">文件夹名称</param>
/// <param name="porosity">孔隙率</param>
/// <param name="needReverse">是否需要反相</param>
/// <returns></returns>
public static bool ComputePorosity(string folder, ref double porosity, bool needReverse = false)
{
bool res = true;
porosity = 0.0;
if (Directory.Exists(folder))
{
var files = Directory.GetFiles(folder, "*.bmp");
Matrix <double> pMat = new Matrix <double>(files.Count(), 1);
Mat img;
int index = 0;
foreach (var file in files)
{
img = CvInvoke.Imread(file, Emgu.CV.CvEnum.LoadImageType.Grayscale);
if (needReverse)
{
CvInvoke.BitwiseNot(img, img);
}
pMat[index++, 0] = CvInvoke.CountNonZero(img) * 1.0 / (img.Cols * img.Rows);
porosity += pMat[index - 1, 0];
}
porosity /= files.Count();
DataReadWriteHelper.RecordInfo("porosity.txt", PackingSystemSetting.ResultDir, pMat, false);
}
else
{
res = false;
}
return(res);
}
public void TestConvolutionAndLaplace()
{
Mat image = new Mat(new Size(300, 400), DepthType.Cv8U, 1);
CvInvoke.Randu(image, new MCvScalar(0.0), new MCvScalar(255.0));
Mat laplacian = new Mat();
CvInvoke.Laplacian(image, laplacian, DepthType.Cv8U);
float[,] k = { { 0, 1, 0 },
{ 1, -4, 1 },
{ 0, 1, 0 } };
ConvolutionKernelF kernel = new ConvolutionKernelF(k);
Mat convoluted = new Mat(image.Size, DepthType.Cv8U, 1);
CvInvoke.Filter2D(image, convoluted, kernel, kernel.Center);
Mat absDiff = new Mat();
CvInvoke.AbsDiff(laplacian, convoluted, absDiff);
int nonZeroPixelCount = CvInvoke.CountNonZero(absDiff);
EmguAssert.IsTrue(nonZeroPixelCount == 0);
//Emgu.CV.UI.ImageViewer.Show(absDiff);
}
public float getRegionSkinPercentage(Image <Gray, Byte> input, float cols, float rows)
{
float area = cols * rows;
int white = CvInvoke.CountNonZero(input);
float skinPerc = (white / area);
return(skinPerc);
}
//public static Highlighter[] HighlightMatches(Rectangle[] Matches)
//{
// var result = new List<Highlighter>();
// foreach (var m in Matches)
// {
// result.Add(new Highlighter(m, System.Drawing.Color.Red));
// }
// return result.ToArray();
//}
//public static void HighlightMatches(Rectangle[] Matches, TimeSpan Duration)
//{
// foreach (var Match in Matches)
// {
// Task.Factory.StartNew(() =>
// {
// var h2 = new Highlighter(Match, System.Drawing.Color.Red);
// System.Threading.Thread.Sleep(Duration);
// h2.remove();
// });
// }
//}
//public static void HighlightMatch(Rectangle Match, bool Blocking, Color Color, TimeSpan Duration)
//{
// if (!Blocking)
// {
// Task.Factory.StartNew(() =>
// {
// var h2 = new Highlighter(Match, System.Drawing.Color.Red);
// System.Threading.Thread.Sleep(Duration);
// h2.remove();
// System.Windows.Forms.Application.DoEvents();
// });
// return;
// }
// var h = new Highlighter(Match, System.Drawing.Color.Red);
// System.Threading.Thread.Sleep(Duration);
// h.remove();
// System.Windows.Forms.Application.DoEvents();
//}
//https://www.meridium.se/sv/blogg/imagematching-using-opencv/
public static void FindMatch(Mat modelImage, Mat observedImage, out VectorOfKeyPoint modelKeyPoints, out VectorOfKeyPoint observedKeyPoints, VectorOfVectorOfDMatch matches, out Mat mask, out Mat homography, out long score)
{
int k = 2;
double uniquenessThreshold = 0.80;
homography = null;
modelKeyPoints = new VectorOfKeyPoint();
observedKeyPoints = new VectorOfKeyPoint();
using (UMat uModelImage = modelImage.GetUMat(AccessType.Read))
using (UMat uObservedImage = observedImage.GetUMat(AccessType.Read))
{
var featureDetector = new Emgu.CV.Features2D.KAZE();
Mat modelDescriptors = new Mat();
featureDetector.DetectAndCompute(uModelImage, null, modelKeyPoints, modelDescriptors, false);
Mat observedDescriptors = new Mat();
featureDetector.DetectAndCompute(uObservedImage, null, observedKeyPoints, observedDescriptors, false);
// KdTree for faster results / less accuracy
using (var ip = new Emgu.CV.Flann.KdTreeIndexParams())
using (var sp = new Emgu.CV.Flann.SearchParams())
using (var matcher = new Emgu.CV.Features2D.FlannBasedMatcher(ip, sp))
{
matcher.Add(modelDescriptors);
matcher.KnnMatch(observedDescriptors, matches, k, null);
mask = new Mat(matches.Size, 1, DepthType.Cv8U, 1);
mask.SetTo(new MCvScalar(255));
Emgu.CV.Features2D.Features2DToolbox.VoteForUniqueness(matches, uniquenessThreshold, mask);
// Calculate score based on matches size
// ---------------------------------------------->
score = 0;
for (int i = 0; i < matches.Size; i++)
{
// if (mask.GetData(i)[0] == 0) continue;
foreach (var e in matches[i].ToArray())
{
++score;
}
}
// <----------------------------------------------
int nonZeroCount = CvInvoke.CountNonZero(mask);
if (nonZeroCount >= 4)
{
nonZeroCount = Emgu.CV.Features2D.Features2DToolbox.VoteForSizeAndOrientation(modelKeyPoints, observedKeyPoints, matches, mask, 1.5, 20);
if (nonZeroCount >= 4)
{
homography = Emgu.CV.Features2D.Features2DToolbox.GetHomographyMatrixFromMatchedFeatures(modelKeyPoints, observedKeyPoints, matches, mask, 2);
}
}
}
}
}
public static int FindMatch2(Mat modelImage, TemplateContainer.ImageData template, out long matchTime, out VectorOfKeyPoint modelKeyPoints, out VectorOfKeyPoint observedKeyPoints, VectorOfVectorOfDMatch matches, out Mat mask, out Mat homography)
{
Stopwatch watch;
homography = null;
BriefDescriptorExtractor descriptor = new BriefDescriptorExtractor();
modelKeyPoints = new VectorOfKeyPoint();
observedKeyPoints = new VectorOfKeyPoint();
using (UMat uModelImage = modelImage.GetUMat(AccessType.Read))
//using (UMat uObservedImage = template.image.Mat.GetUMat(AccessType.Read))
{
//extract features from the object image
Mat modelDescriptors = new Mat();
featureDetector.DetectAndCompute(uModelImage, null, modelKeyPoints, modelDescriptors, false);
watch = Stopwatch.StartNew();
// extract features from the observed image
//featureDetector.DetectAndCompute(uObservedImage, null, observedKeyPoints, observedDescriptors, false);
observedKeyPoints = template.keyPointsSurf;
observedDescriptors = template.descriptorSurf;
// Bruteforce, slower but more accurate
// You can use KDTree for faster matching with slight loss in accuracy
using (Emgu.CV.Flann.LinearIndexParams ip = new Emgu.CV.Flann.LinearIndexParams())
using (Emgu.CV.Flann.SearchParams sp = new SearchParams())
using (DescriptorMatcher matcher = new FlannBasedMatcher(ip, sp))
{
matcher.Add(modelDescriptors);
matcher.KnnMatch(observedDescriptors, matches, k, null);
mask = new Mat(matches.Size, 1, DepthType.Cv8U, 1);
mask.SetTo(new MCvScalar(255));
Features2DToolbox.VoteForUniqueness(matches, uniquenessThreshold, mask);
nonZeroCount = CvInvoke.CountNonZero(mask);
if (nonZeroCount >= 10)
{
nonZeroCount = Features2DToolbox.VoteForSizeAndOrientation(modelKeyPoints, observedKeyPoints,
matches, mask, 1.8, 18);
if (nonZeroCount >= 12)
{
homography = Features2DToolbox.GetHomographyMatrixFromMatchedFeatures(modelKeyPoints,
observedKeyPoints, matches, mask, 2);
}
}
}
watch.Stop();
}
matchTime = watch.ElapsedMilliseconds;
return(nonZeroCount);
}
private float ImageWhiteRatio(Mat thresImage)
{
if (thresImage.Depth != DepthType.Cv8U)
{
throw new Exception("Изображение должно быть черно-белым");
}
int whiteCount = CvInvoke.CountNonZero(thresImage);
int imagePixelCount = thresImage.Rows * thresImage.Cols;
float whiteRatio = (float)(whiteCount) / (float)imagePixelCount;
return(whiteRatio);
}
public static List <ImageSearchResult> SearchImageForObjects(WorldObject modelObject, string imageToSearch)
{
int k = 2;
double uniquenessThreshold = 0.8;
double hessianThresh = 300;
int nonZeroThreshold = 10;
ObjectFeatures targetImageFeatures = DetectFeatures_Brisk(imageToSearch);
Mat mask;
List <ImageSearchResult> searchResults = new List <ImageSearchResult>();
foreach (ObjectView view in modelObject.Views)
{
if (view == null)
{
continue;
}
VectorOfVectorOfDMatch matches = new VectorOfVectorOfDMatch();
BFMatcher matcher = new BFMatcher(DistanceType.L2);
matcher.Add(view.Features.Descriptors);
matcher.KnnMatch(targetImageFeatures.Descriptors, matches, 2, null);
mask = new Mat(matches.Size, 1, DepthType.Cv8U, 1);
mask.SetTo(new MCvScalar(255));
Features2DToolbox.VoteForUniqueness(matches, uniquenessThreshold, mask);
int nonZeroCount = CvInvoke.CountNonZero(mask);
if (nonZeroCount >= nonZeroThreshold)
{
nonZeroCount = Features2DToolbox.VoteForSizeAndOrientation(view.Features.KeyPoints,
targetImageFeatures.KeyPoints, matches, mask, 1.5, 20);
if (nonZeroCount >= nonZeroThreshold)
{
Mat homography = Features2DToolbox.GetHomographyMatrixFromMatchedFeatures(view.Features.KeyPoints,
targetImageFeatures.KeyPoints, matches, mask, 2);
searchResults.Add(new ImageSearchResult(view, homography, matches, targetImageFeatures, mask));
}
}
}
return(searchResults);
}
public static Bitmap Skelatanize(Bitmap image2)
{
Bitmap image = new Bitmap(image2);
for (int y = 0; (y <= (image.Height - 1)); y++)
{
for (int x = 0; (x <= (image.Width - 1)); x++)
{
Color inv = image.GetPixel(x, y);
inv = Color.FromArgb(255, (255 - inv.R), (255 - inv.G), (255 - inv.B));
image.SetPixel(x, y, inv);
}
}
Image <Gray, byte> imgOld = new Image <Gray, byte>(image);
Image <Gray, byte> img2 = (new Image <Gray, byte>(imgOld.Width, imgOld.Height, new Gray(255))).Sub(imgOld);
Image <Gray, byte> eroded = new Image <Gray, byte>(img2.Size);
Image <Gray, byte> temp = new Image <Gray, byte>(img2.Size);
Image <Gray, byte> skel = new Image <Gray, byte>(img2.Size);
skel.SetValue(0);
CvInvoke.Threshold(img2, img2, 127, 255, 0);
var element = CvInvoke.GetStructuringElement(ElementShape.Cross, new Size(3, 3), new Point(-1, -1));
bool done = false;
while (!done)
{
CvInvoke.Erode(img2, eroded, element, new Point(-1, -1), 1, BorderType.Reflect, default(MCvScalar));
CvInvoke.Dilate(eroded, temp, element, new Point(-1, -1), 1, BorderType.Reflect, default(MCvScalar));
CvInvoke.Subtract(img2, temp, temp);
CvInvoke.BitwiseOr(skel, temp, skel);
eroded.CopyTo(img2);
if (CvInvoke.CountNonZero(img2) == 0)
{
done = true;
}
}
Bitmap image3 = new Bitmap(skel.Bitmap);
for (int y = 0; (y <= (image.Height - 1)); y++)
{
for (int x = 0; (x <= (image.Width - 1)); x++)
{
Color inv = image.GetPixel(x, y);
inv = Color.FromArgb(255, (255 - inv.R), (255 - inv.G), (255 - inv.B));
image.SetPixel(x, y, inv);
}
}
return(image3);
}
public float getImageSkinPercentage(Image <Gray, Byte> input)
{
float area = input.Cols * input.Rows;
int white = CvInvoke.CountNonZero(input);
float skinPerc = (white / area);
if (float.IsNaN(skinPerc))
{
skinPerc = 0;
}
return(skinPerc);
}
/// <summary>
///
/// </summary>
/// <param name="observedKeyPoints"></param>
/// <param name="modelKeyPoint"></param>
/// <returns></returns>
public static VectorOfPoint Matching(VectorOfKeyPoint observedKeyPoints, VectorOfKeyPoint modelKeyPoints, Mat observedDescriptors, Mat modelDescriptors, Size modelSize)
{
KAZE featureDetector = new KAZE();
using (var ip = new LinearIndexParams())
using (var sp = new SearchParams())
using (var matcher = new FlannBasedMatcher(ip, sp))
using (var matches = new VectorOfVectorOfDMatch())
{
Mat homography = new Mat();
matcher.Add(modelDescriptors);
matcher.KnnMatch(observedDescriptors, matches, 2, null);
var mask = new Mat(matches.Size, 1, DepthType.Cv8U, 1);
mask.SetTo(new MCvScalar(255));
Features2DToolbox.VoteForUniqueness(matches, 0.80, mask);
int nonZeroCount = CvInvoke.CountNonZero(mask);
if (nonZeroCount >= 4)
{
nonZeroCount = Features2DToolbox.VoteForSizeAndOrientation(modelKeyPoints, observedKeyPoints, matches, mask, 1.5, 20);
if (nonZeroCount >= 4)
{
homography = Features2DToolbox.GetHomographyMatrixFromMatchedFeatures(modelKeyPoints, observedKeyPoints, matches, mask, 2);
}
}
if (homography != null && !homography.Size.IsEmpty)
{
Rectangle rect = new Rectangle(Point.Empty, modelSize);
PointF[] pts = new PointF[]
{
new PointF(rect.Left, rect.Bottom),
new PointF(rect.Right, rect.Bottom),
new PointF(rect.Right, rect.Top),
new PointF(rect.Left, rect.Top)
};
pts = CvInvoke.PerspectiveTransform(pts, homography);
Point[] points = Array.ConvertAll <PointF, Point>(pts, Point.Round);
return(new VectorOfPoint(points));
}
else
{
return(new VectorOfPoint());
}
}
}
private static bool IntersectsContour(Point[] Cnt1, Point[] Cnt2, Rectangle BoudingCnt1)
{
bool intersect = false;
bool canIntersect = false;
Point[] cntPTranform1 = new Point[Cnt1.Length];
Point[] cntPTranform2 = new Point[Cnt2.Length];
for (int i = 0; i < Cnt1.Length; i++)
{
cntPTranform1[i] = new Point(Cnt1[i].X - BoudingCnt1.X, Cnt1[i].Y - BoudingCnt1.Y);
}
for (int i = 0; i < Cnt2.Length; i++)
{
cntPTranform2[i] = new Point(Cnt2[i].X - BoudingCnt1.X, Cnt2[i].Y - BoudingCnt1.Y);
if ((cntPTranform2[i].X > 0 && cntPTranform2[i].X < BoudingCnt1.Width) ||
(cntPTranform2[i].Y > 0 && cntPTranform2[i].Y < BoudingCnt1.Height))
{
canIntersect = true;
}
}
if (canIntersect)
{
using (VectorOfPoint cnt1 = new VectorOfPoint(cntPTranform1))
using (VectorOfPoint cnt2 = new VectorOfPoint(cntPTranform2))
using (VectorOfVectorOfPoint contour1 = new VectorOfVectorOfPoint())
using (VectorOfVectorOfPoint contour2 = new VectorOfVectorOfPoint())
using (Image <Gray, byte> image1 = new Image <Gray, byte>(BoudingCnt1.Size))
using (Image <Gray, byte> image2 = new Image <Gray, byte>(BoudingCnt1.Size))
using (Image <Gray, byte> imageAnd = new Image <Gray, byte>(BoudingCnt1.Size))
{
contour1.Push(cnt1);
contour2.Push(cnt2);
CvInvoke.DrawContours(image1, contour1, -1, new MCvScalar(255), -1);
CvInvoke.DrawContours(image2, contour2, -1, new MCvScalar(255), -1);
CvInvoke.BitwiseAnd(image1, image2, imageAnd);
int count = CvInvoke.CountNonZero(imageAnd);
if (count > 0)
{
intersect = true;
}
//CvInvoke.Imshow("image1", image1);
//CvInvoke.Imshow("image2", image2);
//CvInvoke.Imshow("imageAnd", imageAnd);
//CvInvoke.WaitKey(0);
//Console.WriteLine("go");
}
}
return(intersect);
}
/// <summary>
///
///
/// TODO: thresholds must be set
/// </summary>
/// <param name="model"></param>
/// <param name="imageToSearch"></param>
/// <returns></returns>
public static bool SearchImageForObjects(List <ObjectFeatures> model, Bitmap image)
{
int k = 2;
double uniquenessThreshold = 0.8;
double hessianThresh = 300;
ObjectFeatures targetImageFeatures = DetectFeatures(image);
Mat mask;
VectorOfVectorOfDMatch matches = new VectorOfVectorOfDMatch();
BFMatcher matcher = new BFMatcher(DistanceType.L2);
foreach (ObjectFeatures of in model)
{
matcher.Add(of.Descriptors);
matcher.KnnMatch(targetImageFeatures.Descriptors, matches, 2, null);
mask = new Mat(matches.Size, 1, DepthType.Cv8U, 1);
mask.SetTo(new MCvScalar(255));
Features2DToolbox.VoteForUniqueness(matches, uniquenessThreshold, mask);
int nonZeroCount = CvInvoke.CountNonZero(mask);
if (nonZeroCount >= 4)
{
nonZeroCount = Features2DToolbox.VoteForSizeAndOrientation(of.KeyPoints,
targetImageFeatures.KeyPoints, matches, mask, 1.5, 20);
if (nonZeroCount >= 4)
{
return(true);
/*
* Mat homography = Features2DToolbox.GetHomographyMatrixFromMatchedFeatures(view.Features.KeyPoints,
* targetImageFeatures.KeyPoints, matches, mask, 2);
*
* searchResults.Add(new ImageSearchResult(view, homography, matches));
*/
}
}
}
return(false);
}
public static void FindMatchWM(Mat modelImage, Mat observedImage, out long matchTime, out VectorOfKeyPoint modelKeyPoints, out VectorOfKeyPoint observedKeyPoints, VectorOfVectorOfDMatch matches, out Mat mask, out Mat homography, Feature2D computer, Feature2D detector)
{
Stopwatch watch;
modelKeyPoints = new VectorOfKeyPoint(); // точки на модели
observedKeyPoints = new VectorOfKeyPoint(); // точки на большем изображении
homography = null;
int k = 2;
using (Mat uModelImage = modelImage.Clone())
using (Mat uObservedImage = observedImage.Clone())
{
//получаем дескрипторы из первого изображения
Mat modelDescriptors = new Mat();
DetectAndCompute(uModelImage, out modelKeyPoints, out modelDescriptors, detector, computer);
watch = Stopwatch.StartNew();
// ... из второго изображения
Mat observedDescriptors = new Mat();
DetectAndCompute(uObservedImage, out observedKeyPoints, out observedDescriptors, detector, computer);
BFMatcher matcher = new BFMatcher(DistanceType.L2); // "сравниватель" дескрипторов на 2-х изображениях
matcher.Add(modelDescriptors);
matcher.KnnMatch(observedDescriptors, matches, k, null); // сравнение
mask = new Mat(matches.Size, 1, DepthType.Cv8U, 1);
mask.SetTo(new MCvScalar(255));
Features2DToolbox.VoteForUniqueness(matches, 0.8, mask); // построениии маски (см ниже)
int nonZeroCount = CvInvoke.CountNonZero(mask);
if (nonZeroCount >= 4)
{
nonZeroCount = Features2DToolbox.VoteForSizeAndOrientation(modelKeyPoints, observedKeyPoints,
matches, mask, 1.5, 20);
if (nonZeroCount >= 4)
{
homography = Features2DToolbox.GetHomographyMatrixFromMatchedFeatures(modelKeyPoints, // получение предположительной зоны, куда должна встать модель
observedKeyPoints, matches, mask, 2);
}
}
watch.Stop();
}
matchTime = watch.ElapsedMilliseconds;
}
public void FindMatch(Image <Gray, byte> modelImage, Image <Gray, byte> observedImage, double hessianThresh, int k,
double uniquenessThreshold, VectorOfVectorOfDMatch matches, out VectorOfKeyPoint modelKeyPoints,
out VectorOfKeyPoint observedKeyPoints, out Mat mask, out Mat homography)
{
homography = null;
modelKeyPoints = new VectorOfKeyPoint();
observedKeyPoints = new VectorOfKeyPoint();
CudaSURFDetector surfCuda = new CudaSURFDetector((float)hessianThresh);
using (GpuMat gpuModelImage = new GpuMat(modelImage))
//extract features from the object image
using (GpuMat gpuModelKeyPoints = surfCuda.DetectKeyPointsRaw(gpuModelImage, null))
using (
GpuMat gpuModelDescriptors = surfCuda.ComputeDescriptorsRaw(gpuModelImage, null, gpuModelKeyPoints))
using (CudaBFMatcher matcher = new CudaBFMatcher(DistanceType.L2))
{
surfCuda.DownloadKeypoints(gpuModelKeyPoints, modelKeyPoints);
// extract features from the observed image
using (GpuMat gpuObservedImage = new GpuMat(observedImage))
using (GpuMat gpuObservedKeyPoints = surfCuda.DetectKeyPointsRaw(gpuObservedImage, null))
using (
GpuMat gpuObservedDescriptors = surfCuda.ComputeDescriptorsRaw(gpuObservedImage, null,
gpuObservedKeyPoints))
{
matcher.KnnMatch(gpuObservedDescriptors, gpuModelDescriptors, matches, k);
surfCuda.DownloadKeypoints(gpuObservedKeyPoints, observedKeyPoints);
mask = new Mat(matches.Size, 1, DepthType.Cv8U, 1);
mask.SetTo(new MCvScalar(255));
Features2DToolbox.VoteForUniqueness(matches, uniquenessThreshold, mask);
int nonZeroCount = CvInvoke.CountNonZero(mask);
if (nonZeroCount >= 4)
{
nonZeroCount = Features2DToolbox.VoteForSizeAndOrientation(modelKeyPoints, observedKeyPoints,
matches, mask, 1.5, 20);
if (nonZeroCount >= 4)
{
homography = Features2DToolbox.GetHomographyMatrixFromMatchedFeatures(modelKeyPoints,
observedKeyPoints, matches, mask, 2);
}
}
}
}
}
public static void FindMatch(string pageFile, string templateFile)
{
Image <Rgb, byte> page = getPreprocessedImage(pageFile);
Image <Rgb, byte> template = getPreprocessedImage(templateFile);
var detector = new ORBDetector();
VectorOfKeyPoint templateKeyPoints = new VectorOfKeyPoint();
Mat templateDescriptors = new Mat();
detector.DetectAndCompute(template, null, templateKeyPoints, templateDescriptors, false);
VectorOfKeyPoint pageKeyPoints = new VectorOfKeyPoint();
Mat pageDescriptors = new Mat();
detector.DetectAndCompute(page, null, pageKeyPoints, pageDescriptors, false);
using (var matcher = new BFMatcher(DistanceType.L1))
{
matcher.Add(templateDescriptors);
VectorOfVectorOfDMatch matches = new VectorOfVectorOfDMatch();
//VectorOfDMatch matches2 = new VectorOfDMatch();
//matcher.Match(pageDescriptors, matches2);
matcher.KnnMatch(pageDescriptors, matches, 2, null);
Mat mask = new Mat(matches.Size, 1, DepthType.Cv8U, 1);
mask.SetTo(new MCvScalar(255));
Features2DToolbox.VoteForUniqueness(matches, 0.8, mask);
Mat homography = new Mat();
int nonZeroCount = CvInvoke.CountNonZero(mask);
if (nonZeroCount >= 4)
{
nonZeroCount = Features2DToolbox.VoteForSizeAndOrientation(templateKeyPoints, pageKeyPoints, matches, mask, 1.5, 20);
if (nonZeroCount >= 4)
{
homography = Features2DToolbox.GetHomographyMatrixFromMatchedFeatures(templateKeyPoints, pageKeyPoints, matches, mask, 2);
}
}
Mat result = new Mat();
Features2DToolbox.DrawMatches(template, templateKeyPoints, page, pageKeyPoints, matches, result, new MCvScalar(0, 255, 0), new MCvScalar(255, 0, 0), mask, Features2DToolbox.KeypointDrawType.NotDrawSinglePoints);
//Features2DToolbox.DrawMatches(template, templateKeyPoints, page, pageKeyPoints, matches2, result, new MCvScalar(0, 255, 0), new MCvScalar(255, 0, 0), null, Features2DToolbox.KeypointDrawType.NotDrawSinglePoints);
MainForm.This.PageBox.Image = result.ToBitmap();
}
}
public void TestMatrixSubtract()
{
Matrix <float> f = new Matrix <float>(600, 480);
//set the value to 300
f.SetValue(new MCvScalar(300));
f -= 10;
using (ScalarArray sa = new ScalarArray(290))
using (Mat absDiff = new Mat())
{
//calculate the different of the value in f mat with 290
CvInvoke.AbsDiff(f, sa, absDiff);
int nonZeroCount = CvInvoke.CountNonZero(absDiff);
//Console.WriteLine(String.Format("number of elements that is not 290: {0}", nonZeroCount));
}
}
public IDrawer FindMatch(KeyFrame keyFrame, Image <Bgr, Byte> observedImage, List <KeyFrame> keyframes = null)
{
if (keyFrame.KeyPoints == null)
{
keyFrame.KeyPoints = new VectorOfKeyPoint(CPU.Detect(keyFrame.Frame));
}
if (keyFrame.Descriptors == null)
{
keyFrame.Descriptors = new Mat();
descriptor.Compute(keyFrame.Frame, keyFrame.KeyPoints, keyFrame.Descriptors);
}
// extract features from the observed image
observedKeyPoints = new VectorOfKeyPoint(CPU.Detect(observedImage));
descriptor.Compute(observedImage, observedKeyPoints, observedDescriptors);
matcher.Add(keyFrame.Descriptors);
matcher.KnnMatch(observedDescriptors, matches, k, null);
mask = new Mat(matches.Size, 1, DepthType.Cv8U, 1);
mask.SetTo(new MCvScalar(255));
Features2DToolbox.VoteForUniqueness(matches, uniquenessThreshold, mask);
int nonZeroCount = CvInvoke.CountNonZero(mask);
if (nonZeroCount >= 4)
{
nonZeroCount = Features2DToolbox.VoteForSizeAndOrientation(keyFrame.KeyPoints, observedKeyPoints,
matches, mask, 1.5, 20);
if (nonZeroCount >= 4)
{
homography = Features2DToolbox.GetHomographyMatrixFromMatchedFeatures(keyFrame.KeyPoints, observedKeyPoints, matches, mask, 2);
}
nonZeroCount = CvInvoke.CountNonZero(mask);
if (nonZeroCount < 9)
{
homography = null;
}
//if (keyframes != null && homography == null)
// keyframes.Add(new KeyFrame() { Frame = observedImage, KeyPoints = observedKeyPoints, Descriptors = observedDescriptors });
}
return(this);
}
protected Mat GetHomography(VectorOfKeyPoint keyPoints1, VectorOfKeyPoint keyPoints2, VectorOfVectorOfDMatch matches, Mat mask)
{
Mat homography = null;
mask.SetTo(new MCvScalar(255));
Features2DToolbox.VoteForUniqueness(matches, 0.9, mask);
int i = CvInvoke.CountNonZero(mask);
if (i >= 4)
{
i = Features2DToolbox.VoteForSizeAndOrientation(keyPoints1, keyPoints2, matches, mask, 1.5, 20);
if (i >= 4)
{
homography = Features2DToolbox.GetHomographyMatrixFromMatchedFeatures(keyPoints1, keyPoints2, matches, mask, 2);
}
}
return(homography);
}
private static Mat FindMatchWithoutCuda(Mat modelImage, Mat observedImage, VectorOfKeyPoint modelKeyPoints, VectorOfKeyPoint observedKeyPoints, VectorOfVectorOfDMatch matches, out Mat mask, Mat homography, int k, double uniquenessThreshold, double hessianThresh)
{
using (UMat uModelImage = modelImage.GetUMat(AccessType.Read))
using (UMat uObservedImage = observedImage.GetUMat(AccessType.Read))
{
SURF surfCPU = new SURF(hessianThresh, upright: true);
UMat modelDescriptors;
if (!FindDescriptors(surfCPU, modelKeyPoints, uModelImage, out modelDescriptors))
{
Logger.Log(LogType.Error, "Feature Descriptor for Model image is empty. Is the image too small?");
return(mask = null);
}
UMat observedDescriptors;
if (!FindDescriptors(surfCPU, observedKeyPoints, uObservedImage, out observedDescriptors))
{
Logger.Log(LogType.Error, "Feature Descriptor for Observed image is empty. Is the image too small?");
return(mask = null);
}
BFMatcher matcher = new BFMatcher(DistanceType.L2);
matcher.Add(modelDescriptors);
matcher.KnnMatch(observedDescriptors, matches, k, null);
mask = new Mat(matches.Size, 1, DepthType.Cv8U, 1);
mask.SetTo(new MCvScalar(255));
Features2DToolbox.VoteForUniqueness(matches, uniquenessThreshold, mask);
int nonZeroCount = CvInvoke.CountNonZero(mask);
if (nonZeroCount >= 4)
{
nonZeroCount = Features2DToolbox.VoteForSizeAndOrientation(modelKeyPoints, observedKeyPoints, matches, mask, 1.5, 20);
if (nonZeroCount >= 4)
{
homography = Features2DToolbox.GetHomographyMatrixFromMatchedFeatures(modelKeyPoints, observedKeyPoints, matches, mask, 2);
}
}
}
return(homography);
}
/// <summary>
/// Find wrinkles on an image with in a recangle
/// </summary>
/// <param name="shortImage">Image on which wrinkles need to calculate</param>
/// <param name="rect">Rectangles with in which wrinkles needs to calculate</param>
/// <returns>Returns the intensity of wrinkles</returns>
public double findWrinkles(Mat shortImage, Rectangle rect)
{
Image <Gray, byte> procImage = shortImage.ToImage <Gray, byte>();
procImage.ROI = rect;
float[] GrayHist;
DenseHistogram Histo = new DenseHistogram(255, new RangeF(0, 255));
Histo.Calculate(new Image <Gray, byte>[] { procImage }, true, null);
////The data is here
GrayHist = new float[256];
Histo.CopyTo <float>(GrayHist);
////Calculate Threashold on the basis of histogram of Image
int threashHold = calculate_threashHold(GrayHist);
procImage = procImage.Canny(threashHold, threashHold);
return((double)CvInvoke.CountNonZero(procImage));
}
public void FindMatches(Image <Rgb, byte> SubMap, out VectorOfKeyPoint VectorSubMapKeyPoint,
out Mat SubMapDiscriptors, out VectorOfVectorOfDMatch matches,
out Mat mask, out System.Drawing.Rectangle zone, out Mat homography, int k, double uniquenessThreshold, SIFTParametrs parametrs)
{
VectorSubMapKeyPoint = new VectorOfKeyPoint();
SubMapDiscriptors = new Mat();
matches = new VectorOfVectorOfDMatch();
zone = new System.Drawing.Rectangle();
using (SIFT siftCPU = new SIFT(parametrs.nFeatures, parametrs.nOctaveLayers,
parametrs.contrastThreshold, parametrs.edgeThreshold, parametrs.sigma))
{
siftCPU.DetectAndCompute(SubMap, null, VectorSubMapKeyPoint, SubMapDiscriptors, false);
}
matches = new VectorOfVectorOfDMatch();
using (Emgu.CV.Flann.LinearIndexParams ip = new Emgu.CV.Flann.LinearIndexParams())
using (Emgu.CV.Flann.SearchParams sp = new SearchParams())
using (Emgu.CV.Features2D.DescriptorMatcher matcher = new FlannBasedMatcher(ip, sp))
{
matcher.Add(SubMapDiscriptors);
matcher.KnnMatch(MapDiscriptors, matches, k, null);
}
mask = new Mat(matches.Size, 1, DepthType.Cv8U, 1);
mask.SetTo(new MCvScalar(255));
Features2DToolbox.VoteForUniqueness(matches, uniquenessThreshold, mask);
homography = null;
int nonZeroCount = CvInvoke.CountNonZero(mask);
if (nonZeroCount >= 4)
{
nonZeroCount = Features2DToolbox.VoteForSizeAndOrientation(VectorSubMapKeyPoint, VectorMapKeyPoint,
matches, mask, 1.5, 20);
if (nonZeroCount >= 4)
{
homography = Features2DToolbox.GetHomographyMatrixFromMatchedFeatures(
VectorSubMapKeyPoint, VectorMapKeyPoint, matches, mask, 2);
}
}
}
