I am trying to detect text fields on Windows Form but CvInvoke.MinAreaRect(contour) returns rectangle, rotated by -7.29419661 Angle.
My code is
Image<Bgr, Byte> a =
new Image<Bgr, byte>(#"d:/Art/documents/Projects/InputFieldsDetector/Images/Form345_1.PNG");
imageBox1.Image = a;
UMat grayed = new UMat();
CvInvoke.CvtColor(a, grayed, ColorConversion.Bgr2Gray);
imageBox2.Image = grayed;
UMat canny = new UMat();
CvInvoke.Canny(grayed, canny, 50, 200, 3);
imageBox3.Image = canny;
VectorOfVectorOfPoint cnts = new VectorOfVectorOfPoint();
UMat hierarchy = new UMat();
CvInvoke.FindContours(canny, cnts, null, RetrType.Tree, ChainApproxMethod.ChainApproxSimple);
Image<Bgr, Byte> justCountor = a.Clone();
List<string> sizes = new List<string>();
int count = cnts.Size;
for (int i = 0; i < count; i++)
{
VectorOfPoint contour = cnts[i];
var area = CvInvoke.ContourArea(contour);
//if (area > 10000 && area < 15000)
if (area > 200 && area < 300)
{
sizes.Add(area.ToString());
Point[] pts = contour.ToArray();
var forDraw = CvInvoke.MinAreaRect(contour);
// forDraw.Angle = 0;
//forDraw.Center.Y += 10;
justCountor.Draw(forDraw, new Bgr(Color.DarkOrange), 2);
}
}
imageBox4.Image = justCountor;
List<double> result = sizes.Select(x => double.Parse(x)).ToList();
result.Sort();
sizes = result.Select(x => x.ToString()).ToList();
File.WriteAllLines("c:/temp/qqq.txt", sizes);
Original image is:
If I uncomment section
forDraw.Angle = 0;
forDraw.Center.Y += 10;
sizes of detected rects are similar to sizes of fields...
Tell me, please, why returned rects are rotated and how to fix that?
You can see in the Canny output that the algorithm is interpreting the shadows as borders. The easiest way to fix that is prefilter the image with a threshold with a high value near to the white of the box background.
Image<Bgr, Byte> a =
new Image<Bgr, byte>(#"d:/Art/documents/Projects/InputFieldsDetector/Images/Form345_1.PNG");
imageBox1.Image = a;
UMat grayed = new UMat();
CvInvoke.CvtColor(a, grayed, ColorConversion.Bgr2Gray);
imageBox2.Image = grayed;
UMat thresholded = new UMat();
CvInvoke.Threshold(grayed, thresholded, 128, 255, ThresholdType.Binary);
imageBox5.Image = thresholded;
UMat canny = new UMat();
CvInvoke.Canny(thresholded, canny, 50, 200, 3);
imageBox3.Image = canny;
VectorOfVectorOfPoint cnts = new VectorOfVectorOfPoint();
UMat hierarchy = new UMat();
CvInvoke.FindContours(canny, cnts, null, RetrType.Tree, ChainApproxMethod.ChainApproxSimple);
Image<Bgr, Byte> justCountor = a.Clone();
List<string> sizes = new List<string>();
int count = cnts.Size;
for (int i = 0; i < count; i++)
{
VectorOfPoint contour = cnts[i];
var area = CvInvoke.ContourArea(contour);
if (area > 200 && area < 300)
{
sizes.Add(area.ToString());
Point[] pts = contour.ToArray();
var forDraw = CvInvoke.MinAreaRect(contour);
// forDraw.Angle = 0;
//forDraw.Center.Y += 10;
if (forDraw.Angle==0)
justCountor.Draw(forDraw, new Bgr(Color.DarkOrange), 2);
}
}
imageBox4.Image = justCountor;
List<double> result = sizes.Select(x => double.Parse(x)).ToList();
result.Sort();
sizes = result.Select(x => x.ToString()).ToList();
File.WriteAllLines("c:/temp/qqq.txt", sizes);
Related
i am using C# EmguCv library to detect diamonds from the image capture by a live camera and saved into the folder. i have done other task of the project and only remaining the detection part and almost got it but just missing something that i don't know where is the problem . so here is the Image and it should be detected as Image2 perfect as this image so now i am trying something but it not giving me the result i want. here's i what i am getting is image3 and image4.
here is my code:
imgInput = new Image<Bgr, byte>(img_path);
if (imgInput == null)
{
return;
}
try
{
// Convert image to grayscale
Mat grayImage = new Mat();
CvInvoke.CvtColor(imgInput, grayImage, ColorConversion.Bgr2Gray);
// Apply Gaussian blur to reduce noise
CvInvoke.GaussianBlur(grayImage, grayImage, new Size(7, 7), 4);
// Apply Canny edge detection
Mat edges = new Mat();
CvInvoke.Canny(grayImage, edges, 75, 200);
VectorOfVectorOfPoint contours = new VectorOfVectorOfPoint();
CvInvoke.FindContours(edges, contours, null, RetrType.List, ChainApproxMethod.ChainApproxSimple);
int jk = 0;
dataGridView1.Columns.Add("stone_id", "Stone ID");
for (int i = 0; i < contours.Size; i++)
{
double perimeter = CvInvoke.ArcLength(contours[i], true);
VectorOfPoint approx = new VectorOfPoint();
CvInvoke.ApproxPolyDP(contours[i], approx, 0.04 * perimeter, true);
var bbox = CvInvoke.BoundingRectangle(contours[i]);
process_img = new Image<Bgr, byte>(img_path);
process_img.ROI = bbox;
var img = process_img.Copy();
if (jk == sel_row_id)
{
CvInvoke.DrawContours(imgInput, contours, i, new MCvScalar(0, 255, 17), 2);
if (contours.Size > 0)
{
byte maxRed, maxBlue, maxGreen;
maxRed = maxBlue = maxGreen = 0;
float meanRed, meanBlue, meanGreen;
meanRed = meanBlue = meanGreen = 0;
double medRed,medBlue,medGreen;
medRed = medBlue = medGreen = 0;
FindMax(img.Bitmap, ref maxRed, ref maxBlue, ref maxGreen, ref meanRed, ref meanBlue, ref meanGreen, ref medRed, ref medBlue, ref medGreen);
R_txtbox.Text = maxRed.ToString();
B_txtbox.Text = maxBlue.ToString();
G_txtbox.Text = maxGreen.ToString();
R_mean.Text = meanRed.ToString();
B_mean.Text = meanBlue.ToString();
G_mean.Text = meanGreen.ToString();
R_med.Text = medRed.ToString();
B_med.Text = medBlue.ToString();
G_med.Text = medGreen.ToString();
pictureBox5.Image = img.ToBitmap();
//colorCode.Text = myRgbColor.ToString();
}
}
else
{
CvInvoke.DrawContours(imgInput, contours, i, new MCvScalar(0, 0, 255), 2);
}
dataGridView1.Rows.Add(jk.ToString());
jk++;
pictureBox4.Image = imgInput.Bitmap;
img.Save("F:\\Objects" + "\\" + (i + 1) + ".jpg");
}
RefreshGridView();
}
catch (Exception ex)
{
MessageBox.Show(ex.Message);
}
I'm trying to follow this OpenCV tutorial but I have not managed to create the FaceInvoke.FaceDetectNative function, I tried to use this function but the application stops working.
static bool MyDetector(IntPtr input, IntPtr output)
{
CascadeClassifier faceDetector = new CascadeClassifier(#"..\..\Resource\EMGUCV\haarcascade_frontalface_default.xml");
Image<Gray, byte> grayImage = (new Image<Bgr, byte>(CvInvoke.cvGetSize(input))).Convert<Gray, byte>();
grayImage._EqualizeHist();
Rectangle[] faces = faceDetector.DetectMultiScale(grayImage, 1.1, 10, Size.Empty);
VectorOfRect rects = new VectorOfRect(faces);
CvInvoke.cvCopy(rects.Ptr, output, IntPtr.Zero);
return true;
}
On the other hand I tried calling the GetFaces method by passing a Mat object = new Mat (); as IOutputArray which also has not worked (Crash error).
FacemarkLBFParams fParams = new FacemarkLBFParams();
fParams.ModelFile = #"..\..\Resource\EMGUCV\facemarkmodel.yaml";
FacemarkLBF facemark = new FacemarkLBF(fParams);
facemark.SetFaceDetector(MyDetector);
VectorOfRect result = new VectorOfRect();
Image<Bgr, Byte> image = new Image<Bgr, byte>(#"C:\Users\matias\Documents\Proyectos\100-20.bmp");
bool success = facemark.GetFaces(image, result);
Rectangle[] faces = result.ToArray();
Thank's
After several hours I have managed to detect the points of a face, for that use the Fit method, which receives the image, the faces (such as VectorOfRect) and a VectorOfVectorOfPointF for the output
public Image<Bgr, Byte> GetFacePoints()
{
CascadeClassifier faceDetector = new CascadeClassifier(#"..\..\Resource\EMGUCV\haarcascade_frontalface_default.xml");
FacemarkLBFParams fParams = new FacemarkLBFParams();
fParams.ModelFile = #"..\..\Resource\EMGUCV\lbfmodel.yaml";
fParams.NLandmarks = 68; // number of landmark points
fParams.InitShapeN = 10; // number of multiplier for make data augmentation
fParams.StagesN = 5; // amount of refinement stages
fParams.TreeN = 6; // number of tree in the model for each landmark point
fParams.TreeDepth = 5; //he depth of decision tree
FacemarkLBF facemark = new FacemarkLBF(fParams);
//facemark.SetFaceDetector(MyDetector);
Image<Bgr, Byte> image = new Image<Bgr, byte>(#"C:\Users\matias\Downloads\personas-buena-vibra-caracteristicas-1200x600.jpg");
Image<Gray, byte> grayImage = image.Convert<Gray, byte>();
grayImage._EqualizeHist();
VectorOfRect faces = new VectorOfRect(faceDetector.DetectMultiScale(grayImage));
VectorOfVectorOfPointF landmarks = new VectorOfVectorOfPointF();
facemark.LoadModel(fParams.ModelFile);
bool success = facemark.Fit(grayImage, faces, landmarks);
if (success)
{
Rectangle[] facesRect = faces.ToArray();
for (int i = 0; i < facesRect.Length; i++)
{
image.Draw(facesRect[i], new Bgr(Color.Blue), 2);
FaceInvoke.DrawFacemarks(image, landmarks[i], new Bgr(Color.Blue).MCvScalar);
}
return image;
}
return null;
}
Now all that remains is to optimize the code and continue with my project
I'm currently modifying EmguCV's (Ver 3.0.0.2157) SurfFeature example (Seen here).
I'm trying to determine the amount of matched pairs of points in order to calculate a percentage of similarity between the inputted images.
From what I understand, this information is stored in the mask variable, but I don't know how to access it?
(This question has been asked before here, but the example source code being referenced is using an older version of EmguCV)
Thanks in advance!
p determine matches
public static Image<Bgr, Byte> Draw(Image<Gray, Byte> modelImage, Image<Gray, byte> observedImage, out long matchTime, out int nonofZeroCount)
{
int returnValue = 0;
Stopwatch watch;
HomographyMatrix homography = null;
SURFDetector surfCPU = new SURFDetector(500, false);
VectorOfKeyPoint modelKeyPoints;
VectorOfKeyPoint observedKeyPoints;
Matrix<int> indices;
Matrix<byte> mask;
int k = 2;
double uniquenessThreshold = 0.8;
if (GpuInvoke.HasCuda)
{
GpuSURFDetector surfGPU = new GpuSURFDetector(surfCPU.SURFParams, 0.01f);
using (GpuImage<Gray, Byte> gpuModelImage = new GpuImage<Gray, byte>(modelImage))
//extract features from the object image
using (GpuMat<float> gpuModelKeyPoints = surfGPU.DetectKeyPointsRaw(gpuModelImage, null))
using (GpuMat<float> gpuModelDescriptors = surfGPU.ComputeDescriptorsRaw(gpuModelImage, null, gpuModelKeyPoints))
using (GpuBruteForceMatcher<float> matcher = new GpuBruteForceMatcher<float>(DistanceType.L2))
{
modelKeyPoints = new VectorOfKeyPoint();
surfGPU.DownloadKeypoints(gpuModelKeyPoints, modelKeyPoints);
watch = Stopwatch.StartNew();
// extract features from the observed image
using (GpuImage<Gray, Byte> gpuObservedImage = new GpuImage<Gray, byte>(observedImage))
using (GpuMat<float> gpuObservedKeyPoints = surfGPU.DetectKeyPointsRaw(gpuObservedImage, null))
using (GpuMat<float> gpuObservedDescriptors = surfGPU.ComputeDescriptorsRaw(gpuObservedImage, null, gpuObservedKeyPoints))
using (GpuMat<int> gpuMatchIndices = new GpuMat<int>(gpuObservedDescriptors.Size.Height, k, 1, true))
using (GpuMat<float> gpuMatchDist = new GpuMat<float>(gpuObservedDescriptors.Size.Height, k, 1, true))
using (GpuMat<Byte> gpuMask = new GpuMat<byte>(gpuMatchIndices.Size.Height, 1, 1))
using (Stream stream = new Stream())
{
matcher.KnnMatchSingle(gpuObservedDescriptors, gpuModelDescriptors, gpuMatchIndices, gpuMatchDist, k, null, stream);
indices = new Matrix<int>(gpuMatchIndices.Size);
mask = new Matrix<byte>(gpuMask.Size);
//gpu implementation of voteForUniquess
using (GpuMat<float> col0 = gpuMatchDist.Col(0))
using (GpuMat<float> col1 = gpuMatchDist.Col(1))
{
GpuInvoke.Multiply(col1, new MCvScalar(uniquenessThreshold), col1, stream);
GpuInvoke.Compare(col0, col1, gpuMask, CMP_TYPE.CV_CMP_LE, stream);
}
observedKeyPoints = new VectorOfKeyPoint();
surfGPU.DownloadKeypoints(gpuObservedKeyPoints, observedKeyPoints);
//wait for the stream to complete its tasks
//We can perform some other CPU intesive stuffs here while we are waiting for the stream to complete.
stream.WaitForCompletion();
gpuMask.Download(mask);
gpuMatchIndices.Download(indices);
if (GpuInvoke.CountNonZero(gpuMask) >= 4)
{
int nonZeroCount = Features2DToolbox.VoteForSizeAndOrientation(modelKeyPoints, observedKeyPoints, indices, mask, 1.5, 20);
if (nonZeroCount >= 4)
homography = Features2DToolbox.GetHomographyMatrixFromMatchedFeatures(modelKeyPoints, observedKeyPoints, indices, mask, 2);
returnValue = nonZeroCount;
}
watch.Stop();
}
}
}
else
{
//extract features from the object image
modelKeyPoints = surfCPU.DetectKeyPointsRaw(modelImage, null);
Matrix<float> modelDescriptors = surfCPU.ComputeDescriptorsRaw(modelImage, null, modelKeyPoints);
watch = Stopwatch.StartNew();
// extract features from the observed image
observedKeyPoints = surfCPU.DetectKeyPointsRaw(observedImage, null);
Matrix<float> observedDescriptors = surfCPU.ComputeDescriptorsRaw(observedImage, null, observedKeyPoints);
BruteForceMatcher<float> matcher = new BruteForceMatcher<float>(DistanceType.L2);
matcher.Add(modelDescriptors);
indices = new Matrix<int>(observedDescriptors.Rows, k);
using (Matrix<float> dist = new Matrix<float>(observedDescriptors.Rows, k))
{
matcher.KnnMatch(observedDescriptors, indices, dist, k, null);
mask = new Matrix<byte>(dist.Rows, 1);
mask.SetValue(255);
Features2DToolbox.VoteForUniqueness(dist, uniquenessThreshold, mask);
}
int nonZeroCount = CvInvoke.cvCountNonZero(mask);
if (nonZeroCount >= 4)
{
nonZeroCount = Features2DToolbox.VoteForSizeAndOrientation(modelKeyPoints, observedKeyPoints, indices, mask, 1.5, 20);
if (nonZeroCount >= 4)
homography = Features2DToolbox.GetHomographyMatrixFromMatchedFeatures(modelKeyPoints, observedKeyPoints, indices, mask, 2);
}
returnValue = nonZeroCount;
watch.Stop();
}
int p = mask.ManagedArray.OfType<byte>().ToList().Where(q => q == 1).Count();
//Draw the matched keypoints
Image<Bgr, Byte> result = Features2DToolbox.DrawMatches(modelImage, modelKeyPoints, observedImage, observedKeyPoints,
indices, new Bgr(255, 255, 255), new Bgr(255, 255, 255), mask, Features2DToolbox.KeypointDrawType.DEFAULT);
#region draw the projected region on the image
if (homography != null && p > 20)
{ //draw a rectangle along the projected model
Rectangle rect = modelImage.ROI;
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)};
homography.ProjectPoints(pts);
result.DrawPolyline(Array.ConvertAll<PointF, Point>(pts, Point.Round), true, new Bgr(Color.Red), 5);
}
#endregion
matchTime = watch.ElapsedMilliseconds;
nonofZeroCount = returnValue;
return result;
}
I have developed a working C# face recognition program using EmguCV.
However, if I load "haarcascade_fullbody.xml" instead of "haarcascade_frontalface_alt_tree.xml" I get the almighty Access Violation.
This is the code;
public Bitmap detection(Bitmap Source)
{
List<Image<Gray, byte>> TrainedImages = this.TrainedImages;
List<String> Names = this.Names;
Image<Bgr, byte> ImageFrame = new Image<Bgr, byte>(Source);
Image<Gray, byte> grayFrame = ImageFrame.Convert<Gray, byte>();
Image<Bgr, byte> overlay = new Image<Bgr, byte>(Source.Width, Source.Height);
Graphics FaceCanvas;
List<String> finimg = new List<String>();
//HaarCascade haar = new HaarCascade("haarcascade_frontalface_alt_tree.xml");
HaarCascade haar = new HaarCascade("haarcascade_fullbody.xml");
var faces = grayFrame.DetectHaarCascade(haar, 1.1, 3, HAAR_DETECTION_TYPE.DO_CANNY_PRUNING, new System.Drawing.Size(25, 25))[0];
foreach (var face in faces)
{
overlay.Draw(face.rect, new Bgr(System.Drawing.Color.Green), 3);
tempbmp = new Bitmap(100, 100);
FaceCanvas = Graphics.FromImage(tempbmp);
FaceCanvas.DrawImage(grayFrame.ToBitmap(), 0, 0, face.rect, GraphicsUnit.Pixel);
detected.Add(tempbmp);
if (doit)
{
saveBitmap(tempbmp, trainpath, trainnamer.Text);
doit = false;
}
if (doit10)
{
for (int k = 1; k <= 10; k++)
saveBitmap(tempbmp, trainpath, trainnamer.Text);
doit10 = false;
}
try
{
MCvTermCriteria termCrit = new MCvTermCriteria(TrainedImages.ToArray().Length, 0.001);//????????????
EigenObjectRecognizer recognizer = new EigenObjectRecognizer(TrainedImages.ToArray(), Names.ToArray(), 2500, ref termCrit);
MCvFont font = new MCvFont(FONT.CV_FONT_HERSHEY_TRIPLEX, 0.5d, 0.5d);
String name = recognizer.Recognize(new Image<Gray, byte>(tempbmp));
if (Names.Contains(name) == false)
name = "Stranger";
else
name = removeformat(name);
overlay.Draw(name, ref font, new System.Drawing.Point(face.rect.Left, face.rect.Top - 5), new Bgr(System.Drawing.Color.Green));
finimg.Add(name);
}
catch (IndexOutOfRangeException)
{
MCvFont font = new MCvFont(FONT.CV_FONT_HERSHEY_TRIPLEX, 0.5d, 0.5d);
ImageFrame.Draw("Stranger", ref font, new System.Drawing.Point(face.rect.Left, face.rect.Top - 5), new Bgr(color));
continue;
}
}
detected.Clear();
Bitmap supra = overlay.ToBitmap();
supra.MakeTransparent(System.Drawing.Color.Black);
return supra;
}
Apparently there is a problem with the xml, as any other haarcascade I try to load loads succesfully. I recommend using the HOGDescriptor instead or "haarcascade_mcs_upperbody.xml" for pedestrian detecting.
How can I compute the hog descriptor vector of an image using EMGU CV and C#.
If i make something like this:
float[] f;
Image<Bgr, Byte> img1 = new Image<Bgr, Byte>(fullPath);
f = hog.Compute(img1, Size.Empty, Size.Empty,null );
it doesn't work, it gives a
Object reference not set to an instance of an object.
exception. I want to compute the hog descriptor with default parameters.
Does someone know how to do this ?
Emgu cv is very poorly documented.
I have modified the code and now I am getting the following error: "External component has thrown an exception" The code is listed below
public float[] GetVector(Image<Bgr, Byte> im)
{
HOGDescriptor hog = new HOGDescriptor(); // with defaults values
// Image<Bgr, Byte> pImage = new Image<Bgr, Byte>(;
//pImage.ROI = new Rectangle(new Point(0, 0), new Size(64, 128));
Point[] p = new Point[im.Width * im.Height];
int k = 0;
for (int i = 0; i < im.Width; i++)
{
for (int j = 0; j < im.Height; j++)
{
Point p1 = new Point(i, j);
p[k++] = p1;
}
}
return hog.Compute(im, new Size(8, 8), new Size(0, 0), p);
}
Just for the record here is he answer:
public Image<Bgr, Byte> Resize(Image<Bgr, Byte> im)
{
return im.Resize(64, 128, Emgu.CV.CvEnum.INTER.CV_INTER_LINEAR);
}
public float[] GetVector(Image<Bgr, Byte> im)
{
HOGDescriptor hog = new HOGDescriptor(); // with defaults values
Image<Bgr, Byte> imageOfInterest = Resize(im);
Point[] p = new Point[imageOfInterest.Width * imageOfInterest.Height];
int k = 0;
for (int i = 0; i < imageOfInterest.Width; i++)
{
for (int j = 0; j < imageOfInterest.Height; j++)
{
Point p1 = new Point(i, j);
p[k++] = p1;
}
}
return hog.Compute(imageOfInterest, new Size(8, 8), new Size(0, 0), p);
}
If someone else will ever need it :)