private IEnumerable <Bitmap> DoRecognize(Bitmap b)
{
List <Bitmap> Result = new List <Bitmap>();
var NotClassifiedFeatures = FeatureExtractor.ExtractFeatures(b, null);
List <SURFFeature> FeatureRemain = new List <SURFFeature>();
Parallel.ForEach(NotClassifiedFeatures, (NotClassifiedFeature) =>
{
var KnnResult = knn.Classify(k, NotClassifiedFeature);
if (KnnResult.Confidence >= ConfidenceThreshold)
{
lock (FeatureRemain)
FeatureRemain.Add(NotClassifiedFeature);
}
});
var GroupedFeatureRemains = FeatureRemain.GroupBy(x => x.Tag);
Bitmap FinalResult = (Bitmap)b.Clone();
//Draw Features
FeaturesMarker featuresMarker = new FeaturesMarker(FeatureRemain.Select(x => x.Original));
Bitmap MarkedBitmap = featuresMarker.Apply(b);
//Draw bounding box
foreach (var GroupedFeatureRemain in GroupedFeatureRemains)
{
string Tag = GroupedFeatureRemain.Key;
Point2DGrouper point2DGrouper = new Point2DGrouper(MaximumPointGroupDistance)
{
MinimumGroupCount = MinimumPointGroupCount
};
var BoundingBoxes = point2DGrouper
.GetGrouped2DPoints(GroupedFeatureRemain.Select(f => f.GetLocation()))
.GroupBy(p => p.GroupID)
.Select(group => group.GetBoundingBox(MinimumPointGroupArea))
.Where(bbox => bbox != null);
var ObjectBox = BoundingBoxes.GetBoundingBox();
Brush brush = SelectBrush(Tag);
if (BoundingBoxes != null)
{
MarkedBitmap.DrawRect(BoundingBoxes.Select(boxes => boxes.ToRectangle()), brush, 3, "Bbox:" + Tag);
}
if (ObjectBox != null)
{
FinalResult.DrawRect(ObjectBox.ToRectangle(), brush, 3, "Object:" + Tag);
}
}
FinalResult.Tag = "Final Result";
MarkedBitmap.Tag = "Class Bounding Boxes";
Result.Add(FinalResult);
Result.Add(MarkedBitmap);
return(Result);
}
public void ProcessImageTest4()
{
Bitmap[] bitmaps =
{
Resources.flower01,
Resources.flower03,
Resources.flower06,
Resources.flower07,
Resources.flower09,
Resources.flower10,
};
var surf = new SpeededUpRobustFeaturesDetector();
int current = 0;
foreach (Bitmap img in bitmaps)
{
List <SpeededUpRobustFeaturePoint> expected;
List <SpeededUpRobustFeaturePoint> actual;
// Create OpenSURF detector by Chris Evans
{
// Create Integral Image
OpenSURFcs.IntegralImage iimg = OpenSURFcs.IntegralImage.FromImage(img);
// Extract the interest points
var pts = OpenSURFcs.FastHessian.getIpoints(0.0002f, 5, 2, iimg);
// Describe the interest points
OpenSURFcs.SurfDescriptor.DecribeInterestPoints(pts, false, false, iimg);
expected = new List <SpeededUpRobustFeaturePoint>();
foreach (var p in pts)
{
expected.Add(new SpeededUpRobustFeaturePoint(p.x, p.y, p.scale,
p.laplacian, p.orientation, p.response));
}
}
// Create Accord.NET SURF detector (based on OpenSURF by Chris Evans)
{
actual = surf.ProcessImage(img);
}
var img1 = new FeaturesMarker(actual).Apply(img);
var img2 = new FeaturesMarker(expected).Apply(img);
ImageBox.Show(new Concatenate(img1).Apply(img2), PictureBoxSizeMode.Zoom);
current++;
}
}
public void ProcessImageTest4()
{
var bitmaps = BagOfVisualWordsTest.GetImages();
var surf = new SpeededUpRobustFeaturesDetector();
int current = 0;
foreach (Bitmap img in bitmaps)
{
List <SpeededUpRobustFeaturePoint> expected;
List <SpeededUpRobustFeaturePoint> actual;
// Create OpenSURF detector by Chris Evans
{
// Create Integral Image
OpenSURFcs.IntegralImage iimg = OpenSURFcs.IntegralImage.FromImage(img);
// Extract the interest points
var pts = OpenSURFcs.FastHessian.getIpoints(0.0002f, 5, 2, iimg);
// Describe the interest points
OpenSURFcs.SurfDescriptor.DecribeInterestPoints(pts, false, false, iimg);
expected = new List <SpeededUpRobustFeaturePoint>();
foreach (var p in pts)
{
expected.Add(new SpeededUpRobustFeaturePoint(p.x, p.y, p.scale,
p.laplacian, p.orientation, p.response));
}
}
// Create Accord.NET SURF detector (based on OpenSURF by Chris Evans)
{
actual = surf.ProcessImage(img);
}
var img1 = new FeaturesMarker(actual).Apply(img);
var img2 = new FeaturesMarker(expected).Apply(img);
// ImageBox.Show(new Concatenate(img1).Apply(img2), PictureBoxSizeMode.Zoom);
current++;
for (int i = 0; i < expected.Count; i++)
{
var e = expected[i];
var a = actual[i];
Assert.AreEqual(e, a);
}
}
}
public void ExampleTest()
{
Bitmap lena = Accord.Imaging.Image.Clone(Resources.lena512);
// The freak detector can be used with any other corners detection
// algorithm. The default corners detection method used is the FAST
// corners detection. So, let's start creating this detector first:
//
var detector = new FastCornersDetector(60);
// Now that we have a corners detector, we can pass it to the FREAK
// feature extraction algorithm. Please note that if we leave this
// parameter empty, FAST will be used by default.
//
var freak = new FastRetinaKeypointDetector(detector);
// Now, all we have to do is to process our image:
List <FastRetinaKeypoint> points = freak.ProcessImage(lena);
// Afterwards, we should obtain 83 feature points. We can inspect
// the feature points visually using the FeaturesMarker class as
//
FeaturesMarker marker = new FeaturesMarker(points, scale: 20);
// And showing it on screen with
// ImageBox.Show(marker.Apply(lena));
// We can also inspect the feature vectors (descriptors) associated
// with each feature point. In order to get a descriptor vector for
// any given point, we can use
//
byte[] feature = points[42].Descriptor;
// By default, feature vectors will have 64 bytes in length. We can also
// display those vectors in more readable formats such as HEX or base64
//
string hex = points[42].ToHex();
string b64 = points[42].ToBase64();
// The above base64 result should be:
//
// "3W8M/ev///ffbr/+v3f34vz//7X+f0609v//+++/1+jfq/e83/X5/+6ft3//b4uaPZf7ePb3n/P93/rIbZlf+g=="
//
Assert.AreEqual(83, points.Count);
Assert.AreEqual(64, feature.Length);
Assert.AreEqual("3W8M/ev///ffbr/+v3f34vz//7X+f0609v//+++/1+jfq/e83/X5/+6ft3//b4uaPZf7ePb3n/P93/rIbZlf+g==", b64);
}
private void surf()
{
var surf = new Accord.Imaging.SpeededUpRobustFeaturesDetector();
surfPoints1 = surf.ProcessImage(img1).ToArray();
surfPoints2 = surf.ProcessImage(img2).ToArray();
// Show the marked points in the original images
Bitmap img1mark = new FeaturesMarker(surfPoints1).Apply(img1);
Bitmap img2mark = new FeaturesMarker(surfPoints2).Apply(img2);
// Concatenate the two images together in a single image (just to show on screen)
Concatenate concatenate = new Concatenate(img1mark);
pictureBox1.Image = concatenate.Apply(img2mark);
}
private void btnSurf_Click(object sender, EventArgs e)
{
// Step 1: Detect feature points using Surf Corners Detector
SpeededUpRobustFeaturesDetector surf = new SpeededUpRobustFeaturesDetector();
surfPoints1 = surf.Transform(img1);
surfPoints2 = surf.Transform(img2);
// Show the marked points in the original images
Bitmap img1mark = new FeaturesMarker(surfPoints1).Apply(img1);
Bitmap img2mark = new FeaturesMarker(surfPoints2).Apply(img2);
// Concatenate the two images together in a single image (just to show on screen)
Concatenate concatenate = new Concatenate(img1mark);
pictureBox.Image = concatenate.Apply(img2mark);
}
private void DetectButton_OnClick(object sender, RoutedEventArgs e)
{
var threshold = (float)Math.Pow(10.0, this.LogThresholdSlider.Value);
var octaves = (int)this.OctaveSlider.Value;
var initial = (int)this.InitialSlider.Value;
// Create a new SURF Features Detector using the given parameters
var surf = new SpeededUpRobustFeaturesDetector(threshold, octaves, initial);
var points = surf.ProcessImage(this.lenna);
// Create a new AForge's Corner Marker Filter
var features = new FeaturesMarker(points);
// Apply the filter and display it on a picturebox
this.LenaImage.Source = (BitmapSource)features.Apply(this.lenna);
}
private void button1_Click(object sender, EventArgs e)
{
// Open a image
Bitmap lenna = Properties.Resources.lena512;
float threshold = (float)numThreshold.Value;
int octaves = (int)numOctaves.Value;
int initial = (int)numInitial.Value;
// Create a new SURF Features Detector using the given parameters
SpeededUpRobustFeaturesDetector surf =
new SpeededUpRobustFeaturesDetector(threshold, octaves, initial);
List <SpeededUpRobustFeaturePoint> points = surf.ProcessImage(lenna);
// Create a new AForge's Corner Marker Filter
FeaturesMarker features = new FeaturesMarker(points);
// Apply the filter and display it on a picturebox
pictureBox1.Image = features.Apply(lenna);
}
private void button1_Click(object sender, EventArgs e)
{
// Open a image
Bitmap lenna = Surf.Properties.Resources.lena512;
// Create a new SURF Features Detector using the given parameters
SpeededUpRobustFeaturesDetector surf =
new SpeededUpRobustFeaturesDetector(0.0002f, 5, 2);
var points = surf.ProcessImage(lenna);
// Get the SURF Features Descriptor from the detector
SurfDescriptor descriptor = surf.GetDescriptor();
descriptor.Describe(points);
// Create a new AForge's Corner Marker Filter
FeaturesMarker features = new FeaturesMarker(points.ToArray());
// Apply the filter and display it on a picturebox
pictureBox1.Image = features.Apply(lenna);
}
private Bitmap CompareAndDrawImage(Bitmap modelImage, Bitmap observedImage, SurfSettings setting)
{
Stopwatch watch1 = new Stopwatch();
Stopwatch watch2 = new Stopwatch();
Bitmap returnBitmap;
watch2.Start();
watch1.Reset(); watch1.Start();
double hessianThreshold = setting.HessianThresh.HasValue ? setting.HessianThresh.Value : 500;
float hessianThreshold2 = (float)hessianThreshold / 1000000;
Debug.WriteLine("hessianThreshold2: {0}", hessianThreshold2);
SpeededUpRobustFeaturesDetector surf = new SpeededUpRobustFeaturesDetector(hessianThreshold2);
List <SpeededUpRobustFeaturePoint> surfPoints1 = surf.ProcessImage(modelImage);
List <SpeededUpRobustFeaturePoint> surfPoints2 = surf.ProcessImage(observedImage);
Debug.WriteLine("Surf points count: {0}", surfPoints1.Count);
Debug.WriteLine("Surf points count: {0}", surfPoints2.Count);
//long memoryFootprint = MemorySize.GetBlobSizeinKb(surfPoints2);
//Debug.WriteLine("Surf extractor: {0} kb", memoryFootprint);
watch1.Stop();
Debug.WriteLine("Surf Detection tooked {0} ms", watch1.ElapsedMilliseconds);
watch1.Reset(); watch1.Start();
// Show the marked points in the original images
Bitmap img1mark = new FeaturesMarker(surfPoints1, 2).Apply(modelImage);
Bitmap img2mark = new FeaturesMarker(surfPoints2, 2).Apply(observedImage);
// Concatenate the two images together in a single image (just to show on screen)
Concatenate concatenate = new Concatenate(img1mark);
returnBitmap = concatenate.Apply(img2mark);
watch1.Stop();
Debug.WriteLine("Surf point plotting tooked {0} ms", watch1.ElapsedMilliseconds);
//watch1.Reset(); watch1.Start();
//List<IntPoint>[] coretionalMatches = getMatches(surfPoints1, surfPoints2);
//watch1.Stop();
//Debug.WriteLine("Correctional Match tooked {0} ms", watch1.ElapsedMilliseconds);
//// Get the two sets of points
//IntPoint[] correlationPoints11 = coretionalMatches[0].ToArray();
//IntPoint[] correlationPoints22 = coretionalMatches[1].ToArray();
//Debug.WriteLine("Correclation points count: {0}", correlationPoints11.Length);
//Debug.WriteLine("Correclation points count: {0}", correlationPoints22.Length);
Debug.WriteLine("Threshold: {0}", setting.UniquenessThreshold.Value);
watch1.Reset(); watch1.Start();
// Step 2: Match feature points using a k-NN
KNearestNeighborMatching matcher = new KNearestNeighborMatching(2);
matcher.Threshold = setting.UniquenessThreshold.Value;
IntPoint[][] matches = matcher.Match(surfPoints1, surfPoints2);
watch1.Stop();
Debug.WriteLine("Knn Match tooked {0} ms", watch1.ElapsedMilliseconds);
// Get the two sets of points
IntPoint[] correlationPoints1 = matches[0];
IntPoint[] correlationPoints2 = matches[1];
Debug.WriteLine("Knn points count: {0}", correlationPoints1.Length);
Debug.WriteLine("Knn points count: {0}", correlationPoints2.Length);
//watch1.Reset(); watch1.Start();
//// Show the marked correlations in the concatenated image
//PairsMarker pairs = new PairsMarker(
// correlationPoints1, // Add image1's width to the X points to show the markings correctly
// correlationPoints2.Apply(p => new IntPoint(p.X + modelImage.Width, p.Y)), Color.Blue);
//returnBitmap = pairs.Apply(returnBitmap);
//watch1.Stop();
//Debug.WriteLine("Match pair marking tooked {0} ms", watch1.ElapsedMilliseconds);
if (correlationPoints1.Length < 4 || correlationPoints2.Length < 4)
{
MessageBox.Show("Insufficient points to attempt a fit.");
return(null);
}
watch1.Reset(); watch1.Start();
// Step 3: Create the homography matrix using a robust estimator
//RansacHomographyEstimator ransac = new RansacHomographyEstimator(0.001, 0.99);
RansacHomographyEstimator ransac = new RansacHomographyEstimator(0.001, 0.99);
MatrixH homography = ransac.Estimate(correlationPoints1, correlationPoints2);
watch1.Stop();
Debug.WriteLine("Ransac tooked {0} ms", watch1.ElapsedMilliseconds);
watch1.Reset(); watch1.Start();
// Plot RANSAC results against correlation results
IntPoint[] inliers1 = correlationPoints1.Submatrix(ransac.Inliers);
IntPoint[] inliers2 = correlationPoints2.Submatrix(ransac.Inliers);
watch1.Stop();
Debug.WriteLine("Ransac SubMatrix {0} ms", watch1.ElapsedMilliseconds);
Debug.WriteLine("Ransac points count: {0}", inliers1.Length);
Debug.WriteLine("Ransac points count: {0}", inliers2.Length);
watch1.Reset(); watch1.Start();
PairsMarker inlierPairs = new PairsMarker(
inliers1, // Add image1's width to the X points to show the markings correctly
inliers2.Apply(p => new IntPoint(p.X + modelImage.Width, p.Y)), Color.Red);
returnBitmap = inlierPairs.Apply(returnBitmap);
watch1.Stop();
Debug.WriteLine("Ransac plotting tooked {0} ms", watch1.ElapsedMilliseconds);
watch2.Stop();
return(returnBitmap);
}
private void process1()
{
var bitmap1 = (Bitmap)sourcebox1.Image;
var bitmap2 = (Bitmap)sourcebox2.Image;
var hash1 = ImagePhash.ComputeDigest(bitmap1.ToLuminanceImage());
var hash2 = ImagePhash.ComputeDigest(bitmap2.ToLuminanceImage());
var score = ImagePhash.GetCrossCorrelation(hash1, hash2);
Console.WriteLine("score: {0}", score);
//threshold value
var thres = new Threshold(110);
Grayscale filter = new Grayscale(0.2125, 0.7154, 0.0721);
// apply the filter to the model
Bitmap grey1 = filter.Apply(bitmap1);
thres.ApplyInPlace(grey1);
// Apply the filter to the observed image
Bitmap grey2 = filter.Apply(bitmap2);
thres.ApplyInPlace(grey2);
int modelPoints = 0, matchingPoints = 0;
var skewChecker = new DocumentSkewChecker();
var angle1 = skewChecker.GetSkewAngle(grey1);
var rotationFilter1 = new RotateBicubic(-angle1);
rotationFilter1.FillColor = Color.White;
grey1 = rotationFilter1.Apply(grey1);
var angle2 = skewChecker.GetSkewAngle(grey2);
var rotationFilter2 = new RotateBicubic(-angle2);
rotationFilter2.FillColor = Color.White;
grey2 = rotationFilter2.Apply(grey2);
//CorrelationMatching matcher = new CorrelationMatching(5, grey1, grey2);
//var results = matcher.GetHashCode();
var detector = new FastCornersDetector(15);
var freak = new FastRetinaKeypointDetector(detector);
FastRetinaKeypoint[] features1 = freak.Transform(grey1).ToArray();
modelPoints = features1.Count();
Console.WriteLine("count: {0}", modelPoints);
FastRetinaKeypoint[] features2 = freak.Transform(grey2).ToArray();
Console.WriteLine("count: {0}", features2.Count());
KNearestNeighborMatching matcher = new KNearestNeighborMatching(7);
//var length = 0;
IntPoint[][] results = matcher.Match(features1, features2);
matchingPoints = results[0].Count(); // similarity of image1 to image2
////matchingPoints = results[1].Count(); // similarity of image2 to image1
Console.WriteLine("matched points: {0}", matchingPoints);
sourcebox1.Image = bitmap1;
sourcebox2.Image = bitmap2;
var marker1 = new FeaturesMarker(features1, 30);
var marker2 = new FeaturesMarker(features2, 30);
double similPercent = 0;
if (matchingPoints <= 0)
{
similPercent = 0.0f;
}
similPercent = (matchingPoints * 100d) / (double)modelPoints;
Console.WriteLine("score: {0}", similPercent);
simil1.Text = similPercent.ToString("##.##") + "%";
simil2.Text = (score * 100.00d).ToString("##.##") + "%";
angle_text.Text = angle2.ToString("##.##") + "°";
resultbox1.Image = marker1.Apply(grey1);
resultbox2.Image = marker2.Apply(grey2);
}
private void cornerDetectorToolStripMenuItem_Click(object sender, EventArgs e)
{
Bitmap image = new Bitmap(System.Drawing.Image.FromFile(@"C:\OSU3\UAS\Training Videos\ZoltanTestSets\test\DJI_0247.rd.JPG"));
float threshold = 0.001f;
/*int octaves = (int)numOctaves.Value;
* int initial = (int)numInitial.Value;*/
ResizeNearestNeighbor filter = new ResizeNearestNeighbor(600, 400);
image = filter.Apply(image);
// Create a new SURF Features Detector using the given parameters
SpeededUpRobustFeaturesDetector surf =
new SpeededUpRobustFeaturesDetector(threshold);
List <SpeededUpRobustFeaturePoint> points = surf.ProcessImage(image);
// Create a new AForge's Corner Marker Filter
FeaturesMarker features = new FeaturesMarker(points, 5);
// Apply the filter and display it on a picturebox
Bitmap image_feature = features.Apply(image);
SingleImageWnd form = new SingleImageWnd(image_feature);
form.MdiParent = this;
form.Show();
/*Bitmap image = new Bitmap(System.Drawing.Image.FromFile(@"C:\OSU3\CAR\Reports\Targets\Target1\DSC00217.JPG"));
* Bitmap image2 = new Bitmap(image.Width, image.Height);
*
* using (Graphics g = Graphics.FromImage(image2))
* {
* g.DrawImage(image, 0, 0);
*
* Grayscale filter = new Grayscale(.33, .33, .33);
* image = filter.Apply(image);
*
* double sigma = 2;
* float k = 4 / 10;
* float threshold = 500;
*
* // Create a new Harris Corners Detector using the given parameters
* HarrisCornersDetector harris = new HarrisCornersDetector(k)
* {
* Measure = HarrisCornerMeasure.Harris, //: HarrisCornerMeasure.Noble,
* Threshold = threshold,
* Sigma = sigma
* };
*
* List<IntPoint> corners = harris.ProcessImage(image);
*
* foreach (IntPoint corner in corners)
* {
* //A circle with Red Color and 2 Pixel wide line
* //gf.DrawEllipse(new Pen(Color.Red, 2), new Rectangle(0, 0, 200, 200));
* DrawCircle(g, new Pen(Color.Red, 1), corner.X, corner.Y, 1);
* }
*
* }
*
* ImageForm form = new ImageForm(image2);
* form.MdiParent = this;
* form.Show();*/
}