/// <summary>
/// The main program entry point
/// </summary>
/// <param name="args">The command line arguments</param>
static void Main(string[] args)
{
// set up Dlib facedetectors and shapedetectors
using (var fd = Dlib.GetFrontalFaceDetector())
using (var sp = ShapePredictor.Deserialize("shape_predictor_68_face_landmarks.dat"))
{
// load input image
var img = Dlib.LoadImage <RgbPixel>(inputFilePath);
// find all faces in the image
var faces = fd.Operator(img);
foreach (var face in faces)
{
// find the landmark points for this face
var shape = sp.Detect(img, face);
// draw the landmark points on the image
for (var i = 0; i < shape.Parts; i++)
{
var point = shape.GetPart((uint)i);
var rect = new Rectangle(point);
Dlib.DrawRectangle(img, rect, color: new RgbPixel(255, 255, 0), thickness: 4);
}
}
// export the modified image
Dlib.SaveJpeg(img, "output.jpg");
}
}
private void BackgroundWorkerOnDoWork(object sender, DoWorkEventArgs doWorkEventArgs)
{
var path = doWorkEventArgs.Argument as string;
if (string.IsNullOrWhiteSpace(path) || !File.Exists(path))
{
return;
}
// DlibDotNet can create Array2D from file but this sample demonstrate
// converting managed image class to dlib class and vice versa.
using (var faceDetector = Dlib.GetFrontalFaceDetector())
using (var ms = new MemoryStream(File.ReadAllBytes(path)))
using (var bitmap = (Bitmap)Image.FromStream(ms))
{
using (var image = bitmap.ToArray2D <RgbPixel>())
{
var dets = faceDetector.Detect(image);
foreach (var r in dets)
{
Dlib.DrawRectangle(image, r, new RgbPixel {
Green = 255
});
}
var result = image.ToBitmap();
this.pictureBox.Invoke(new Action(() =>
{
this.pictureBox.Image?.Dispose();
this.pictureBox.Image = result;
}));
}
}
}
public static void DetectFacesAsync(string inputFilePath, string subscriptionKey, string uriBase, IFaceClient client, string vocabularyPath)
{
// set up Dlib facedetector
DirectoryInfo dir = new DirectoryInfo(inputFilePath);
using (var fd = Dlib.GetFrontalFaceDetector())
{
foreach (FileInfo files in dir.GetFiles("*.jpg"))
{
string _inputFilePath = inputFilePath + files.Name;
// load input image
Array2D <RgbPixel> img = Dlib.LoadImage <RgbPixel>(_inputFilePath);
// find all faces in the image
Rectangle[] faces = fd.Operator(img);
if (faces.Length != 0)
{
Console.WriteLine("Picture " + files.Name + " have faces, sending data to Azure");
MakeAnalysisRequestAsync(_inputFilePath, subscriptionKey, uriBase, files.Name, client, vocabularyPath).Wait();
}
foreach (var face in faces)
{
// draw a rectangle for each face
Dlib.DrawRectangle(img, face, color: new RgbPixel(0, 255, 255), thickness: 4);
}
// export the modified image
Dlib.SaveJpeg(img, "./Results/" + files.Name);
}
}
private void buscarrosto(Bitmap frame)
{
Image <Rgb, Byte> imageCV = new Image <Rgb, byte>(frame);
Emgu.CV.Mat mat = imageCV.Mat;
var array = new byte[mat.Width * mat.Height * mat.ElementSize];
mat.CopyTo(array);
using (Array2D <RgbPixel> image = Dlib.LoadImageData <RgbPixel>(array, (uint)mat.Height, (uint)mat.Width, (uint)(mat.Width * mat.ElementSize)))
{
using (FrontalFaceDetector fd = Dlib.GetFrontalFaceDetector())
{
var faces = fd.Operator(image);
foreach (DlibDotNet.Rectangle face in faces)
{
FullObjectDetection shape = _ShapePredictor.Detect(image, face);
ChipDetails faceChipDetail = Dlib.GetFaceChipDetails(shape, 150, 0.25);
Array2D <RgbPixel> faceChip = Dlib.ExtractImageChip <RgbPixel>(image, faceChipDetail);
Bitmap bitmap1 = faceChip.ToBitmap <RgbPixel>();
MainWindow.main.Statusa1 = bitmap1;
Dlib.DrawRectangle(image, face, color: new RgbPixel(0, 255, 255), thickness: 4);
}
}
frame = image.ToBitmap <RgbPixel>();
MainWindow.main.Statusa = frame;
}
}
private static List <(OutputLabels <Matrix <float> >, Rectangle[])> GetData(List <Bitmap> bitmaps, bool isAFace = false)
{
var datas = new List <(OutputLabels <Matrix <float> >, Rectangle[])>();
try
{
foreach (var bitmap in bitmaps)
{
var faces = new List <Matrix <RgbPixel> >();
var dets = new Rectangle[0];
//在图像中寻找人脸我们需要一个人脸检测器:
using (var detector = Dlib.GetFrontalFaceDetector())
{
using (var img = bitmap.ToMatrix <RgbPixel>())
{
// 人脸 面积从大到小排序
dets = detector.Operator(img).OrderByDescending(x => x.Area).ToArray();
// 是否只检测面积最大的人脸
if (isAFace)
{
var shape = _SP.Detect(img, dets[0]);
var faceChipDetail = Dlib.GetFaceChipDetails(shape, 150, 0.25);
var faceChip = Dlib.ExtractImageChip <RgbPixel>(img, faceChipDetail);
faces.Add(faceChip);
}
else
{
foreach (var face in dets)
{
var shape = _SP.Detect(img, face);
var faceChipDetail = Dlib.GetFaceChipDetails(shape, 150, 0.25);
var faceChip = Dlib.ExtractImageChip <RgbPixel>(img, faceChipDetail);
faces.Add(faceChip);
}
}
if (!faces.Any())
{
datas.Add((null, null));
}
else
{
//此调用要求DNN将每个人脸图像转换为128D矢量。
//在这个128D的矢量空间中，来自同一个人的图像会彼此接近
//但是来自不同人的载体将会非常不同。所以我们可以用这些向量
//辨别一对图片是来自同一个人还是不同的人。
datas.Add((_NET.Operator(faces), dets));
}
}
}
}
}
catch (Exception ex)
{
LogHelperNLog.Error(ex);
}
return(datas);
}
public static void DrawPointsOfLandmarks(FileInfo image)
{
using (var fd = Dlib.GetFrontalFaceDetector())
using (var sp = ShapePredictor.Deserialize(GetFile(ShapePredictorFileName).FullName))
{
using (var img = Dlib.LoadImage <RgbPixel>(image.FullName))
{
var faces = fd.Operator(img);
// for each face draw over the facial landmarks
foreach (var face in faces)
{
var shape = sp.Detect(img, face);
// draw the landmark points on the image
for (var i = 0; i < shape.Parts; i++)
{
var point = shape.GetPart((uint)i);
var rect = new Rectangle(point);
if (i == 0)
{
Dlib.DrawRectangle(img, rect, color: new RgbPixel(255, 255, 255), thickness: 8);
}
else if (i == 21 || i == 22 || i == 39 || i == 42 || i == 33 || i == 51 || i == 57 ||
i == 48 ||
i == 54)
{
Dlib.DrawRectangle(img, rect, color: new RgbPixel(255, 0, 255), thickness: 4);
}
else if (i == 18 || i == 19 || i == 20 || i == 21) // left eye
{
Dlib.DrawRectangle(img, rect, color: new RgbPixel(255, 0, 0), 6);
}
else if (i == 22 || i == 23 || i == 24 || i == 25) // right eye
{
Dlib.DrawRectangle(img, rect, color: new RgbPixel(255, 128, 0), 6);
}
else if (i == 48 || i == 49 || i == 50) // left lip
{
Dlib.DrawRectangle(img, rect, color: new RgbPixel(255, 255, 0), 2);
}
else if (i == 52 || i == 53 || i == 54) // right lip
{
Dlib.DrawRectangle(img, rect, color: new RgbPixel(255, 0, 128), 2);
}
else
{
Dlib.DrawRectangle(img, rect, color: new RgbPixel(0, 0, 0), thickness: 4);
}
}
Dlib.SavePng(img, "output.jpg");
}
}
}
}
/// <summary>
/// 具体计算
/// </summary>
/// <param name="bitmap"></param>
/// <returns></returns>
public Rectangle[] Face(Bitmap bitmap)
{
var dets = new Rectangle[0];
using (var detector = Dlib.GetFrontalFaceDetector())
//using (var img = Dlib.LoadImage<RgbPixel>("png.png"))
using (var img = bitmap.ToArray2D <RgbPixel>())
{
dets = detector.Operator(img);
}
return(dets);
}
public Rectangle[] DetectFacesBoundingBoxes(Array2D <RgbPixel> img)
{
Rectangle[] facesBoundingBoxes;
// Set up and apply face detector
using (var fd = Dlib.GetFrontalFaceDetector())
{
facesBoundingBoxes = fd.Operator(img);
}
return(facesBoundingBoxes);
}
/// <summary>
/// 使用路径获取位置数据
/// </summary>
/// <param name="url"></param>
/// <returns></returns>
public static Rectangle[] GetResult(string url)
{
var dets = new Rectangle[0];
url = Path.Combine(AppDomain.CurrentDomain.BaseDirectory, url);
using (var detector = Dlib.GetFrontalFaceDetector())
//using (var img = Dlib.LoadImage<RgbPixel>("png.png"))
using (var img = Dlib.LoadImage <RgbPixel>(url))
{
dets = detector.Operator(img);
}
return(dets);
}
private static void DetectFacesOnImage(Array2D <RgbPixel> image)
{
// set up Dlib facedetector
using (var fd = Dlib.GetFrontalFaceDetector())
{
// find all faces in the image
var faces = fd.Operator(image);
foreach (Rectangle face in faces)
{
// draw a rectangle for each face
Dlib.DrawRectangle(image, face, color: new RgbPixel(0, 255, 255), thickness: 4);
}
}
}
public static void DetectFacesOnImage(string sourceImagePath, string destImagePath)
{
// set up Dlib facedetector
using (var fd = Dlib.GetFrontalFaceDetector())
{
// load input image
var image = Dlib.LoadImage <RgbPixel>(sourceImagePath);
DetectFacesOnImage(image);
// export the modified image
Dlib.SaveJpeg(image, destImagePath);
}
}
public void FindFaces()
{
using (var fd = Dlib.GetFrontalFaceDetector())
{
var img = Dlib.LoadImage <RgbPixel>(path);
// find all faces in the image
var faces = fd.Operator(img);
foreach (var face in faces)
{
// draw a rectangle for each face
Dlib.DrawRectangle(img, face, color: new RgbPixel(0, 255, 255), thickness: 4);
}
Dlib.SaveJpeg(img, @"D:\output.png");
}
}
/// <summary>
/// 具体计算
/// </summary>
/// <param name="bitmaps"></param>
/// <returns></returns>
private static List <List <Landmark68ViewModler> > GetDate(List <Bitmap> bitmaps)
{
List <List <FullObjectDetection> > Detection = new List <List <FullObjectDetection> >();
List <List <Landmark68ViewModler> > landmark68s = new List <List <Landmark68ViewModler> >();
//人脸检测器
using (var detector = Dlib.GetFrontalFaceDetector())
{
foreach (var bitmap in bitmaps)
{
var shapes = new List <FullObjectDetection>();
// 图片转换
using (var img = bitmap.ToArray2D <RgbPixel>())
{
//获取位置数据
var dets = detector.Operator(img);
// 循环人脸数据
foreach (var rect in dets)
{
// 特征点检测
var shape = _SP.Detect(img, rect);
if (shape.Parts > 2)
{
shapes.Add(shape);
}
List <Landmark68ViewModler> landmark68 = new List <Landmark68ViewModler>();
for (uint i = 0; i < shape.Parts; i++)
{
var item = shape.GetPart(i);
landmark68.Add(new Landmark68ViewModler()
{
X = item.X,
Y = item.Y,
});
}
landmark68s.Add(landmark68);
}
}
Detection.Add(shapes);
}
}
return(landmark68s);
}
public static int Number(string file)
{
using (var fd = Dlib.GetFrontalFaceDetector())
{
var img = Dlib.LoadImage <RgbPixel>(file);
int number = 0;
var faces = fd.Operator(img);
foreach (var face in faces)
{
number += 1;
}
return(number);
}
}
public static void Recognize(string file)
{
using (var fd = Dlib.GetFrontalFaceDetector())
{
var img = Dlib.LoadImage <RgbPixel>(file);
//hola
var faces = fd.Operator(img);
foreach (var face in faces)
{
Dlib.DrawRectangle(img, face, color: new RgbPixel(0, 255, 255), thickness: 4);
}
Dlib.SaveJpeg(img, file);
}
}
/// <summary>
/// The main program entry point
/// </summary>
/// <param name="args">The command line arguments</param>
static void Main(string[] args)
{
// set up Dlib facedetector
using (var fd = Dlib.GetFrontalFaceDetector())
{
// load input image
var img = Dlib.LoadImage <RgbPixel>(inputFilePath);
// find all faces in the image
var faces = fd.Operator(img);
foreach (var face in faces)
{
// draw a rectangle for each face
Dlib.DrawRectangle(img, face, color: new RgbPixel(0, 255, 255), thickness: 4);
}
// export the modified image
Dlib.SaveJpeg(img, "output.jpg");
}
}
/// <summary>
/// 具体计算
/// </summary>
/// <param name="bitmaps"></param>
/// <returns></returns>
private static List <Rectangle[]> GetDate(List <Bitmap> bitmaps)
{
List <Rectangle[]> rectangles = new List <Rectangle[]>();
// 检测器
using (var detector = Dlib.GetFrontalFaceDetector())
{
// 循环所有的图片
foreach (var bitmap in bitmaps)
{
// 图片格式转化
using (var img = bitmap.ToArray2D <RgbPixel>())
{
// 获取位置数据
var dets = detector.Operator(img);
rectangles.Add(dets);
}
}
}
return(rectangles);
}
public void GetImage(string imagePath)
{
Array2D <RgbPixel> image = Dlib.LoadImage <RgbPixel>(imagePath);
using (FrontalFaceDetector fd = Dlib.GetFrontalFaceDetector())
{
var faces = fd.Operator(image);
foreach (DlibDotNet.Rectangle face in faces)
{
FullObjectDetection shape = _ShapePredictor.Detect(image, face);
ChipDetails faceChipDetail = Dlib.GetFaceChipDetails(shape, 150, 0.25);
Array2D <RgbPixel> faceChip = Dlib.ExtractImageChip <RgbPixel>(image, faceChipDetail);
Bitmap bitmap1 = faceChip.ToBitmap <RgbPixel>();
MainWindow.main.Statusa1 = bitmap1;
Dlib.DrawRectangle(image, face, color: new RgbPixel(0, 255, 255), thickness: 4);
}
}
Bitmap frame = image.ToBitmap <RgbPixel>();
MainWindow.main.Statusa = frame;
}
public static string TestCustomImage(string dir)
{
DataViewSchema predictionPipelineSchema;
ITransformer predictionPipeline = mlContext.Model.Load("model.zip", out predictionPipelineSchema);
PredictionEngine <FeatureInputData, ExpressionPrediction> predictionEngine = mlContext.Model.CreatePredictionEngine <FeatureInputData, ExpressionPrediction>(predictionPipeline);
var img = Dlib.LoadImage <RgbPixel>(dir);
// Set up Dlib Face Detector
using (var fd = Dlib.GetFrontalFaceDetector())
// ... and Dlib Shape Detector
using (var sp = ShapePredictor.Deserialize("shape_predictor_68_face_landmarks.dat"))
{
// find all faces in the image
var faces = fd.Operator(img);
// for each face draw over the facial landmarks
foreach (var face in faces)
{
// find the landmark points for this face
var shape = sp.Detect(img, face);
FeatureInputData inputData = new FeatureInputData
{
leftEyebrow = CalculateLeftEyebrow(shape),
rightEyebrow = CalculateRightEyebrow(shape),
leftLip = CalculateLeftLip(shape),
rightLip = CalculateRightLip(shape),
lipWidth = CalculateLipWidth(shape),
lipHeight = CalculateLipHeight(shape)
};
ExpressionPrediction prediction = predictionEngine.Predict(inputData);
return(prediction.expression.ToString());
}
}
return("N/A");
}
/// <summary>
/// 具体计算
/// </summary>
/// <param name="bitmap"></param>
/// <param name="sp"></param>
/// <returns></returns>
public List <FullObjectDetection> Face(Bitmap bitmap)
{
// 加载模型文件
if (sp == null)
{
var basePath = AppDomain.CurrentDomain.BaseDirectory;
sp = ShapePredictor.Deserialize(basePath + "ShapeModel/shape_predictor_68_face_landmarks.dat");
}
//var link = new ImageWindow.OverlayLine[0];
var shapes = new List <FullObjectDetection>();
using (var detector = Dlib.GetFrontalFaceDetector())
{
using (var img = bitmap.ToArray2D <RgbPixel>())
{
var dets = detector.Operator(img);
foreach (var rect in dets)
{
var shape = sp.Detect(img, rect);
if (shape.Parts > 2)
{
shapes.Add(shape);
}
}
//if (shapes.Any())
//{
// //就是这个
// var lines = Dlib.RenderFaceDetections(shapes);
// link = lines;
//}
}
}
return(shapes);
}
/// <summary>
/// The main program entry point
/// </summary>
/// <param name="args">The command line arguments</param>
static void Main(string[] args)
{
// set up Dlib facedetectors and shapedetectors
using (var fd = Dlib.GetFrontalFaceDetector())
using (var sp = ShapePredictor.Deserialize("shape_predictor_68_face_landmarks.dat"))
{
// load input image
var img = Dlib.LoadImage <RgbPixel>(inputFilePath);
// find all faces in the image
var faces = fd.Operator(img);
foreach (var face in faces)
{
// find the landmark points for this face
var shape = sp.Detect(img, face);
// build the 3d face model
var model = Utility.GetFaceModel();
// get the landmark point we need
var landmarks = new MatOfPoint2d(1, 6,
(from i in new int[] { 30, 8, 36, 45, 48, 54 }
let pt = shape.GetPart((uint)i)
select new OpenCvSharp.Point2d(pt.X, pt.Y)).ToArray());
// build the camera matrix
var cameraMatrix = Utility.GetCameraMatrix((int)img.Rect.Width, (int)img.Rect.Height);
// build the coefficient matrix
var coeffs = new MatOfDouble(4, 1);
coeffs.SetTo(0);
// find head rotation and translation
Mat rotation = new MatOfDouble();
Mat translation = new MatOfDouble();
Cv2.SolvePnP(model, landmarks, cameraMatrix, coeffs, rotation, translation);
// find euler angles
var euler = Utility.GetEulerMatrix(rotation);
// calculate head rotation in degrees
var yaw = 180 * euler.At <double>(0, 2) / Math.PI;
var pitch = 180 * euler.At <double>(0, 1) / Math.PI;
var roll = 180 * euler.At <double>(0, 0) / Math.PI;
// looking straight ahead wraps at -180/180, so make the range smooth
pitch = Math.Sign(pitch) * 180 - pitch;
// calculate if the driver is facing forward
// the left/right angle must be in the -25..25 range
// the up/down angle must be in the -10..10 range
var facingForward =
yaw >= -25 && yaw <= 25 &&
pitch >= -10 && pitch <= 10;
// create a new model point in front of the nose, and project it into 2d
var poseModel = new MatOfPoint3d(1, 1, new Point3d(0, 0, 1000));
var poseProjection = new MatOfPoint2d();
Cv2.ProjectPoints(poseModel, rotation, translation, cameraMatrix, coeffs, poseProjection);
// draw the key landmark points in yellow on the image
foreach (var i in new int[] { 30, 8, 36, 45, 48, 54 })
{
var point = shape.GetPart((uint)i);
var rect = new Rectangle(point);
Dlib.DrawRectangle(img, rect, color: new RgbPixel(255, 255, 0), thickness: 4);
}
// draw a line from the tip of the nose pointing in the direction of head pose
var landmark = landmarks.At <Point2d>(0);
var p = poseProjection.At <Point2d>(0);
Dlib.DrawLine(
img,
new DlibDotNet.Point((int)landmark.X, (int)landmark.Y),
new DlibDotNet.Point((int)p.X, (int)p.Y),
color: new RgbPixel(0, 255, 255));
// draw a box around the face if it's facing forward
if (facingForward)
{
Dlib.DrawRectangle(img, face, color: new RgbPixel(0, 255, 255), thickness: 4);
}
}
// export the modified image
Dlib.SaveJpeg(img, "output.jpg");
}
}
private void Test(Bitmap bitmap)
{
var rvec = new double[] { 0, 0, 0 };
var tvec = new double[] { 0, 0, 0 };
//FullObjectDetection shape = null;
using (var detector = Dlib.GetFrontalFaceDetector())
using (var img = bitmap.ToArray2D <RgbPixel>())
{
//获取位置数据
var dets = detector.Operator(img);
// 循环人脸数据
foreach (var rect in dets)
{
// 特征点检测
var shape = _SP.Detect(img, rect);
var focal_length = (double)bitmap.Width; // 图片的宽度
var center = ((double)bitmap.Width / 2.0, (double)bitmap.Height / 2.0); //图片的宽度/2，图片的高度/2 中心点
var p1 = shape.GetPart(0);
var p2 = shape.GetPart(16);
var dx = (double)(p2.X - p1.X);
var dy = (double)(p2.Y - p1.Y);
var num = (dy / dx);
var aa = Math.Tan(num);
var bb = aa * 180;
var cc = bb / Math.PI;
var nA = (Math.Atan(dy / dx)) * 180 / Math.PI;
// 需要进行改变
var cameraMatrix = new double[3, 3]
{
{ focal_length, 0, center.Item1 },
{ 0, focal_length, center.Item2 },
{ 0, 0, 1 }
};
var dist = new double[] { 0, 0, 0, 0, 0 };
// 基础点
var objPts = new Point3f[]
{
new Point3f(0.0f, 0.0f, 0.0f), // Nose tip
new Point3f(0.0f, -330.0f, -65.0f), // Chin
new Point3f(-225.0f, 170.0f, -135.0f), // Left eye left corner
new Point3f(225.0f, 170.0f, -135.0f), // Right eye right corne
new Point3f(-150.0f, -150.0f, -125.0f), // Left Mouth corner
new Point3f(150.0f, -150.0f, -125.0f) // Right mouth corner
};
// 这个参数
double[,] jacobian = new double[4, 1];
// 人脸的位置
var imgPts = new Point2f[]
{
new Point2f(shape.GetPart(30).X, shape.GetPart(30).Y), // Nose tip
new Point2f(shape.GetPart(8).X, shape.GetPart(8).Y), // Chin
new Point2f(shape.GetPart(36).X, shape.GetPart(36).Y), // Left eye left corner
new Point2f(shape.GetPart(45).X, shape.GetPart(45).Y), // Right eye right corne
new Point2f(shape.GetPart(48).X, shape.GetPart(48).Y), // Left Mouth corner
new Point2f(shape.GetPart(54).X, shape.GetPart(54).Y), // Right mouth corner
};
//var imgPts = new Point2f[]
//{
// new Point2f(359, 391), // Nose tip
// new Point2f(399, 561), // Chin
// new Point2f(337, 297), // Left eye left corner
// new Point2f(513, 301), // Right eye right corne
// new Point2f(345, 465), // Left Mouth corner
// new Point2f(453, 469) // Right mouth corner
//};
Cv2.SolvePnP(objPts, imgPts, cameraMatrix, dist, out rvec, out tvec, flags: SolvePnPFlags.Iterative);
GetEulerAngle(rvec);
var arr = new List <Point3f>()
{
new Point3f(0.0f, 0.0f, 1000.0f)
};
Cv2.ProjectPoints(arr, rvec, tvec, cameraMatrix, dist, out imgPts, out jacobian);
Cv2.Rodrigues(rvec, out cameraMatrix);
var im = Cv2.ImRead("headPose.jpg");
Cv2.Line(im, (int)shape.GetPart(30).X, (int)shape.GetPart(30).Y, (int)imgPts[0].X, (int)imgPts[0].Y, Scalar.Blue, (int)LineTypes.Link8);
Cv2.ImShow("output", im);
Cv2.WaitKey(0);
//Cv2.Line(im, 0, 0, 0, 0, Scalar.All(255));
}
}
}
private static InputDataImages GetFeaturesValuesFromImage(string str)
{
var returnClass = new InputDataImages();
using (var fd = Dlib.GetFrontalFaceDetector())
// ... and Dlib Shape DetectorS
using (var sp = ShapePredictor.Deserialize("shape_predictor_68_face_landmarks.dat"))
{
// load input image
var img = Dlib.LoadImage <RgbPixel>(str);
// find all faces i n the image
var faces = fd.Operator(img);
// for each face draw over the facial landmarks
// Create the CSV file and fill in the first line with the header
foreach (var face in faces)
{
// find the landmark points for this face
var shape = sp.Detect(img, face);
// draw the landmark points on the image
for (var i = 0; i < shape.Parts; i++)
{
var point = shape.GetPart((uint)i);
var rect = new Rectangle(point);
Dlib.DrawRectangle(img, rect, color: new RgbPixel(255, 255, 0), thickness: 4);
}
/////////////// WEEK 9 LAB ////////////////
double[] LeftEyebrowDistances = new double[4];
double[] RightEyebrowDistances = new double[4];
float LeftEyebrowSum = 0;
float RightEyebrowSum = 0;
//LIP VARIABLES
double[] LeftLipDistances = new double[4];
double[] RightLipDistances = new double[4];
float LeftLipSum = 0;
float RightLipSum = 0;
LeftEyebrowDistances[0] = (shape.GetPart(21) - shape.GetPart(39)).Length;
LeftEyebrowDistances[1] = (shape.GetPart(20) - shape.GetPart(39)).Length;
LeftEyebrowDistances[2] = (shape.GetPart(19) - shape.GetPart(39)).Length;
LeftEyebrowDistances[3] = (shape.GetPart(18) - shape.GetPart(39)).Length;
RightEyebrowDistances[0] = (shape.GetPart(22) - shape.GetPart(42)).Length;
RightEyebrowDistances[1] = (shape.GetPart(23) - shape.GetPart(42)).Length;
RightEyebrowDistances[2] = (shape.GetPart(24) - shape.GetPart(42)).Length;
RightEyebrowDistances[3] = (shape.GetPart(25) - shape.GetPart(42)).Length;
//LIP
LeftLipDistances[0] = (shape.GetPart(51) - shape.GetPart(33)).Length;
LeftLipDistances[1] = (shape.GetPart(50) - shape.GetPart(33)).Length;
LeftLipDistances[2] = (shape.GetPart(49) - shape.GetPart(33)).Length;
LeftLipDistances[3] = (shape.GetPart(48) - shape.GetPart(33)).Length;
RightLipDistances[0] = (shape.GetPart(51) - shape.GetPart(33)).Length;
RightLipDistances[1] = (shape.GetPart(52) - shape.GetPart(33)).Length;
RightLipDistances[2] = (shape.GetPart(53) - shape.GetPart(33)).Length;
RightLipDistances[3] = (shape.GetPart(54) - shape.GetPart(33)).Length;
for (int i = 0; i < 4; i++)
{
LeftEyebrowSum += (float)(LeftEyebrowDistances[i] / LeftEyebrowDistances[0]);
RightEyebrowSum += (float)(RightEyebrowDistances[i] / RightEyebrowDistances[0]);
}
LeftLipSum += (float)(LeftLipDistances[1] / LeftLipDistances[0]);
LeftLipSum += (float)(LeftLipDistances[2] / LeftLipDistances[0]);
LeftLipSum += (float)(LeftLipDistances[3] / LeftLipDistances[0]);
RightLipSum += (float)(RightLipDistances[1] / RightLipDistances[0]);
RightLipSum += (float)(RightLipDistances[2] / RightLipDistances[0]);
RightLipSum += (float)(RightLipDistances[3] / RightLipDistances[0]);
double LipWidth = (float)((shape.GetPart(48) - shape.GetPart(54)).Length / (shape.GetPart(33) - shape.GetPart(51)).Length);
double LipHeight = (float)((shape.GetPart(51) - shape.GetPart(57)).Length / (shape.GetPart(33) - shape.GetPart(51)).Length);
returnClass.LeftEyebrow = LeftEyebrowSum;
returnClass.RightEyebrow = RightLipSum;
returnClass.LeftLip = LeftLipSum;
returnClass.RightLip = RightLipSum;
returnClass.LipWidth = (float)LipWidth;
returnClass.LipHeight = (float)LipHeight;
// export the modified image
string filePath = "output" + ".jpg";
Dlib.SaveJpeg(img, filePath);
}
}
using (System.IO.StreamWriter file = new System.IO.StreamWriter(@"TestingFeatureVectorValues.csv", true))
{
DirectoryInfo dr = new DirectoryInfo(str);
//Console.WriteLine(dr.Parent.Name.ToString());
string ParentFolderName = dr.Parent.Name.ToString();
file.WriteLine(ParentFolderName + "," + returnClass.LeftEyebrow.ToString() + "," + returnClass.RightEyebrow.ToString()
+ "," + returnClass.LeftLip.ToString() + "," + returnClass.RightLip.ToString() + "," + returnClass.LipWidth.ToString()
+ "," + returnClass.LipHeight.ToString());
}
return(returnClass);
}
// The main program entry point
static void Main(string[] args)
{
bool use_mirror = false;
// file paths
string[] files = Directory.GetFiles("images", "*.*", SearchOption.AllDirectories);
List <FullObjectDetection> shapes = new List <FullObjectDetection>();
List <string> emotions = new List <string>();
// Set up Dlib Face Detector
using (var fd = Dlib.GetFrontalFaceDetector())
// ... and Dlib Shape Detector
using (var sp = ShapePredictor.Deserialize("shape_predictor_68_face_landmarks.dat"))
{
// load input image
for (int i = 0; i < files.Length; i++)
{
var emotion = GetEmotion(files[i]);
var img = Dlib.LoadImage <RgbPixel>(files[i]);
// find all faces in the image
var faces = fd.Operator(img);
// for each face draw over the facial landmarks
foreach (var face in faces)
{
// find the landmark points for this face
var shape = sp.Detect(img, face);
shapes.Add(shape);
emotions.Add(emotion);
// draw the landmark points on the image
for (var i2 = 0; i2 < shape.Parts; i2++)
{
var point = shape.GetPart((uint)i2);
var rect = new Rectangle(point);
if (point == GetPoint(shape, 40) || point == GetPoint(shape, 22))
{
Dlib.DrawRectangle(img, rect, color: new RgbPixel(0, 255, 0), thickness: 4);
}
else
{
Dlib.DrawRectangle(img, rect, color: new RgbPixel(255, 255, 0), thickness: 4);
}
}
}
// export the modified image
Console.WriteLine(files[i]);
Dlib.SaveJpeg(img, "output_" + files[i]);
}
string header = "leftEyebrow,rightEyebrow,leftLip,rightLip,lipHeight,lipWidth,emotion\n";
System.IO.File.WriteAllText(@"feature_vectors.csv", header);
for (var i = 0; i < shapes.Count; i++)
{
var shape = shapes[i];
var emotion = emotions[i];
using (System.IO.StreamWriter file = new System.IO.StreamWriter(@"feature_vectors.csv", true))
{
file.WriteLine(GetLeftEyebrow(shape) + "," + GetRightEyebrow(shape) + "," +
GetLeftLip(shape) + "," + GetRightLip(shape) + "," + GetLipWidth(shape) + "," + GetLipHeight(shape) +
"," + emotion);
if (use_mirror)
{
file.WriteLine(GetRightEyebrow(shape) + "," + GetLeftEyebrow(shape) + "," +
GetRightLip(shape) + "," + GetLeftLip(shape) + "," + GetLipWidth(shape) + "," + GetLipHeight(shape) +
"," + emotion);
}
}
}
}
}
/// <summary>
/// Predict the emotion of an image.
/// </summary>
/// <param name="imageFileInfo"><see cref="FileInfo"/> of the image file.</param>
/// <param name="TFaceData">Type of face data that the parameters should be used.</param>
/// <param name="predictedEmotion">The emotion that was predicted.</param>
/// <param name="predictedEmotionWithAllLabels">All the other emotions with their scores appended after.</param>
public static void PredictEmotion(FileInfo imageFileInfo, Type TFaceData, out FaceOutput predictedEmotion, out Dictionary <string, float> predictedEmotionWithAllLabels)
{
if (mlContext == null)
{
mlContext = new MLContext();
}
if (model == null)
{
model = mlContext.Model.Load(GetModelZipFileName(TFaceData), out var dataView);
}
predictedEmotion = null;
predictedEmotionWithAllLabels = null;
// Not using generics because different function calls are required anyway.
if (TFaceData == typeof(FaceData1))
{
using (var predictor = mlContext.Model.CreatePredictionEngine <FaceData1, FaceOutput>(model))
{
using (var fd = Dlib.GetFrontalFaceDetector())
using (var sp = ShapePredictor.Deserialize(GetFile(ShapePredictorFileName).FullName))
{
var faceDataFromImage = GetFaceData1FromImage(imageFileInfo, sp, fd, false);
faceDataFromImage.Emotion = ""; // Get rid of label, as this is what we want to know.
predictedEmotion = predictor.Predict(faceDataFromImage);
}
// Prediction with all labels.
predictedEmotionWithAllLabels = new Dictionary <string, float>();
var slotNames = new VBuffer <ReadOnlyMemory <char> >();
predictor.OutputSchema.GetColumnOrNull("Label")?.GetKeyValues(ref slotNames);
var names = new string[slotNames.Length];
var num = 0;
foreach (var denseValue in slotNames.DenseValues())
{
predictedEmotionWithAllLabels.Add(denseValue.ToString(), predictedEmotion.Scores[num++]);
}
Console.WriteLine("Predicted Emotion: " + predictedEmotion.PredictedEmotion);
Console.WriteLine($"Scores: {string.Join(" ", predictedEmotion.Scores)}");
}
}
else if (TFaceData == typeof(FaceData2))
{
using (var predictor = mlContext.Model.CreatePredictionEngine <FaceData2, FaceOutput>(model))
{
using (var fd = Dlib.GetFrontalFaceDetector())
using (var sp = ShapePredictor.Deserialize(GetFile(ShapePredictorFileName).FullName))
{
var faceDataFromImage = GetFaceData2FromImage(imageFileInfo, sp, fd, false);
faceDataFromImage.Emotion = ""; // Get rid of label, as this is what we want to know.
predictedEmotion = predictor.Predict(faceDataFromImage);
}
// Prediction with all labels.
predictedEmotionWithAllLabels = new Dictionary <string, float>();
var slotNames = new VBuffer <ReadOnlyMemory <char> >();
predictor.OutputSchema.GetColumnOrNull("Label")?.GetKeyValues(ref slotNames);
var names = new string[slotNames.Length];
var num = 0;
foreach (var denseValue in slotNames.DenseValues())
{
predictedEmotionWithAllLabels.Add(denseValue.ToString(), predictedEmotion.Scores[num++]);
}
Console.WriteLine("Predicted Emotion: " + predictedEmotion.PredictedEmotion);
Console.WriteLine($"Scores: {string.Join(" ", predictedEmotion.Scores)}");
}
}
else if (TFaceData == typeof(FaceData3))
{
using (var predictor = mlContext.Model.CreatePredictionEngine <FaceData3, FaceOutput>(model))
{
using (var fd = Dlib.GetFrontalFaceDetector())
using (var sp = ShapePredictor.Deserialize(GetFile(ShapePredictorFileName).FullName))
{
var faceDataFromImage = GetFaceData3FromImage(imageFileInfo, sp, fd, false);
faceDataFromImage.Emotion = ""; // Get rid of label, as this is what we want to know.
predictedEmotion = predictor.Predict(faceDataFromImage);
}
// Prediction with all labels.
predictedEmotionWithAllLabels = new Dictionary <string, float>();
var slotNames = new VBuffer <ReadOnlyMemory <char> >();
predictor.OutputSchema.GetColumnOrNull("Label")?.GetKeyValues(ref slotNames);
var names = new string[slotNames.Length];
var num = 0;
foreach (var denseValue in slotNames.DenseValues())
{
predictedEmotionWithAllLabels.Add(denseValue.ToString(), predictedEmotion.Scores[num++]);
}
Console.WriteLine("Predicted Emotion: " + predictedEmotion.PredictedEmotion);
Console.WriteLine($"Scores: {string.Join(" ", predictedEmotion.Scores)}");
}
}
}
static void Main(string[] args)
{
/// FaceDetectionWith_API
Location[] coord = TestImage(fileName, Model.Hog);
/// Face DetectionWith_DLIB
using (var fd = Dlib.GetFrontalFaceDetector())
{
var img = Dlib.LoadImage <RgbPixel>(fileName);
// find all faces in the image
var faces = fd.Operator(img);
foreach (var face in faces)
{
// draw a rectangle for each face
Dlib.DrawRectangle(img, face, color: new RgbPixel(0, 255, 255), thickness: 4);
}
Dlib.SaveJpeg(img, outputName);
}
// The first thing we are going to do is load all our models. First, since we need to
// find faces in the image we will need a face detector:
using (var detector = Dlib.GetFrontalFaceDetector())
// We will also use a face landmarking model to align faces to a standard pose: (see face_landmark_detection_ex.cpp for an introduction)
using (var sp = ShapePredictor.Deserialize("shape_predictor_68_face_landmarks.dat"))
// And finally we load the DNN responsible for face recognition.
using (var net = DlibDotNet.Dnn.LossMetric.Deserialize("dlib_face_recognition_resnet_model_v1.dat"))
using (var img = Dlib.LoadImageAsMatrix <RgbPixel>(fileName))
using (var win = new ImageWindow(img))
{
var faces = new List <Matrix <RgbPixel> >();
foreach (var face in detector.Operator(img))
{
var shape = sp.Detect(img, face);
var faceChipDetail = Dlib.GetFaceChipDetails(shape, 150, 0.25);
var faceChip = Dlib.ExtractImageChip <RgbPixel>(img, faceChipDetail);
//faces.Add(move(face_chip));
faces.Add(faceChip);
win.AddOverlay(face);
}
if (!faces.Any())
{
Console.WriteLine("No faces found in image!");
return;
}
// This call asks the DNN to convert each face image in faces into a 128D vector.
// In this 128D vector space, images from the same person will be close to each other
// but vectors from different people will be far apart. So we can use these vectors to
// identify if a pair of images are from the same person or from different people.
var faceDescriptors = net.Operator(faces);
// In particular, one simple thing we can do is face clustering. This next bit of code
// creates a graph of connected faces and then uses the Chinese whispers graph clustering
// algorithm to identify how many people there are and which faces belong to whom.
var edges = new List <SamplePair>();
for (uint i = 0; i < faceDescriptors.Count; ++i)
{
for (var j = i; j < faceDescriptors.Count; ++j)
{
// Faces are connected in the graph if they are close enough. Here we check if
// the distance between two face descriptors is less than 0.6, which is the
// decision threshold the network was trained to use. Although you can
// certainly use any other threshold you find useful.
var diff = faceDescriptors[i] - faceDescriptors[j];
if (Dlib.Length(diff) < 0.6)
{
edges.Add(new SamplePair(i, j));
}
}
}
Dlib.ChineseWhispers(edges, 100, out var numClusters, out var labels);
// This will correctly indicate that there are 4 people in the image.
Console.WriteLine($"number of people found in the image: {numClusters}");
// Отобразим результат в ImageList
var winClusters = new List <ImageWindow>();
for (var i = 0; i < numClusters; i++)
{
winClusters.Add(new ImageWindow());
}
var tileImages = new List <Matrix <RgbPixel> >();
for (var clusterId = 0ul; clusterId < numClusters; ++clusterId)
{
var temp = new List <Matrix <RgbPixel> >();
for (var j = 0; j < labels.Length; ++j)
{
if (clusterId == labels[j])
{
temp.Add(faces[j]);
}
}
winClusters[(int)clusterId].Title = $"face cluster {clusterId}";
var tileImage = Dlib.TileImages(temp);
tileImages.Add(tileImage);
winClusters[(int)clusterId].SetImage(tileImage);
}
// Finally, let's print one of the face descriptors to the screen.
using (var trans = Dlib.Trans(faceDescriptors[0]))
{
Console.WriteLine($"face descriptor for one face: {trans}");
// It should also be noted that face recognition accuracy can be improved if jittering
// is used when creating face descriptors. In particular, to get 99.38% on the LFW
// benchmark you need to use the jitter_image() routine to compute the descriptors,
// like so:
var jitterImages = JitterImage(faces[0]).ToArray();
var ret = net.Operator(jitterImages);
using (var m = Dlib.Mat(ret))
using (var faceDescriptor = Dlib.Mean <float>(m))
using (var t = Dlib.Trans(faceDescriptor))
{
Console.WriteLine($"jittered face descriptor for one face: {t}");
// If you use the model without jittering, as we did when clustering the bald guys, it
// gets an accuracy of 99.13% on the LFW benchmark. So jittering makes the whole
// procedure a little more accurate but makes face descriptor calculation slower.
Console.WriteLine("hit enter to terminate");
Console.ReadKey();
foreach (var jitterImage in jitterImages)
{
jitterImage.Dispose();
}
foreach (var tileImage in tileImages)
{
tileImage.Dispose();
}
foreach (var edge in edges)
{
edge.Dispose();
}
foreach (var descriptor in faceDescriptors)
{
descriptor.Dispose();
}
foreach (var face in faces)
{
face.Dispose();
}
}
}
}
System.Console.ReadLine();
}
public static void CreateFeatureVectors()
{
int faceCount = 0;
float leftEyebrow, rightEyebrow, leftLip, rightLip, lipHeight, lipWidth;
string output;
if (currentDataType == Datatype.Testing)
{
output = testingOutput;
}
else
{
output = trainingOutput;
}
string[] dirs = Directory.GetFiles(currentFilePath, "*.*", SearchOption.AllDirectories);
// Set up Dlib Face Detector
using (var fd = Dlib.GetFrontalFaceDetector())
// ... and Dlib Shape Detector
using (var sp = ShapePredictor.Deserialize("shape_predictor_68_face_landmarks.dat"))
{
string header = "leftEyebrow,rightEyebrow,leftLip,rightLip,lipWidth,lipHeight,label\n";
// Create the CSV file and fill in the first line with the header
System.IO.File.WriteAllText(output, header);
foreach (string dir in dirs)
{
// call function that sets the label based on what the filename contains
string label = DetermineLabel(dir);
// load input image
if (!(dir.EndsWith("png") || dir.EndsWith("jpg")))
{
continue;
}
var img = Dlib.LoadImage <RgbPixel>(dir);
// find all faces in the image
var faces = fd.Operator(img);
// for each face draw over the facial landmarks
foreach (var face in faces)
{
// Write to the console displaying the progress and current emotion
Form1.SetProgress(faceCount, dirs.Length - 1);
// find the landmark points for this face
var shape = sp.Detect(img, face);
for (var i = 0; i < shape.Parts; i++)
{
RgbPixel colour = new RgbPixel(255, 255, 255);
var point = shape.GetPart((uint)i);
var rect = new DlibDotNet.Rectangle(point);
Dlib.DrawRectangle(img, rect, color: colour, thickness: 2);
}
SetFormImage(img);
leftEyebrow = CalculateLeftEyebrow(shape);
rightEyebrow = CalculateRightEyebrow(shape);
leftLip = CalculateLeftLip(shape);
rightLip = CalculateRightLip(shape);
lipWidth = CalculateLipWidth(shape);
lipHeight = CalculateLipHeight(shape);
using (System.IO.StreamWriter file = new System.IO.StreamWriter(output, true))
{
file.WriteLine(leftEyebrow + "," + rightEyebrow + "," + leftLip + "," + rightLip + "," + lipWidth + "," + lipHeight + "," + label);
}
// Increment count used for console output
faceCount++;
}
}
if (currentDataType == Datatype.Testing)
{
var testDataView = mlContext.Data.LoadFromTextFile <FeatureInputData>(output, hasHeader: true, separatorChar: ',');
GenerateMetrics(testDataView);
}
Form1.HideImage();
}
}
private static int Main(string[] args)
{
var app = new CommandLineApplication(false);
app.Name = nameof(AgeTraining);
app.Description = "The program for training Adience OUI Unfiltered faces for gender and age classification dataset";
app.HelpOption("-h|--help");
app.Command("train", command =>
{
const uint epochDefault = 300;
const double learningRateDefault = 0.001d;
const double minLearningRateDefault = 0.00001d;
const uint minBatchSizeDefault = 256;
const uint validationDefault = 30;
var datasetOption = command.Option("-d|--dataset", "The directory of dataset", CommandOptionType.SingleValue);
var epochOption = command.Option("-e|--epoch", $"The epoch. Default is {epochDefault}", CommandOptionType.SingleValue);
var learningRateOption = command.Option("-l|--lr", $"The learning rate. Default is {learningRateDefault}", CommandOptionType.SingleValue);
var minLearningRateOption = command.Option("-m|--min-lr", $"The minimum learning rate. Default is {minLearningRateDefault}", CommandOptionType.SingleValue);
var minBatchSizeOption = command.Option("-b|--min-batchsize", $"The minimum batch size. Default is {minBatchSizeDefault}", CommandOptionType.SingleValue);
var validationOption = command.Option("-v|--validation-interval", $"The interval of validation. Default is {validationDefault}", CommandOptionType.SingleValue);
var useMeanOption = command.Option("-u|--use-mean", "Use mean image", CommandOptionType.NoValue);
command.OnExecute(() =>
{
var dataset = datasetOption.Value();
if (!datasetOption.HasValue() || !Directory.Exists(dataset))
{
Console.WriteLine("dataset does not exist");
return(-1);
}
var epoch = epochDefault;
if (epochOption.HasValue() && !uint.TryParse(epochOption.Value(), out epoch))
{
Console.WriteLine("epoch is invalid value");
return(-1);
}
var learningRate = learningRateDefault;
if (learningRateOption.HasValue() && !double.TryParse(learningRateOption.Value(), NumberStyles.Float, Thread.CurrentThread.CurrentCulture.NumberFormat, out learningRate))
{
Console.WriteLine("learning rate is invalid value");
return(-1);
}
var minLearningRate = minLearningRateDefault;
if (minLearningRateOption.HasValue() && !double.TryParse(minLearningRateOption.Value(), NumberStyles.Float, Thread.CurrentThread.CurrentCulture.NumberFormat, out minLearningRate))
{
Console.WriteLine("minimum learning rate is invalid value");
return(-1);
}
var minBatchSize = minBatchSizeDefault;
if (minBatchSizeOption.HasValue() && !uint.TryParse(minBatchSizeOption.Value(), out minBatchSize))
{
Console.WriteLine("minimum batch size is invalid value");
return(-1);
}
var validation = validationDefault;
if (validationOption.HasValue() && !uint.TryParse(validationOption.Value(), out validation) || validation == 0)
{
Console.WriteLine("validation interval is invalid value");
return(-1);
}
var useMean = useMeanOption.HasValue();
Console.WriteLine($" Dataset: {dataset}");
Console.WriteLine($" Epoch: {epoch}");
Console.WriteLine($" Learning Rate: {learningRate}");
Console.WriteLine($" Min Learning Rate: {minLearningRate}");
Console.WriteLine($" Min Batch Size: {minBatchSize}");
Console.WriteLine($"Validation Interval: {validation}");
Console.WriteLine($" Use Mean: {useMean}");
Console.WriteLine();
var baseName = $"adience-age-network_{epoch}_{learningRate}_{minLearningRate}_{minBatchSize}_{useMean}";
Train(baseName, dataset, epoch, learningRate, minLearningRate, minBatchSize, validation, useMean);
return(0);
});
});
app.Command("test", command =>
{
var datasetOption = command.Option("-d|--dataset", "The directory of dataset", CommandOptionType.SingleValue);
var modelOption = command.Option("-m|--model", "The model file.", CommandOptionType.SingleValue);
command.OnExecute(() =>
{
var dataset = datasetOption.Value();
if (!datasetOption.HasValue() || !Directory.Exists(dataset))
{
Console.WriteLine("dataset does not exist");
return(-1);
}
var model = modelOption.Value();
if (!datasetOption.HasValue() || !File.Exists(model))
{
Console.WriteLine("model does not exist");
return(-1);
}
Console.WriteLine($"Dataset: {dataset}");
Console.WriteLine($" Model: {model}");
Console.WriteLine();
Test(dataset, model);
return(0);
});
});
app.Command("preprocess", command =>
{
var datasetOption = command.Option("-d|--dataset", "The directory of dataset", CommandOptionType.SingleValue);
var outputOption = command.Option("-o|--output", "The path to output preprocessed dataset", CommandOptionType.SingleValue);
command.OnExecute(() =>
{
var dataset = datasetOption.Value();
if (!datasetOption.HasValue() || !Directory.Exists(dataset))
{
Console.WriteLine("dataset does not exist");
return(-1);
}
var output = outputOption.Value();
if (!outputOption.HasValue())
{
Console.WriteLine("output does not specify");
return(-1);
}
Directory.CreateDirectory(output);
var types = new[]
{
"train", "test"
};
foreach (var type in types)
{
var imageDir = Path.Combine(dataset, type);
if (!Directory.Exists(imageDir))
{
Console.WriteLine($"{imageDir} does not exist");
return(-1);
}
var csv = Path.Combine(dataset, $"{type}.csv");
if (!File.Exists(csv))
{
Console.WriteLine($"{csv} does not exist");
return(-1);
}
File.Copy(csv, Path.Combine(output, $"{type}.csv"), true);
Directory.CreateDirectory(Path.Combine(output, type));
}
Console.WriteLine($"Dataset: {dataset}");
Console.WriteLine($" Output: {output}");
Console.WriteLine();
using (var posePredictor = ShapePredictor.Deserialize("shape_predictor_5_face_landmarks.dat"))
using (var faceDetector = Dlib.GetFrontalFaceDetector())
{
foreach (var type in types)
{
Preprocess(type, dataset, faceDetector, posePredictor, output);
}
}
return(0);
});
});
return(app.Execute(args));
}
private void BackgroundWorkerOnDoWork(object sender, DoWorkEventArgs doWorkEventArgs)
{
var path = doWorkEventArgs.Argument as string;
if (string.IsNullOrWhiteSpace(path) || !File.Exists(path))
{
return;
}
using (var faceDetector = Dlib.GetFrontalFaceDetector())
using (var img = Dlib.LoadImage <RgbPixel>(path))
{
Dlib.PyramidUp(img);
var dets = faceDetector.Operator(img);
var shapes = new List <FullObjectDetection>();
foreach (var rect in dets)
{
var shape = this._ShapePredictor.Detect(img, rect);
if (shape.Parts <= 2)
{
continue;
}
shapes.Add(shape);
}
if (shapes.Any())
{
var lines = Dlib.RenderFaceDetections(shapes);
foreach (var line in lines)
{
Dlib.DrawLine(img, line.Point1, line.Point2, new RgbPixel
{
Green = 255
});
}
var wb = img.ToBitmap();
this.pictureBoxImage.Image?.Dispose();
this.pictureBoxImage.Image = wb;
foreach (var l in lines)
{
l.Dispose();
}
var chipLocations = Dlib.GetFaceChipDetails(shapes);
using (var faceChips = Dlib.ExtractImageChips <RgbPixel>(img, chipLocations))
using (var tileImage = Dlib.TileImages(faceChips))
{
// It is NOT necessary to re-convert WriteableBitmap to Matrix.
// This sample demonstrate converting managed image class to
// dlib class and vice versa.
using (var tile = tileImage.ToBitmap())
using (var mat = tile.ToMatrix <RgbPixel>())
{
var tile2 = mat.ToBitmap();
this.pictureBoxTileImage.Image?.Dispose();
this.pictureBoxTileImage.Image = tile2;
}
}
foreach (var c in chipLocations)
{
c.Dispose();
}
}
foreach (var s in shapes)
{
s.Dispose();
}
}
}
/// <summary>
/// Extract features from images, and store them in a csv file at the .exe directory.
/// </summary>
/// <param name="faceData">Type of face data that will be stored.</param>
/// <seealso cref="FaceData1"/>
/// <seealso cref="FaceData2"/>
/// <seealso cref="FaceData3"/>
public static void ExtractFeatures(Type faceData)
{
// Setup CSV file
string header = $"Emotion, Mode: {faceData.ToString()}\n";
File.WriteAllText(GetFacialFeaturesFileName(faceData), header);
StreamWriter csvFile = new StreamWriter(GetFacialFeaturesFileName(faceData), true);
using (var fd = Dlib.GetFrontalFaceDetector())
using (var sp = ShapePredictor.Deserialize(GetFile(ShapePredictorFileName).FullName))
{
// Get all images
DirectoryInfo mugImgDirInfo = GetDirectory("MUG Images");
DirectoryInfo googleImgDirInfo = GetDirectory("Google Set");
DirectoryInfo cohnKanadeeImgDirInfo = GetDirectory("Cohn-Kanade Images");
List <FileInfo> imageFiles = new List <FileInfo>();
foreach (var directoryInfo in cohnKanadeeImgDirInfo.GetDirectories())
{
imageFiles.AddRange(directoryInfo.GetFiles("*.png"));
}
//foreach (var directoryInfo in googleImgDirInfo.GetDirectories())
//{
// imageFiles.AddRange(directoryInfo.GetFiles("*.jpg"));
//}
//imageFiles.AddRange(mugImgDirInfo.GetFiles("*.jpg"));
foreach (var imageFile in imageFiles)
{
if (faceData == typeof(FaceData1))
{
var faceData1 = GetFaceData1FromImage(imageFile, sp, fd);
if (faceData1 == null)
{
continue;
}
// Write to CSV
csvFile.WriteLine(faceData1.Emotion + "," + faceData1.LeftEyebrow + "," + faceData1.RightEyebrow +
"," + faceData1.LeftLip + "," + faceData1.RightLip +
"," + faceData1.LipHeight + "," + faceData1.LipWidth);
}
else if (faceData == typeof(FaceData2))
{
var faceData2 = GetFaceData2FromImage(imageFile, sp, fd);
if (faceData2 == null)
{
continue;
}
csvFile.Write($"{faceData2.Emotion},");
foreach (var rawCoordsX in faceData2.RawCoordiantesX)
{
csvFile.Write($"{rawCoordsX},");
}
foreach (var rawCoordsY in faceData2.RawCoordiantesY)
{
csvFile.Write($"{rawCoordsY},");
}
foreach (var angleOfFeature in faceData2.AngleBetweenFeatures)
{
csvFile.Write($"{angleOfFeature},");
}
foreach (var lengthOfFeature in faceData2.LengthBetweenFeatures)
{
csvFile.Write($"{lengthOfFeature},");
}
csvFile.Write("\n");
}
else if (faceData == typeof(FaceData3))
{
var faceData3 = GetFaceData3FromImage(imageFile, sp, fd);
if (faceData3 == null)
{
continue;
}
csvFile.WriteLine(
$"{faceData3.Emotion},{faceData3.LeftEyebrowDistance},{faceData3.RightEyebrowDistance},{faceData3.LeftEyeWidth},{faceData3.RightEyeWidth},{faceData3.LeftEyeHeight},{faceData3.RightEyeHeight},{faceData3.OuterLipWidth},{faceData3.InnerLipWidth},{faceData3.OuterLipHeight},{faceData3.InnerLipHeight},{faceData3.LeftLipEdgeAngle},{faceData3.RightLipEdgeAngle}");
}
else
{
throw new ArgumentException("Invalid TFaceData.", "faceData");
}
}
// Close file
csvFile.Close();
}
}