IInputArray image parameter for face detection in emgucv in c# using haarcascade

Question

I have installed emgu.cv 3.2 (new version) and visual studio 2012 and for the face detection using windows form application I tried to used haarcascade. I have done the referencing

(Emgu.CV.DebuggerVisualizers.VS2012.dll, Emgu.CV.UI.dll, Emgu.CV.UI.GL.dll, Emgu.CV.World.dll)

and add existing

(opencv_ffmpeg320.dll and others)

. The new version of emgu.cv seems to have changed some names of methods like Capture replaced by VideoCapture. But still, I am stuck to complete the face detection code below (last code). What should I do to put IInputArray image parameter on DetectMultiScale(). Please help!

    capture = new VideoCapture(0);
    haar = new CascadeClassifier("haarcascade_frontalface_default.xml");

    Image<Bgr, byte> nextFrame = capture.QueryFrame().ToImage<Bgr, byte>()
    Image<Gray, byte> grayframe = nextFrame.Convert<Gray, byte>();
     // stuck here below to put IInputArray image    
                        var faces = haar.DetectMultiScale( , 1.1, 10, 
                          Emgu.CV.CvEnum.HaarDetectionType.DoCannyPruning,  
                          new Size(20, 20));
      // or you can use this to code
                        MCvAvgComp[][] faces = 
                      haar.DetectMultiScale(**IInputArray image** , 1.1, 
                      10, Emgu.CV.CvEnum.HaarDetectionType.DoCannyPruning, 
                      new Size(20, 20));

Nabeel Zafar Nabeel Zafar · Accepted Answer · 2017-07-20T09:46:15

The new EmguCv uses Mat as the image format by default. so in the IInputArray you need to pass the Mat

Mat matFrame = capture.QueryFrame();
Image<Bgr, byte> nextFrame = matFrame.ToImage<Bgr, byte>()
Image<Gray, byte> grayframe = nextFrame.Convert<Gray, byte>();

var faces = haar.DetectMultiScale( matFrame, 1.1, 10, 
                  Emgu.CV.CvEnum.HaarDetectionType.DoCannyPruning,  
                  new Size(20, 20));

IInputArray and IOutArray are interfaces which accept:

A CvArray, which is the base class of Matrix and Image<,>
A Mat, which is the Open CV equivalent of cv::Mat
A UMat, which is the Open CV equivalent of cv::UMat
A ScalarArray, which can be used to convert a scalar to an IInputArray
VectorOf{XXX}, this is the interface for the C++ standard vector

IInputArray image parameter for face detection in emgucv in c# using haarcascade

1 Answers