http://www.emgu.com
Create a new HOGDescriptor using the specific parameters

Namespace: Emgu.CV.OpenCL
Assembly: Emgu.CV.OpenCL (in Emgu.CV.OpenCL.dll) Version: 2.4.10.1935 (2.4.10.1935)

Syntax

C#
public OclHOGDescriptor(
	Size winSize,
	Size blockSize,
	Size blockStride,
	Size cellSize,
	int nbins,
	double winSigma,
	double L2HysThreshold,
	bool gammaCorrection,
	int nLevels
)
Visual Basic
Public Sub New ( 
	winSize As Size,
	blockSize As Size,
	blockStride As Size,
	cellSize As Size,
	nbins As Integer,
	winSigma As Double,
	L2HysThreshold As Double,
	gammaCorrection As Boolean,
	nLevels As Integer
)
Visual C++
public:
OclHOGDescriptor(
	Size winSize, 
	Size blockSize, 
	Size blockStride, 
	Size cellSize, 
	int nbins, 
	double winSigma, 
	double L2HysThreshold, 
	bool gammaCorrection, 
	int nLevels
)
F#
new : 
        winSize : Size * 
        blockSize : Size * 
        blockStride : Size * 
        cellSize : Size * 
        nbins : int * 
        winSigma : float * 
        L2HysThreshold : float * 
        gammaCorrection : bool * 
        nLevels : int -> OclHOGDescriptor

Parameters

winSize
Type: System.Drawing..::..Size
Detection window size. Must be aligned to block size and block stride. Must match the size of the training image. Use (64, 128) for default.
blockSize
Type: System.Drawing..::..Size
Block size in cells. Use (16, 16) for default.
blockStride
Type: System.Drawing..::..Size
Block stride. Must be a multiple of cell size. Use (8,8) for default.
cellSize
Type: System.Drawing..::..Size
Cell size. Use (8, 8) for default.
nbins
Type: System..::..Int32
Number of bins. Use 9 bins per cell for deafault.
winSigma
Type: System..::..Double
Gaussian smoothing window parameter. Use -1 for default.
L2HysThreshold
Type: System..::..Double
L2-Hys normalization method shrinkage. Use 0.2 for default.
gammaCorrection
Type: System..::..Boolean
Do gamma correction preprocessing or not. Use true for default.
nLevels
Type: System..::..Int32
Maximum number of detection window increases. Use 64 for default

See Also