C# Class Emgu.CV.Features2D.SurfDetector

Mostra file Open project: genecyber/PredatorCV Class Usage Examples

Public Properties

Property Type Description
extended int
hessianThreshold double
nOctaveLayers int
nOctaves int

Public Methods

Method Description
ComputeDescriptors ( Byte>.Image image, byte>.Image mask, MKeyPoint keyPoints ) : Emgu.CV.Features2D.ImageFeature[]

Compute the descriptor given the image and the point location

ComputeDescriptors ( byte>.Image image, MKeyPoint keyPoints ) : Emgu.CV.Features2D.ImageFeature[]

Compute the ImageFeature on the image from the given keypoint locations.

DetectFeatures ( Byte>.Image image, byte>.Image mask ) : Emgu.CV.Features2D.ImageFeature[]

Detect image features from the given image

DetectKeyPoints ( Byte>.Image image, byte>.Image mask ) : Emgu.CV.Structure.MKeyPoint[]

Detect the SURF keypoints from the image

DetectKeyPoints ( byte>.Image image ) : Emgu.CV.Structure.MKeyPoint[]

Detect the keypoints in the image

SurfDetector ( double hessianThresh, bool extendedFlag ) : System

Create a MCvSURFParams using the specific values

Private Methods

Method Description
CvSURFDetectorComputeDescriptors ( SurfDetector &detector, IntPtr image, IntPtr mask, IntPtr keypoints, IntPtr descriptors ) : void
CvSURFDetectorDetectFeature ( SurfDetector &detector, IntPtr image, IntPtr mask, IntPtr keypoints, IntPtr descriptors ) : void
CvSURFDetectorDetectKeyPoints ( SurfDetector &detector, IntPtr image, IntPtr mask, IntPtr keypoints ) : void

Method Details

ComputeDescriptors() public method

Compute the descriptor given the image and the point location
public ComputeDescriptors ( Byte>.Image image, byte>.Image mask, MKeyPoint keyPoints ) : Emgu.CV.Features2D.ImageFeature[]
image Byte>.Image The image where the descriptor will be computed from
mask byte>.Image The optional mask, can be null if not needed
keyPoints Emgu.CV.Structure.MKeyPoint The keypoint where the descriptor will be computed from
return Emgu.CV.Features2D.ImageFeature[]

ComputeDescriptors() public method

Compute the ImageFeature on the image from the given keypoint locations.
public ComputeDescriptors ( byte>.Image image, MKeyPoint keyPoints ) : Emgu.CV.Features2D.ImageFeature[]
image byte>.Image The image to compute descriptors from
keyPoints Emgu.CV.Structure.MKeyPoint The keypoints where the descriptor computation is perfromed
return Emgu.CV.Features2D.ImageFeature[]

DetectFeatures() public method

Detect image features from the given image
public DetectFeatures ( Byte>.Image image, byte>.Image mask ) : Emgu.CV.Features2D.ImageFeature[]
image Byte>.Image The image to detect features from
mask byte>.Image The optional mask, can be null if not needed
return Emgu.CV.Features2D.ImageFeature[]

DetectKeyPoints() public method

Detect the SURF keypoints from the image
public DetectKeyPoints ( Byte>.Image image, byte>.Image mask ) : Emgu.CV.Structure.MKeyPoint[]
image Byte>.Image The image to extract SURF features from
mask byte>.Image The optional mask, can be null if not needed
return Emgu.CV.Structure.MKeyPoint[]

DetectKeyPoints() public method

Detect the keypoints in the image
public DetectKeyPoints ( byte>.Image image ) : Emgu.CV.Structure.MKeyPoint[]
image byte>.Image The image from which the key point will be detected from
return Emgu.CV.Structure.MKeyPoint[]

SurfDetector() public method

Create a MCvSURFParams using the specific values
public SurfDetector ( double hessianThresh, bool extendedFlag ) : System
hessianThresh double /// Only features with keypoint.hessian larger than that are extracted. /// good default value is ~300-500 (can depend on the average local contrast and sharpness of the image). /// user can further filter out some features based on their hessian values and other characteristics ///
extendedFlag bool /// false means basic descriptors (64 elements each), /// true means extended descriptors (128 elements each) ///
return System

Property Details

extended public_oe property

0 means basic descriptors (64 elements each), 1 means extended descriptors (128 elements each)
public int extended
return int

hessianThreshold public_oe property

Only features with keypoint.hessian larger than that are extracted. good default value is ~300-500 (can depend on the average local contrast and sharpness of the image). user can further filter out some features based on their hessian values and other characteristics
public double hessianThreshold
return double

nOctaveLayers public_oe property

The number of layers within each octave (4 by default)
public int nOctaveLayers
return int

nOctaves public_oe property

The number of octaves to be used for extraction. With each next octave the feature size is doubled (3 by default)
public int nOctaves
return int