Detailed Description

Hough transform for detecting circles.

Public Member Functions
	CircleHoughTransform (const MemImage *img, const vec4i &roi=vec4i::Zero(), const vec2i &radiusRange=vec2i::Zero())
	Takes the image on which to perform the hough transform, the ROI in which to search (x,y,width,height) and the radius range (min,max) The image is normalized before running the hough transformation.

void	setBlurKernelSize (int size)
	Setting the kernel size to zero disables blurring.

int	blurKernelSize () const

void	setUseCanny (bool useCanny)

bool	useCanny () const

void	compute (float gradientThreshold=0.1f, float gradientsAboveThreshold=0.0f)
	Run hough detection The gradient threshold is wrt.

std::vector< vec3i >	detections (float threshold=0.95f, bool combineDuplicates=true) const
	Return all detected squares in the form [top left x, top left y, side length].

const TypedImage< float > *	detectionMatrix () const

const TypedImage< float > *	edgeMap () const

Protected Attributes
std::unique_ptr< TypedImage< float > >	m_inputNorm
	Normalized input image.

std::unique_ptr< TypedImage< float > >	m_detectionMatrix

std::unique_ptr< TypedImage< float > >	m_edgeMap

vec4i	m_roi
	ROI in which circle must be located in the format (x,y,width,height), default is entire image.

vec2i	m_radiusRange
	Allowed range for the radius, default is a minimum of 10 pixels and up to the half the image size.

int	m_blurKernelSize
	Size of blur kernel which is applied to image before running edge detection.

bool	m_useCanny
	Use Canny edge detection instead of gradient magnitude.

Member Function Documentation

◆ compute()

void compute	(	float	gradientThreshold = 0.1f,
		float	gradientsAboveThreshold = 0.0f )

Run hough detection The gradient threshold is wrt.

a normalized version of the image. When maxGradientsAboveThreshold is large 0 the threshold is increased until there are this many percent of gradients left. The gradient threshold is never decreased below gradientThreshold.

◆ detections()

std::vector< vec3i > detections	(	float	threshold = 0.95f,
		bool	combineDuplicates = true ) const

Return all detected squares in the form [top left x, top left y, side length].

The score is normalized with respect to the number of pixels on the border of the square, so that an ideal square has score 1. Due to numerical accuracy even for perfect data a smaller threshold shoud be used.

The documentation for this class was generated from the following file:

ImFusion/Base/CircleHoughTransform.h

Detailed Description

Public Member Functions

Protected Attributes

Member Function Documentation

◆ compute()

◆ detections()