ILImageThreshold Interface Reference

This interface provide functionalities of threshold operations. More...

Inheritance diagram for ILImageThreshold:

Public Member Functions
void	Binarize (ILImage *img, ILImage *result)
void	Clip (ILImage *img, ILImage *result)
void	SetThreshold (int lb, int ub)
void	SetThresholdAdaptGlobal (int lbBias, int ubBias)
void	SetThresholdAdaptLocal (int blockWidth, int blockHeight, int lbBias, int ubBias)
void	Stretch (ILImage *img, ILImage *result)
void	ThresholdDistance (ILImage *img, ILImage *result)
Public Member Functions inherited from ILObject
ILObject *	Copy ()
LPVErrorCode	Load (LString filename)
void	Reset ()
LPVErrorCode	Save (LString filename)
BOOL	Valid ()

Properties
int	LocalBlockHeight [get]
	The height of the local region used in local adaptive thresholding. More...
int	LocalBlockWidth [get]
	The width of the local region used in local adaptive thresholding. More...
int	ThresholdLB [get]
	The lower bound of used-specified threshold value. More...
int	ThresholdLBBias [get]
	The revised value to generate a adaptive threshold lower bound. More...
LPVThresholdType	ThresholdType [get]
	The thresholding method. More...
int	ThresholdUB [get]
	The upper bound of used-specified threshold value. More...
int	ThresholdUBBias [get]
	The revised value to generate a adaptive threshold upper bound. More...

Detailed Description

This interface provide functionalities of threshold operations.

Thresholding is a classic segmentation method to separate out regions of an image corresponding to objects which we want to analyze. This separation is based on the variation of intensity between the object and the background pixels. To differentiate the pixels, we perform a comparison of each pixel intensity value with respect to a threshold value (which is user-specified or determined by adaptive method)

To use this interface, you should create a LImageThreshold object.

Example Code

C++

ILImageThresholdPtr thresholdOp = LImageThreshold::Create();
thresholdOp->SetThreshold(100, 200);
thresholdOp->Binarize(img, resultImg);

C#

LImageThreshold thresholdOp = new LImageThreshold();
thresholdOp.SetThreshold(100, 200);
thresholdOp.Binarize(img, resultImg);

COM

ILImageThresholdPtr thresholdOp = LImageThreshold::Create();
// or, ILImageThresholdPtr thresholdOp(__uuidof(LImageThreshold)), for absence of built-in Create functions (before 2.2.0)
thresholdOp->SetThreshold(100, 200);
thresholdOp->Binarize(img, resultImg);

Member Function Documentation

Binarize()

void Binarize	(	ILImage *	img,
		ILImage *	result
	)

Binarize the input image and return the result new image.
If the lower bound of threshold value is smaller than the upper bound, pixels within the lower and upper bound of threshold value is set to the object level (maximum value, 255 for 8bit images, 65536 for 16bit images), otherwise, the output pixel is set to the background level (0).
If the lower bound of threshold value is greater than the upper bound, the output result is inverted.

Parameters

[in]	img	The input image
[out]	result	Return result image

Clip()

void Clip	(	ILImage *	img,
		ILImage *	result
	)

Pixels within the lower and upper bound of threshold value is assigned the value of the input pixel, otherwise, is assigned to the value of lower or upper bound.
For example, if the threshold lower bound is 100, upper bound is 200, a pixel of 150 value remains 150, a pixel of 230 outputs 200, a pixel of 50 outputs 100.

Parameters

[in]	img	The input image
[out]	result	Return result image

SetThreshold()

void SetThreshold	(	int	lb,
		int	ub
	)

Use user-specified threshold value

Parameters

[in]	lb	The lower bound of threshold range, in range of 0 ~ 255 for 8bit images, 0 ~ 65535 for 16bit images
[in]	ub	The upper bound of threshold range, in range of 0 ~ 255 for 8bit images, 0 ~ 65535 for 16bit images

SetThresholdAdaptGlobal()

void SetThresholdAdaptGlobal	(	int	lbBias,
		int	ubBias
	)

Use global-adaptive threshold value.
The optimal threshold value is calculated base on the entire input image, then revised by the given bias value. The lower bound of threshold value is @math_eq{t - lbBias} , the upper bound is @math_eq{t + ubBias} .

Parameters

[in]	lbBias	Revise value to optimal threshold value, to generate a threshold lower bound.
[in]	ubBias	Revise value to optimal threshold value, to generate a threshold upper bound.

SetThresholdAdaptLocal()

void SetThresholdAdaptLocal	(	int	blockWidth,
		int	blockHeight,
		int	lbBias,
		int	ubBias
	)

Use local-adaptive threshold value.
The optimal threshold value is calculated base on a @math_eq{blockWidth \times blockHeight} region around individual pixel, then revised by the given bias value. The lower bound of threshold value is @math_eq{t - lbBias} , the upper bound is @math_eq{t + ubBias} .

Parameters

[in]	blockWidth	The width of a pixel's local region, should be an odd number, say, 3, 5, 7, etc.
[in]	blockHeight	The height of a pixel's local region, should be an odd number, say, 3, 5, 7, etc.
[in]	lbBias	Revise value to optimal threshold value, to generate a threshold lower bound.
[in]	ubBias	Revise value to optimal threshold value, to generate a threshold upper bound.

Stretch()

void Stretch	(	ILImage *	img,
		ILImage *	result
	)

Stretch the pixel value within the lower and upper bound of threshold value, others is assigned to 0 or maximum value respectively.
For example for a 8bit image, if the threshold lower bound is 100, upper bound is 200, pixel is assigned to 0 if its input value is within range [0, 100], it's assigned to 255 if within range [200, 255], for the range [101, 199] it's assigned as:

\[ (p - 100) \times 255 / (200 - 100) \]

Parameters

[in]	img	The input image
[out]	result	Return result image

ThresholdDistance()

void ThresholdDistance	(	ILImage *	img,
		ILImage *	result
	)

Each output pixel represents the difference between the greyscale value of each input pixel and the threshold lower bound.
For example, if a pixel value is 100 and the threshold lower bound is 25, then the output pixel value will be 75。

Parameters

[in]	img	The input image
[out]	result	Return result image

Property Documentation

LocalBlockHeight

int LocalBlockHeight

get

The height of the local region used in local adaptive thresholding.

See also

SetThresholdAdaptLocal()

LocalBlockWidth

int LocalBlockWidth

get

The width of the local region used in local adaptive thresholding.

See also

SetThresholdAdaptLocal()

ThresholdLB

int ThresholdLB

get

The lower bound of used-specified threshold value.

See also

SetThreshold()

ThresholdLBBias

int ThresholdLBBias

get

The revised value to generate a adaptive threshold lower bound.

See also

SetThresholdAdaptGlobal(), SetThresholdAdaptLocal()

ThresholdType

LPVThresholdType ThresholdType

get

The thresholding method.

See also

SetThreshold(), SetThresholdAdaptGlobal(), SetThresholdAdaptLocal()

ThresholdUB

int ThresholdUB

get

The upper bound of used-specified threshold value.

See also

SetThreshold()

ThresholdUBBias

int ThresholdUBBias

get

The revised value to generate a adaptive threshold upper bound.

See also

SetThresholdAdaptGlobal(), SetThresholdAdaptLocal()