You are here: Start » Function Reference » Image » Image Enhancement » NormalizeLocalContrast

NormalizeLocalContrast

Header:	FIL.h
Namespace:	fil
Module:	FoundationBasic

Normalizes local contrast of the image using Wallis filter.

Syntax

void fil::NormalizeLocalContrast
(
	const fil::Image& inMonoImage,
	ftl::Optional<const fil::Region&> inRoi,
	const float inTargetMean,
	const float inTargetVariance,
	const int inUniformnessScale,
	const float inBrightnessPreserveRatio,
	fil::Image& outImage
)

Parameters

Name	Type	Range	Default	Description
inMonoImage	const Image&			Monochromatic input image
inRoi	Optional<const Region&>		NIL	Range of pixels to be processed
inTargetMean	const float		128.0f	Target local mean
inTargetVariance	const float	0.1 -	90.0f	Target local variance
inUniformnessScale	const int	1 - +	10	Radius of neighbourhood to uniformize
inBrightnessPreserveRatio	const float	0.0 - 1.0	0.1f	How much of original brightness to be kept
outImage	Image&			Output image

Requirements

For input inMonoImage only pixel formats are supported: 1⨯uint8, 1⨯int8, 1⨯uint16, 1⨯int16, 1⨯int32, 1⨯real.

Read more about pixel formats in Image documentation.

Description

This filter resaturates every pixel of monochromatic image inMonoImage so that its neighbourhood matches approximately average of inTargetMean and variance of inTargetVariance using Wallis algorithm.

Parameter inUniformnessScale determines the radius of the neighbourhood.

Parameter inBrightnessPreserveRatio determines how much of the original brightness is kept on the resulting image.

New value of pixel is given by:

\[ P_{new} = A\ P_{old} + B \]

where

\[A = \frac{Var_{new} }{\frac{90}{CFC} + Var_{loc} } \] \[B = Mean_{new}(1 - BPR) + Mean_{loc}(BPR - A) \]

and

\(Dev_{loc}\) and \(Mean_{loc}\) are local deviation and mean respectively, taken from the square neighbourhood of radius inUniformnessScale
\(Dev_{new}\) and \(Mean_{new}\) are target deviation and mean respectively, inTargetVariance and inTargetMean
CFC is Contrast Force Constant, set to \(0.9\)
BPR is inBrightnessPreserveRatio

Examples

Example image

Output of NormalizeLocalContrast filter

Previous image with NormalizeImage filter applied to it

Remarks

After the filter is run on the image, the neighbourhoods of pixels do not have desired variance and average. First reason for that is presence of constants BPR and CFC. Second reason is that forcing matching given average would require solving system of as many linear equations as there are pixels on the image.

Errors

List of possible exceptions:

Error type	Description
DomainError	Mono image expected on input in NormalizeLocalContrast.
DomainError	Region exceeds an input image in NormalizeLocalContrast.
DomainError	Not supported inMonoImage pixel format in NormalizeLocalContrast. Supported formats: 1xUInt8, 1xInt8, 1xUInt16, 1xInt16, 1xInt32, 1xReal.