org.opencv.xphoto

Class LearningBasedWB

java.lang.Object

org.opencv.core.Algorithm

org.opencv.xphoto.WhiteBalancer

org.opencv.xphoto.LearningBasedWB

public class LearningBasedWB
extends WhiteBalancer

More sophisticated learning-based automatic white balance algorithm. As REF: GrayworldWB, this algorithm works by applying different gains to the input image channels, but their computation is a bit more involved compared to the simple gray-world assumption. More details about the algorithm can be found in CITE: Cheng2015 . To mask out saturated pixels this function uses only pixels that satisfy the following condition: \( \frac{\textrm{max}(R,G,B)}{\texttt{range_max_val}} < \texttt{saturation_thresh} \) Currently supports images of type REF: CV_8UC3 and REF: CV_16UC3.

Field Summary

Fields inherited from class org.opencv.core.Algorithm

nativeObj

Constructor Summary

Constructors

Modifier	Constructor and Description
protected	LearningBasedWB(long addr)

Method Summary

Modifier and Type	Method and Description
static LearningBasedWB	__fromPtr__(long addr)
void	extractSimpleFeatures(Mat src, Mat dst) Implements the feature extraction part of the algorithm.
protected void	finalize()
int	getHistBinNum() Defines the size of one dimension of a three-dimensional RGB histogram that is used internally by the algorithm.
int	getRangeMaxVal() Maximum possible value of the input image (e.g.
float	getSaturationThreshold() Threshold that is used to determine saturated pixels, i.e.
void	setHistBinNum(int val) getHistBinNum SEE: getHistBinNum
void	setRangeMaxVal(int val) getRangeMaxVal SEE: getRangeMaxVal
void	setSaturationThreshold(float val) getSaturationThreshold SEE: getSaturationThreshold

Methods inherited from class org.opencv.xphoto.WhiteBalancer

balanceWhite

Methods inherited from class org.opencv.core.Algorithm

clear, empty, getDefaultName, getNativeObjAddr, save

Methods inherited from class java.lang.Object

clone, equals, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Constructor Detail

LearningBasedWB

protected LearningBasedWB(long addr)

Method Detail

__fromPtr__

public static LearningBasedWB __fromPtr__(long addr)

extractSimpleFeatures

public void extractSimpleFeatures(Mat src,
                                  Mat dst)

Implements the feature extraction part of the algorithm. In accordance with CITE: Cheng2015 , computes the following features for the input image: 1. Chromaticity of an average (R,G,B) tuple 2. Chromaticity of the brightest (R,G,B) tuple (while ignoring saturated pixels) 3. Chromaticity of the dominant (R,G,B) tuple (the one that has the highest value in the RGB histogram) 4. Mode of the chromaticity palette, that is constructed by taking 300 most common colors according to the RGB histogram and projecting them on the chromaticity plane. Mode is the most high-density point of the palette, which is computed by a straightforward fixed-bandwidth kernel density estimator with a Epanechnikov kernel function.

Parameters:

src - Input three-channel image (BGR color space is assumed).

dst - An array of four (r,g) chromaticity tuples corresponding to the features listed above.

getRangeMaxVal

public int getRangeMaxVal()

Maximum possible value of the input image (e.g. 255 for 8 bit images, 4095 for 12 bit images) SEE: setRangeMaxVal

Returns:

automatically generated

setRangeMaxVal

public void setRangeMaxVal(int val)

getRangeMaxVal SEE: getRangeMaxVal

Parameters:

val - automatically generated

getSaturationThreshold

public float getSaturationThreshold()

Threshold that is used to determine saturated pixels, i.e. pixels where at least one of the channels exceeds \(\texttt{saturation_threshold}\times\texttt{range_max_val}\) are ignored. SEE: setSaturationThreshold

Returns:

automatically generated

setSaturationThreshold

public void setSaturationThreshold(float val)

getSaturationThreshold SEE: getSaturationThreshold

Parameters:

val - automatically generated

getHistBinNum

public int getHistBinNum()

Defines the size of one dimension of a three-dimensional RGB histogram that is used internally by the algorithm. It often makes sense to increase the number of bins for images with higher bit depth (e.g. 256 bins for a 12 bit image). SEE: setHistBinNum

Returns:

automatically generated

setHistBinNum

public void setHistBinNum(int val)

getHistBinNum SEE: getHistBinNum

Parameters:

val - automatically generated

finalize

protected void finalize()
                 throws Throwable

Overrides:

finalize in class WhiteBalancer

Throws:

Throwable