Trait opencv::prelude::LearningBasedWBTrait

source ·

pub trait LearningBasedWBTrait: LearningBasedWBTraitConst + WhiteBalancerTrait {
    // Required method
    fn as_raw_mut_LearningBasedWB(&mut self) -> *mut c_void;

    // Provided methods
    fn extract_simple_features(
        &mut self,
        src: &impl ToInputArray,
        dst: &mut impl ToOutputArray
    ) -> Result<()> { ... }
    fn set_range_max_val(&mut self, val: i32) -> Result<()> { ... }
    fn set_saturation_threshold(&mut self, val: f32) -> Result<()> { ... }
    fn set_hist_bin_num(&mut self, val: i32) -> Result<()> { ... }
}

Expand description

Mutable methods for crate::xphoto::LearningBasedWB

Required Methods§

source

fn as_raw_mut_LearningBasedWB(&mut self) -> *mut c_void

Provided Methods§

source

fn extract_simple_features( &mut self, src: &impl ToInputArray, dst: &mut impl ToOutputArray ) -> Result<()>

Implements the feature extraction part of the algorithm.

In accordance with Cheng2015 , computes the following features for the input image:

Chromaticity of an average (R,G,B) tuple
Chromaticity of the brightest (R,G,B) tuple (while ignoring saturated pixels)
Chromaticity of the dominant (R,G,B) tuple (the one that has the highest value in the RGB histogram)
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.

source

fn set_range_max_val(&mut self, val: i32) -> Result<()>

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

§See also

setRangeMaxVal getRangeMaxVal

source

fn set_saturation_threshold(&mut self, val: f32) -> Result<()>

Threshold that is used to determine saturated pixels, i.e. pixels where at least one of the channels exceeds $inline formula$ are ignored.

§See also

setSaturationThreshold getSaturationThreshold

source

fn set_hist_bin_num(&mut self, val: i32) -> Result<()>

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).