ChiSquareDistanceHistogram class
Algorithm class for comparing images with chi-square histogram intersections
Images are converted to histogram representations (x-axis intensity, y-axis frequency). The chi-square distance formula is applied to compute the distance between each bin:
0.5* sum((binCount1 - binCount2)^2 / (binCount1 + binCount2))
Number of histograms bins is 256. Three histograms represent RGB distributions.
- Works well with images of all aspect ratios and dimensions
- Compare for similarity (if two images are similar based on their color distribution)
- Returns percentage difference (0.0 - no difference, 1.0 - 100% difference)
- Inheritance
-
- Object
- Algorithm
- HistogramAlgorithm
- ChiSquareDistanceHistogram
Constructors
- ChiSquareDistanceHistogram({bool ignoreAlpha = false})
Properties
- hashCode → int
-
The hash code for this object.
no setterinherited
- ignoreAlpha ↔ dynamic
-
Ignores alpha channel when computing difference
getter/setter pair
- runtimeType → Type
-
A representation of the runtime type of the object.
no setterinherited
Methods
-
compare(
Image src1, Image src2) → double -
Calculates histogram similarity using chi-squared distance
override
-
noSuchMethod(
Invocation invocation) → dynamic -
Invoked when a nonexistent method or property is accessed.
inherited
-
toString(
) → String -
A string representation of this object.
override
Operators
-
operator ==(
Object other) → bool -
The equality operator.
inherited