Class Saturation<T>

Namespace

AiDotNet.Augmentation.Image

Assembly

AiDotNet.dll

Adjusts the saturation (color intensity) of an image.

public class Saturation<T> : AugmentationBase<T, ImageTensor<T>>, IAugmentation<T, ImageTensor<T>>

Type Parameters

T

The numeric type for calculations.

Inheritance

object

AugmentationBase<T, ImageTensor<T>>

Saturation<T>

Implements

IAugmentation<T, ImageTensor<T>>

Inherited Members

AugmentationBase<T, ImageTensor<T>>.NumOps

AugmentationBase<T, ImageTensor<T>>.OnAugmentationApplied

AugmentationBase<T, ImageTensor<T>>.Name

AugmentationBase<T, ImageTensor<T>>.Probability

AugmentationBase<T, ImageTensor<T>>.IsTrainingOnly

AugmentationBase<T, ImageTensor<T>>.IsEnabled

AugmentationBase<T, ImageTensor<T>>.Apply(ImageTensor<T>, AugmentationContext<T>)

AugmentationBase<T, ImageTensor<T>>.ApplyAugmentation(ImageTensor<T>, AugmentationContext<T>)

AugmentationBase<T, ImageTensor<T>>.GetParameters()

AugmentationBase<T, ImageTensor<T>>.RaiseAugmentationApplied(AugmentationContext<T>, bool)

object.Equals(object)

object.Equals(object, object)

object.GetHashCode()

object.GetType()

object.MemberwiseClone()

object.ReferenceEquals(object, object)

object.ToString()

Remarks

Saturation adjustment changes how vivid or muted colors appear in an image. Higher saturation makes colors more vibrant, while lower saturation makes colors appear more gray or washed out.

For Beginners: Think of saturation like the vibrancy slider on photo apps. High saturation makes colors pop (like a sunset photo), while low saturation makes colors look faded (like an old photograph). A saturation of 0 would make the image completely grayscale.

When to use:

• Images from different cameras with varying color profiles
• Scenes with different lighting temperatures (warm vs cool)
• When you want the model to focus on shapes rather than colors

When NOT to use:

• Color is the primary classification feature (e.g., traffic lights)
• Medical imaging where color accuracy matters
• Tasks involving color matching or color recognition

Constructors

Saturation(double, double, double)

Creates a new saturation augmentation.

public Saturation(double minFactor = 0.8, double maxFactor = 1.2, double probability = 0.5)

Parameters

minFactor double

The minimum saturation factor. Values below 1.0 reduce saturation. Industry standard default is 0.8 (20% desaturation at minimum). A value of 0.0 would produce a grayscale image.

maxFactor double

The maximum saturation factor. Values above 1.0 increase saturation. Industry standard default is 1.2 (20% increase at maximum).

probability double

The probability of applying this augmentation (0.0 to 1.0). Industry standard default is 0.5.

Remarks

For Beginners: The factor range of 0.8 to 1.2 creates subtle, natural-looking variations. Going below 0.5 makes images noticeably washed out, while going above 2.0 can make colors unnaturally vivid.

Properties

MaxFactor

Gets the maximum saturation adjustment factor.

public double MaxFactor { get; }

Property Value

double

Remarks

Values greater than 1.0 increase color intensity.

MinFactor

Gets the minimum saturation adjustment factor.

public double MinFactor { get; }

Property Value

double

Remarks

A factor of 1.0 means no change. Factor of 0.0 converts to grayscale.

Methods

ApplyAugmentation(ImageTensor<T>, AugmentationContext<T>)

Applies the saturation adjustment to the image.

protected override ImageTensor<T> ApplyAugmentation(ImageTensor<T> data, AugmentationContext<T> context)

Parameters

data ImageTensor<T>

context AugmentationContext<T>

Returns

ImageTensor<T>

GetParameters()

Gets the parameters of this augmentation.

public override IDictionary<string, object> GetParameters()

Returns

IDictionary<string, object>

A dictionary of parameter names to values.