GaussianBlur<T>
Models & Types · AiDotNet.Augmentation.Image
Applies Gaussian blur to an image.
Inheritance: AugmentationBase<T, ImageTensor<T>> → GaussianBlur<T>
For Beginners
Think of this like looking at a photo through frosted glass. The image becomes softer and details are less sharp. This teaches your model to recognize objects even when they’re not perfectly in focus.
How It Works
Gaussian blur smooths the image by convolving it with a Gaussian kernel. This simulates out-of-focus images or motion blur, helping the model become robust to blurry inputs.
When to use:
- When deployed images may be out of focus
- When training data is too sharp compared to real-world images
- To reduce high-frequency noise sensitivity
Constructors
| Constructor | Summary |
|---|---|
GaussianBlur(double minSigma, double maxSigma, int kernelSize, double probability) |
Creates a new Gaussian blur augmentation. |
Properties
| Property | Summary |
|---|---|
double MaxSigma { get; } |
Gets the maximum sigma (standard deviation) for the Gaussian kernel. |
double MinSigma { get; } |
Gets the minimum sigma (standard deviation) for the Gaussian kernel. |
int KernelSize { get; } |
Gets the kernel size for the Gaussian blur. |
Methods
| Method | Summary |
|---|---|
IDictionary<string, object> GetParameters() |