AverageBlur

class deeptrack.optical.math.AverageBlur(ksize: int = 3, channel_axis: int | None = -1, **kwargs: Any)

Bases: Blur

Blur an image by computing simple means over neighbourhoods.

Applies a uniform (mean) filter over spatial dimensions.

If channel_axis is specified, the blur is applied independently per channel. Otherwise, all dimensions (including channels, if present) are treated as spatial, and the filter is applied across them.

Parameters

ksize: int

Kernel size for the blur operation.

channel_axis: int or None

The axis representing the channel dimension. If None, channels are not treated separately and the same blurring is applied across all dimensions.

Methods

get(image, ksize, channel_axis, **kwargs) –> np.ndarray | torch.Tensor

Applies the average blurring filter to the input image.

Examples

>>> import deeptrack as dt

Create an input image.

>>> import numpy as np
>>>
>>> input_image = np.random.rand(32, 32)

Define an average blur feature.

>>> average_blur = dt.AverageBlur(ksize=3, channel_axis=None)
>>> output_image = average_blur(input_image)
>>> print(output_image.shape)
(32, 32)