kornia.morphology¶
-
dilation
(tensor: torch.Tensor, kernel: torch.Tensor) → torch.Tensor[source]¶ Returns the dilated image applying the same kernel in each channel.
The kernel must have 2 dimensions, each one defined by an odd number.
- Parameters
tensor (torch.Tensor) – Image with shape \((B, C, H, W)\).
kernel (torch.Tensor) – Structuring element with shape \((H, W)\).
- Returns
Dilated image with shape \((B, C, H, W)\).
- Return type
Example
>>> tensor = torch.rand(1, 3, 5, 5) >>> kernel = torch.ones(3, 3) >>> dilated_img = dilation(tensor, kernel)
-
erosion
(tensor: torch.Tensor, kernel: torch.Tensor) → torch.Tensor[source]¶ Returns the eroded image applying the same kernel in each channel.
The kernel must have 2 dimensions, each one defined by an odd number.
- Parameters
tensor (torch.Tensor) – Image with shape \((B, C, H, W)\).
kernel (torch.Tensor) – Structuring element with shape \((H, W)\).
- Returns
Eroded image with shape \((B, C, H, W)\).
- Return type
Example
>>> tensor = torch.rand(1, 3, 5, 5) >>> kernel = torch.ones(5, 5) >>> output = erosion(tensor, kernel)
-
open
(tensor: torch.Tensor, kernel: torch.Tensor) → torch.Tensor[source]¶ Returns the opened image, (that means, erosion after a dilation) applying the same kernel in each channel.
The kernel must have 2 dimensions, each one defined by an odd number.
- Parameters
tensor (torch.Tensor) – Image with shape \((B, C, H, W)\).
kernel (torch.Tensor) – Structuring element with shape \((H, W)\).
- Returns
Dilated image with shape \((B, C, H, W)\).
- Return type
Example
>>> tensor = torch.rand(1, 3, 5, 5) >>> kernel = torch.ones(3, 3) >>> opened_img = open(tensor, kernel)
-
close
(tensor: torch.Tensor, kernel: torch.Tensor) → torch.Tensor[source]¶ Returns the closed image, (that means, dilation after an erosion) applying the same kernel in each channel.
The kernel must have 2 dimensions, each one defined by an odd number.
- Parameters
tensor (torch.Tensor) – Image with shape \((B, C, H, W)\).
kernel (torch.Tensor) – Structuring element with shape \((H, W)\).
- Returns
Dilated image with shape \((B, C, H, W)\).
- Return type
Example
>>> tensor = torch.rand(1, 3, 5, 5) >>> kernel = torch.ones(3, 3) >>> closed_img = close(tensor, kernel)
-
gradient
(tensor: torch.Tensor, kernel: torch.Tensor) → torch.Tensor[source]¶ Returns the morphological gradient of an image.
That means, (dilation - erosion) applying the same kernel in each channel. The kernel must have 2 dimensions, each one defined by an odd number.
- Parameters
tensor (torch.Tensor) – Image with shape \((B, C, H, W)\).
kernel (torch.Tensor) – Structuring element with shape \((H, W)\).
- Returns
Dilated image with shape \((B, C, H, W)\).
- Return type
Example
>>> tensor = torch.rand(1, 3, 5, 5) >>> kernel = torch.ones(3, 3) >>> gradient_img = gradient(tensor, kernel)
-
top_hat
(tensor: torch.Tensor, kernel: torch.Tensor) → torch.Tensor[source]¶ Returns the top hat tranformation of an image.
That means, (image - opened_image) applying the same kernel in each channel. The kernel must have 2 dimensions, each one defined by an odd number.
See
open
for details.- Parameters
tensor (torch.Tensor) – Image with shape \((B, C, H, W)\).
kernel (torch.Tensor) – Structuring element with shape \((H, W)\).
- Returns
Top hat transformated image with shape \((B, C, H, W)\).
- Return type
Example
>>> tensor = torch.rand(1, 3, 5, 5) >>> kernel = torch.ones(3, 3) >>> top_hat_img = top_hat(tensor, kernel)
-
black_hat
(tensor: torch.Tensor, kernel: torch.Tensor) → torch.Tensor[source]¶ Returns the black hat tranformation of an image.
That means, (closed_image - image) applying the same kernel in each channel. The kernel must have 2 dimensions, each one defined by an odd number.
See
close
for details.- Parameters
tensor (torch.Tensor) – Image with shape \((B, C, H, W)\).
kernel (torch.Tensor) – Structuring element with shape \((H, W)\).
- Returns
Top hat transformated image with shape \((B, C, H, W)\).
- Return type
Example
>>> tensor = torch.rand(1, 3, 5, 5) >>> kernel = torch.ones(3, 3) >>> black_hat_img = black_hat(tensor, kernel)