PixelEdgeDetector

class giant.image_processing.edge_detection.PixelEdgeDetector(*args, **kwargs)

This class implements a basic pixel level edge detector using the Scharr methodology.

Essentially, a Scharr filter is convolved with the image and then Otsu’s method is used to automatically threshold the image gradients to detect the strongest signals, which presumably correspond to edges.

refine_edges(image, edges)

Refines the pixel level edge locations to pixel level edge locations.

This does nothing except return the input…

Parameters:

• image (ndarray[tuple[Any, ...], dtype[_ScalarT]]) – The image to use to refine the edges

• edges (ndarray[tuple[Any, ...], dtype[int64]]) – the edges to refine

Returns:

the refined edges.

Return type:

ndarray[tuple[Any, …], dtype[int64]]

identify_edges(image)

This method identifies pixel level edges in the image.

Parameters:

image (ndarray[tuple[Any, ...], dtype[_ScalarT]]) – The image to detect the edges in.

Returns:

The edges as a 2xn array with x (column) components in the first axis and y (row) components in the second axis

Return type:

ndarray[tuple[Any, …], dtype[int64]]

Methods

identify_edges	This method identifies pixel level edges in the image.
refine_edges	Refines the pixel level edge locations to pixel level edge locations.

Inherited Attributes

• horizontal_mask

• vertical_mask

• horizontal_gradient

• vertical_gradient

• gradient_magnitude