darsia.SegmentationComparison#

class SegmentationComparison(number_of_segmented_images=2, **kwargs)[source]#

Bases: object

Class for comparing segmented images.

Routines for comparing segmentations and creating visualizations of the comparison.

Attributes:

number_of_segmented_imagesint: Number of segmented images that one compares.
segmentation_nameslist[str]: List of names for each of the segmentations. Will affect legends in plots.
componentslist: List of values the different (active) components in the segmentations. As of now, up to two are allowed for and the default values are 1 and 2.
component_nameslist[str]: List of names for each of the components. Will be visual in legends.
gray_colorsnp.ndarray: Array of base gray colors (in RGB space) that accounts for different overlapping segmentations of different components.
colorsnp.ndarray: Color values for the different unique segmentations. Default is created from a colormap (matplotlib) depending on the amount of present segmentations.
color_dictionarydict: Dictionary relating all of the different colors to different overlapping segmentation situations.

Constructor of compare segmentations class.

Parameters:

number_of_segmented_imagesint: Number of segmentations to be compared. Optional keyword arguments (kwargs): segmentation_names (list): list of names for the different segmented images. So far only used in legends and color dictionary. components (list): list of the different components that are considered in the segmented images. So far only two are allowed to be provided. component_names (list): list of names for the different components. So far only used in legends, and color dictionary. gray_colors (np.ndarray): array of three different scales of gray (in RGB format), one for each of the different combinations of components in the segmentations. colors (np.ndarray): Array of different colors that should indicate unique components in each segmentation. light_scaling (float): Indicate how much lighter the second component should be scaled in its unique color.

Methods

`color_fractions`(comparison_image[, colors, ...])	Returns color fractions.
`compare_segmentations_binary_array`(...)	Compare segmentations pixel-wise.
`get_combinations`(*segmentation_numbers[, ...])	Returns a list of all possible combinations of segmentations.
`plot`(image[, figure_name, legend_anchor])	Plots the provided image (should be a comparison of segmentations) with matplotlib.pyplot's imshow and prints a legend with colors from the image and dictionary
`plot_overlay_segmentation`(comparison_image, ...)	Plots a comparison image overlayed a base image using matplotlib.

color_fractions(comparison_image, colors=None, depth_map=None)[source]#

Returns color fractions.

Parameters:

comparison_imagenp.ndarray: Comparison of segmentations.
colorsnp.ndarray: Array of color values in the comparison image.
depth_mapnp.ndarray, optional: Depth map for the image.

Returns:

(dict): Dictionary relating each color to the fraction of
the number of pixels that the color occupies and the
total number of occupied pixels in the image.

compare_segmentations_binary_array(*segmentations, **kwargs)[source]#

Compare segmentations pixel-wise.

Returns an array whose per-pixel value encodes which segmentations are present at that pixel (as a pattern of 1s and 0s). Different kinds of component are not currently distinguished.

Parameters:

*segmentationsnumpy.ndarray: The segmentations to compare.
**kwargs: "roi" (tuple of slices | ndarray of corner points) – region to compare, in pixel/matrix coordinates; defaults to the largest ROI fitting all segmentations. "components" (tuple of int) – components to recognise; default [1, 2].

get_combinations(*segmentation_numbers, num_segmentations=5)[source]#

Returns a list of all possible combinations of segmentations.

Parameters:

*segmentation_numberstuple[int, …]: The segmentation numbers that should be included in the combinations. Defaults to ().
num_segmentationsint, optional: Number of segmentations. Defaults to 5.

Returns:

list[list[int]]: List of all possible combinations of segmentations.

plot(image, figure_name='Comparison', legend_anchor=(0.7, 1))[source]#

Plots the provided image (should be a comparison of segmentations) with matplotlib.pyplot’s imshow and prints a legend with colors from the image and dictionary

Parameters:

imagenp.ndarray: Image with comparison of segmentations.
figure_namestr: Figure name.
legend_anchortuple: Tuple of coordinates (x,y) in Euclidean style that determines legend anchor.

plot_overlay_segmentation(comparison_image, base_image, figure_name='Comparison', opacity=0.6, legend_anchor=(1.0, 1.0), custom_legend=None, custom_legend_text=None)[source]#

Plots a comparison image overlayed a base image using matplotlib.

Parameters:

comparison_imagenp.ndarray: The image containing comparison of segmentations.
base_imagenp.ndarray: The base image that is to be overlayed.
figure_namestr: Figure name.
opacityfloat: Tha opacity value for the comparison image.
legend_anchortuple: Tuple of coordinates (x,y) in euclidean style that determines legend anchor.
custom_legendOptional[list[mpatches.Patch]]: In case it is desirable to create a custom legend.
custom_legend_textOptional[list[str]]: In case it is desirable to customize legend.