paidiverpy.colour_layer

paidiverpy.colour_layer#

__init__.py for colour_layer module.

Submodules#

Classes#

ColourLayer

ColourLayer class.

Package Contents#

class paidiverpy.colour_layer.ColourLayer(parameters: dict[str, object], config_params: dict[str, object] | paidiverpy.config.config_params.ConfigParams | None = None, config_file_path: str | None = None, config: paidiverpy.config.configuration.Configuration | None = None, metadata: paidiverpy.metadata_parser.MetadataParser | None = None, images: paidiverpy.images_layer.ImagesLayer | None = None, paidiverpy: paidiverpy.Paidiverpy | None = None, step_name: str | None = None, client: dask.distributed.Client | None = None, config_index: int | None = None, logger: logging.Logger | None = None, raise_error: bool = False, verbose: int = 2)[source]#

Bases: paidiverpy.Paidiverpy

ColourLayer class.

This class contains the methods for processing the images in the colour layer.

Parameters:

  • parameters (dict) – The parameters for the step.

  • config_params (dict | ConfigParams, optional) – The configuration parameters. It can contain the following keys / attributes: - input_path (str): The path to the input files. - output_path (str): The path to the output files. - metadata_path (str): The path to the metadata file. - metadata_type (str): The type of the metadata file. - track_changes (bool): Whether to track changes. - n_jobs (int): The number of n_jobs.

  • config_file_path (str) – The path to the configuration file.

  • config (Configuration) – The configuration object.

  • metadata (MetadataParser) – The metadata object.

  • images (ImagesLayer) – The images object.

  • paidiverpy (Paidiverpy) – The paidiverpy object.

  • step_name (str) – The name of the step.

  • config_index (int) – The index of the configuration.

  • logger (logging.Logger) – The logger object.

  • raise_error (bool) – Whether to raise an error.

  • verbose (int) – verbose level (0 = none, 1 = errors/warnings, 2 = info).

static grayscale(image_data: numpy.ndarray[Any, Any], params: paidiverpy.models.colour_params.GrayScaleParams | None = None, **_kwargs: dict[str, object]) → numpy.ndarray[Any, Any][source]#

Convert the image to grayscale.

Method to convert the image to grayscale.

Parameters:

  • image_data (np.ndarray) – The input image.

  • params (GrayScaleParams, optional) – Parameters for the grayscale conversion. Defaults to GrayScaleParams().

  • **_kwargs (dict) – Additional keyword arguments.

Raises:

ValueError – If the input image does not have 3 channels or 4 channels with alpha.

Returns:

The updated image.

Return type:

np.ndarray

static gaussian_blur(image_data: numpy.ndarray[Any, Any], params: paidiverpy.models.colour_params.GaussianBlurParams | None = None, **_kwargs: dict[str, object]) → numpy.ndarray[Any, Any][source]#

Gaussian blur.

Method to apply Gaussian blur to the image.

Parameters:

  • image_data (np.ndarray) – The image to apply Gaussian blur.

  • params (GaussianBlurParams, optional) – the parameters for the method. Defaults to GaussianBlurParams().

  • **_kwargs (dict) – Additional keyword arguments.

Raises:

ValueError – Error applying Gaussian blur.

Returns:

The updated image.

Return type:

np.ndarray

static sharpen(image_data: numpy.ndarray[Any, Any], params: paidiverpy.models.colour_params.SharpenParams | None = None, **_kwargs: dict[str, object]) → numpy.ndarray[Any, Any][source]#

Sharpening.

Method to apply sharpening to the image.

Parameters:

  • image_data (np.ndarray) – The image to apply sharpening.

  • params (SharpenParams, optional) – Params for method. Defaults to SharpenParams().

  • **_kwargs (dict) – Additional keyword arguments.

Raises:

ValueError – Error applying sharpening.

Returns:

The updated image.

Return type:

np.ndarray

static contrast_adjustment(image_data: numpy.ndarray[Any, Any], params: paidiverpy.models.colour_params.ContrastAdjustmentParams | None = None, **_kwargs: dict[str, Any]) → numpy.ndarray[Any, Any][source]#

Contrast adjustment.

Method to apply contrast adjustment to the image.

Parameters:

  • image_data (np.ndarray) – The image to apply contrast adjustment.

  • params (ContrastAdjustmentParams, optional) – Params for method. Defaults to ContrastAdjustmentParams().

  • **_kwargs (dict) – Additional keyword arguments.

Raises:

ValueError – Error applying contrast adjustment.

Returns:

The updated image.

Return type:

np.ndarray

static illumination_correction(image_data: numpy.ndarray[Any, Any], params: paidiverpy.models.colour_params.IlluminationCorrectionParams | None = None, **_kwargs: dict[str, Any]) → numpy.ndarray[Any, Any][source]#

Illumination correction.

Method to apply illumination correction to the image.

Parameters:

  • image_data (np.ndarray) – The image to apply illumination correction.

  • params (IlluminationCorrectionParams, optional) – Params for method. Defaults to IlluminationCorrectionParams().

  • **_kwargs (dict) – Additional keyword arguments.

Raises:

ValueError – Error applying illumination correction.

Returns:

The updated image.

Return type:

np.ndarray

static deblur(image_data: numpy.ndarray[Any, Any], params: paidiverpy.models.colour_params.DeblurParams | None = None, **_kwargs: dict[str, object]) → numpy.ndarray[Any, Any][source]#

Deblurring.

Method to apply deblurring to the image.

Parameters:

  • image_data (np.ndarray) – The image to apply deblurring.

  • params (DeblurParams, optional) – Params for method. Defaults to DeblurParams().

  • **_kwargs (dict) – Additional keyword arguments.

Raises:

  • ValueError – Unknown PSF type. Please use ‘gaussian’ or ‘motion’.

  • ValueError – Unknown method type. Please use ‘wiener’.

  • NotImplementedError – Unknown method type. Please use ‘wiener’.

  • ValueError – Error applying contrast adjustment.

Returns:

The updated image.

Return type:

np.ndarray

static colour_alteration(image_data: numpy.ndarray[Any, Any], params: paidiverpy.models.colour_params.ColourAlterationParams | None = None, **_kwargs: dict[str, object]) → numpy.ndarray[Any, Any][source]#

Apply colour alteration to the image.

Parameters:

  • image_data (np.ndarray) – The image to alter colour channel.

  • params (ColourAlterationParams, optional) – Params for method. Defaults to None.

  • **_kwargs (dict) – Additional keyword arguments.

Raises:

  • ValueError – Unknown method type. Please use ‘white_balance’.

  • ValueError – Image is gray-scale’.

  • e – Error applying colour alteration.

Returns:

The updated image.

Return type:

np.ndarray

static edge_detection(image_data: numpy.ndarray[Any, Any], params: paidiverpy.models.colour_params.EdgeDetectionParams | None = None, **_kwargs: dict[str, object]) → numpy.ndarray[Any, Any][source]#

Edge detection.

Method to apply edge detection to the image.

Parameters:

  • image_data (np.ndarray) – The image to apply edge detection.

  • params (EdgeDetectionParams, optional) – Params for method. Defaults to EdgeDetectionParams().

  • **_kwargs (dict) – Additional keyword arguments.

Raises:

e – Error applying edge detection.

Returns:

The updated image.

Return type:

np.ndarray

static get_object_features(gray_image_data: numpy.ndarray[Any, Any], label_image_data: numpy.ndarray[Any, Any], params: paidiverpy.models.colour_params.EdgeDetectionParams) → tuple[dict[str, object], numpy.ndarray][source]#

Get object features.

Get the features of the object.

Parameters:

  • gray_image_data (np.ndarray) – The grayscale image data.

  • label_image_data (np.ndarray) – The label image data.

  • params (EdgeDetectionParams) – The parameters for edge detection.

Returns:

The features of the object and the binary image data.

Return type:

tuple[dict, np.ndarray]

static gaussian_psf(size: list[int], sigma: float) → numpy.ndarray[Any, Any][source]#

Gaussian point spread function.

Create a Gaussian point spread function (PSF).

Parameters:

  • size (List[int]) – The size of the PSF.

  • sigma (float) – The standard deviation of the PSF.

Returns:

The Gaussian PSF.

Return type:

np.ndarray

static motion_psf(size: list[int], length: float, angle_xy: float, angle_z: int = 0) → numpy.ndarray[Any, Any][source]#

Motion point spread function.

Create a motion point spread function (PSF).

Parameters:

  • size (list[int]) – size of the PSF

  • length (float) – length of the PSF

  • angle_xy (float) – angle of the PSF

  • angle_z (int, optional) – tilt in the z-axis. Defaults to 0.

Returns:

The motion PSF

Return type:

np.ndarray

static deconvolution(img: numpy.ndarray[Any, Any], bw_img: numpy.ndarray[Any, Any], blurd_bw_img: numpy.ndarray[Any, Any], deconv: bool, deconv_method: str, deconv_iter: int, deconv_mask_weight: float, small_float_val: float = 1e-06) → numpy.ndarray[Any, Any][source]#

Deconvolution.

Perform deconvolution on the image.

Parameters:

  • img (np.ndarray) – The image to deconvolve

  • bw_img (np.ndarray) – The binary image to use for deconvolution

  • blurd_bw_img (np.ndarray) – The blurred binary image to use for deconvolution

  • deconv (bool) – Whether to perform deconvolution

  • deconv_method (str) – The method to use for deconvolution

  • deconv_iter (int) – The number of iterations for deconvolution

  • deconv_mask_weight (float) – The weight for the deconvolution mask

  • small_float_val (float, optional) – The small float value. Defaults to 1e-6.

Returns:

The deconvolved image

Return type:

np.ndarray

static sharpness_analysis(gray_img: numpy.ndarray[Any, Any], img: numpy.ndarray[Any, Any], features: dict[str, object], estimate_sharpness: bool = True) → dict[str, object][source]#

Sharpness analysis.

Estimate the sharpness of the image using FFTs.

Parameters:

  • gray_img (np.ndarray) – The grayscale image

  • img (np.ndarray) – The image

  • features (dict) – The features of the image

  • estimate_sharpness (bool, optional) – Whether to estimate sharpness.

Defaults to True.

Returns:

The features of the image

Return type:

dict

static detect_edges(img: numpy.ndarray[Any, Any], method: str, blur_radius: float, threshold: dict[str, float]) → numpy.ndarray[Any, Any][source]#

Detect edges.

Detect edges in the image.

Parameters:

  • img (np.ndarray) – The image to detect edges

  • method (str) – The method to use for edge detection

  • blur_radius (float) – The radius for the blur

  • threshold (dict) – The threshold for edge detection

Returns:

The filled edges

Return type:

np.ndarray

static process_edges(edges_mag: numpy.ndarray[Any, Any], low_threshold: float, blur_radius: float) → numpy.ndarray[Any, Any][source]#

Process the edges.

Process the edges using the low threshold.

Parameters:

  • edges_mag (np.ndarray) – The edges magnitude

  • low_threshold (float) – The low threshold

  • blur_radius (float) – The radius for the blur

Returns:

The filled edges

Return type:

np.ndarray

static process_edges_mean(edges_mag: numpy.ndarray[Any, Any], blur_radius: float) → numpy.ndarray[Any, Any][source]#

Process the edges.

Process the edges using the mean.

Parameters:

  • edges_mag (np.ndarray) – The edges magnitude

  • blur_radius (float) – The radius for the blur

Returns:

The filled edges

Return type:

np.ndarray

static make_gaussian(size: int, fwhm: int = 3, center: tuple[int, int] | None = None) → numpy.ndarray[Any, Any][source]#

Make a square gaussian kernel.

Method to make a square gaussian kernel.

Parameters:

  • size (int) – The size of the square.

  • fwhm (int, optional) – The full-width-half-maximum. Defaults to 3.

  • center (tuple, optional) – The center of the square. Defaults to None.

Returns:

The square gaussian kernel.

Return type:

np.ndarray