class ImageStitching

make_weight_matrix(height1, width1, height2, width2, overlap, side)

Generate a linear-ramp weighting matrix for image stitching.

Parameters

• height1 (int) – Size of the 1st image.

• width1 (int) – Size of the 1st image.

• height2 (int) – Size of the 2nd image.

• width2 (int) – Size of the 2nd image.

• overlap (int) – Width of the overlap area between two images.

• side ({0, 1}) – Only two options: 0 or 1. It is used to indicate the overlap side respects to image 1. “0” corresponds to the left side. “1” corresponds to the right side.

pre_process()

This method is called immediately after base_pre_process().

process_frames(data)

This method is called after the plugin has been created by the pipeline framework and forms the main processing step

Parameters

data (list(np.array)) – A list of numpy arrays for each input dataset.

setup()

This method is first to be called after the plugin has been created. It determines input/output datasets and plugin specific dataset information such as the pattern (e.g. sinogram/projection).

stitch_image(mat1, mat2, overlap, side, wei_mat1, wei_mat2, norm)

Stitch projection images or sinogram images using a linear ramp.

Parameters

• mat1 (array_like) – 2D array. Projection image or sinogram image.

• mat2 (array_like) – 2D array. Projection image or sinogram image.

• overlap (float) – Width of the overlap area between two images.

• side ({0, 1}) – Only two options: 0 or 1. It is used to indicate the overlap side respects to image 1. “0” corresponds to the left side. “1” corresponds to the right side.

• wei_mat1 (array_like) – Weighting matrix used for image 1.

• wei_mat2 (array_like) – Weighting matrix used for image 2.

• norm (bool, optional) – Enable/disable normalization before stitching.

Returns

Stitched image.

Return type

array_like