bm_dataset.create_real_synth_dataset module¶
Script for generating synthetic datasets from a single image and landmarks. The output is set of geometrical deformed images with also change color space and related computed new landmarks.
Sample run:
python create_real_synth_dataset.py -i ../data-images/images/Rat-Kidney_HE.jpg -l ../data-images/landmarks/Rat-Kidney_HE.csv -o ../output/synth_dataset --visual
Copyright (C) 2016-2019 Jiri Borovec <jiri.borovec@fel.cvut.cz>
- bm_dataset.create_real_synth_dataset.arg_parse_params()[source]¶
parse the input parameters :return dict: parameters
- bm_dataset.create_real_synth_dataset.deform_image_landmarks(image, points, max_deform=50)[source]¶
deform the image by randomly generated deformation field and compute new positions for all landmarks
- Parameters
image – np.array<height, width, 3>
points – np.array<nb_points, 2>
max_deform (float) – maximal deformation distance in any direction
- Returns
np.array<height, width, 3>, np.array<nb_points, 2>
- bm_dataset.create_real_synth_dataset.draw_image_landmarks(image, points)[source]¶
draw landmarks over the image and return the figure
- Parameters
image – np.array<height, width, 3>
points – np.array<nb_points, 2>
- Returns
object
- bm_dataset.create_real_synth_dataset.export_image_landmarks(image, points, idx, path_out, name_img, visual=False)[source]¶
export the image, landmarks as csv file and if the ‘visual’ is set, draw also landmarks in the image (in separate image)
- bm_dataset.create_real_synth_dataset.generate_deformation_field_gauss(shape, points, max_deform=50, deform_smooth=25)[source]¶
generate deformation field as combination of positive and negative Galatians densities scaled in range +/- max_deform
- bm_dataset.create_real_synth_dataset.generate_deformation_field_rbf(shape, points, max_deform=50, nb_bound_points=25)[source]¶
generate deformation field as thin plate spline deformation in range +/- max_deform
- bm_dataset.create_real_synth_dataset.get_name(path)[source]¶
parse the name without extension from complete path
- Parameters
path (str) –
- Return str
- bm_dataset.create_real_synth_dataset.image_color_shift_hue(image, change_satur=True)[source]¶
take the original image and shift the colour space in HUE
- Parameters
image – np.array<height, width, 3>
change_satur (bool) – whether change also the saturation
- Returns
np.array<height, width, 3>
- bm_dataset.create_real_synth_dataset.main(params)[source]¶
main entry point
- Parameters
params (dict) – dict