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)
Parameters:
-
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
Parameters: Returns: np.array<shape>
-
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
Parameters: Returns: np.array<shape>
-
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