gtda.images: Images

The module gtda.images implements techniques that can be used to apply Topological Data Analysis to images.

Preprocessing

images.Binarizer([threshold, n_jobs])

Binarize all 2D/3D greyscale images in a collection.

images.Inverter([max_value, n_jobs])

Invert all 2D/3D images in a collection.

images.Padder([padding, value, n_jobs])

Pad all 2D/3D images in a collection.

images.ImageToPointCloud([n_jobs])

Represent active pixels in 2D/3D binary images as points in 2D/3D space.

Filtrations

images.HeightFiltration([direction, n_jobs])

Filtrations of 2D/3D binary images based on distances to lines/planes.

images.RadialFiltration([center, radius, …])

Filtrations of 2D/3D binary images based on distances to a reference pixel.

images.DilationFiltration([n_iterations, n_jobs])

Filtrations of 2D/3D binary images based on the dilation of activated regions.

images.ErosionFiltration([n_iterations, n_jobs])

Filtrations of 2D/3D binary images based on the erosion of activated regions.

images.SignedDistanceFiltration([…])

Filtrations of 2D/3D binary images based on the dilation and the erosion of activated regions.

images.DensityFiltration([radius, metric, …])

Filtrations of 2D/3D binary images based on the number of activated neighboring pixels.