Skip to content

Instantly share code, notes, and snippets.

@walterreade
Forked from fmder/elastic_transform.py
Created July 6, 2016 13:52
Show Gist options
  • Star 0 You must be signed in to star a gist
  • Fork 0 You must be signed in to fork a gist
  • Save walterreade/8776a0e57274ea27b6d1a94341159963 to your computer and use it in GitHub Desktop.
Save walterreade/8776a0e57274ea27b6d1a94341159963 to your computer and use it in GitHub Desktop.
Elastic transformation of an image in Python
import numpy
from scipy.ndimage.interpolation import map_coordinates
from scipy.ndimage.filters import gaussian_filter
def elastic_transform(image, alpha, sigma, random_state=None):
"""Elastic deformation of images as described in [Simard2003]_.
.. [Simard2003] Simard, Steinkraus and Platt, "Best Practices for
Convolutional Neural Networks applied to Visual Document Analysis", in
Proc. of the International Conference on Document Analysis and
Recognition, 2003.
"""
if random_state is None:
random_state = numpy.random.RandomState(None)
shape = image.shape
dx = gaussian_filter((random_state.rand(*shape) * 2 - 1), sigma, mode="constant", cval=0) * alpha
dy = gaussian_filter((random_state.rand(*shape) * 2 - 1), sigma, mode="constant", cval=0) * alpha
x, y = numpy.meshgrid(numpy.arange(shape[0]), numpy.arange(shape[1]))
indices = numpy.reshape(y+dy, (-1, 1)), numpy.reshape(x+dx, (-1, 1))
return map_coordinates(image, indices, order=1).reshape(shape)
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment