This documentation is for scikit-learn version 0.10Other versions

Citing

If you use the software, please consider citing scikit-learn.

This page

6.2. Feature extraction

The sklearn.feature_extraction module can be used to extract features in a format supported by machine learning algorithms from datasets consisting of formats such as text and image.

6.2.1. Text feature extraction

XXX: a lot to do here

6.2.2. Image feature extraction

6.2.2.1. Patch extraction

The extract_patches_2d function extracts patches from an image stored as a two-dimensional array, or three-dimensional with color information along the third axis. For rebuilding an image from all its patches, use reconstruct_from_patches_2d. For example let use generate a 4x4 pixel picture with 3 color channels (e.g. in RGB format):

>>> import numpy as np
>>> from sklearn.feature_extraction import image

>>> one_image = np.arange(4 * 4 * 3).reshape((4, 4, 3))
>>> one_image[:, :, 0]  # R channel of a fake RGB picture
array([[ 0,  3,  6,  9],
       [12, 15, 18, 21],
       [24, 27, 30, 33],
       [36, 39, 42, 45]])

>>> patches = image.extract_patches_2d(one_image, (2, 2), max_patches=2,
...     random_state=0)
>>> patches.shape
(2, 2, 2, 3)
>>> patches[:, :, :, 0]
array([[[ 0,  3],
        [12, 15]],

       [[15, 18],
        [27, 30]]])
>>> patches = image.extract_patches_2d(one_image, (2, 2))
>>> patches.shape
(9, 2, 2, 3)
>>> patches[4, :, :, 0]
array([[15, 18],
       [27, 30]])

Let us now try to reconstruct the original image from the patches by averaging on overlapping areas:

>>> reconstructed = image.reconstruct_from_patches_2d(patches, (4, 4, 3))
>>> np.testing.assert_array_equal(one_image, reconstructed)

The PatchExtractor class works in the same way as extract_patches_2d, only it supports multiple images as input. It is implemented as an estimator, so it can be used in pipelines. See:

>>> five_images = np.arange(5 * 4 * 4 * 3).reshape(5, 4, 4, 3)
>>> patches = image.PatchExtractor((2, 2)).transform(five_images)
>>> patches.shape
(45, 2, 2, 3)