scikit-learn · keyur9 · Nov 16, 2017 · Nov 18, 2017 · jnothman · Nov 20, 2017
diff --git a/sklearn/datasets/base.py b/sklearn/datasets/base.py
@@ -19,6 +19,7 @@
 
 from ..utils import Bunch
 from ..utils import check_random_state
+from sklearn.utils.image_read import _imread
 
 import numpy as np
 
@@ -742,24 +743,14 @@ def load_sample_images():
     >>> first_img_data.dtype               #doctest: +SKIP
     dtype('uint8')
     """
-    # Try to import imread from scipy. We do this lazily here to prevent
-    # this module from depending on PIL.
-    try:
-        try:
-            from scipy.misc import imread
-        except ImportError:
-            from scipy.misc.pilutil import imread
-    except ImportError:
-        raise ImportError("The Python Imaging Library (PIL) "
-                          "is required to load data from jpeg files")
     module_path = join(dirname(__file__), "images")
     with open(join(module_path, 'README.txt')) as f:
         descr = f.read()
     filenames = [join(module_path, filename)
                  for filename in os.listdir(module_path)
                  if filename.endswith(".jpg")]
     # Load image data for each image in the source folder.
-    images = [imread(filename) for filename in filenames]
+    images = [_imread(filename) for filename in filenames]
 
     return Bunch(images=images,
                  filenames=filenames,

diff --git a/sklearn/datasets/lfw.py b/sklearn/datasets/lfw.py
@@ -32,7 +32,7 @@
 from .base import get_data_home, _fetch_remote, RemoteFileMetadata
 from ..utils import Bunch
 from ..externals.joblib import Memory
-
+from sklearn.utils.image_read import _imread
 from ..externals.six import b
 
 logger = logging.getLogger(__name__)
@@ -137,13 +137,9 @@ def check_fetch_lfw(data_home=None, funneled=True, download_if_missing=True):
 def _load_imgs(file_paths, slice_, color, resize):
     """Internally used to load images"""
 
-    # Try to import imread and imresize from PIL. We do this here to prevent
-    # the whole sklearn.datasets module from depending on PIL.
+    # Try to import imread from scipy. We do this lazily here to prevent
+    # this module from depending on PIL.
     try:
-        try:
-            from scipy.misc import imread
-        except ImportError:
-            from scipy.misc.pilutil import imread
         from scipy.misc import imresize
     except ImportError:
         raise ImportError("The Python Imaging Library (PIL)"
@@ -181,7 +177,7 @@ def _load_imgs(file_paths, slice_, color, resize):
 
         # Checks if jpeg reading worked. Refer to issue #3594 for more
         # details.
-        img = imread(file_path)
+        img = _imread(file_path)
         if img.ndim is 0:
             raise RuntimeError("Failed to read the image file %s, "
                                "Please make sure that libjpeg is installed"

diff --git a/sklearn/datasets/tests/test_base.py b/sklearn/datasets/tests/test_base.py
@@ -163,10 +163,7 @@ def test_load_sample_image():
 def test_load_missing_sample_image_error():
     have_PIL = True
     try:
-        try:
-            from scipy.misc import imread
-        except ImportError:
-            from scipy.misc.pilutil import imread  # noqa
+        from sklearn.utils.image_read import _imread
     except ImportError:
         have_PIL = False
     if have_PIL:

diff --git a/sklearn/utils/image_read.py b/sklearn/utils/image_read.py
@@ -0,0 +1,62 @@
+"""Utility to read image from file as an array."""
+import numpy as np
+
+# Try to import from PIL as imread is deprecated in SciPy 1.0.0,
+# and will be removed in 1.2.0.
+# Github Issue: https://github.com/scikit-learn/scikit-learn/issues/10147
+try:
+    try:
+        from PIL import Image
+    except ImportError:
+        import Image
+except ImportError:
+    raise ImportError("The Python Imaging Library (PIL) "
+                      "is required to load data from jpeg files")
+
+
+def _imread(name, flatten=False, mode=None):
+    """
+    Read an image from a file as an array.
+    This function is only available if Python Imaging Library (PIL) is installed.
+    Parameters
+    ----------
+    name : str or file object
+        The file name or file object to be read.
+    flatten : bool, optional
+        If True, flattens the color layers into a single gray-scale layer.
+    mode : str, optional
+        Mode to convert image to, e.g. ``'RGB'``.  See the Notes for more
+        details.
+    Returns
+    -------
+    imread : ndarray
+        The array obtained by reading the image.
+    Notes
+    -----
+    `imread` uses the Python Imaging Library (PIL) to read an image.
+    The following notes are from the PIL documentation.
+    `mode` can be one of the following strings:
+    * 'L' (8-bit pixels, black and white)
+    * 'P' (8-bit pixels, mapped to any other mode using a color palette)
+    * 'RGB' (3x8-bit pixels, true color)
+    * 'RGBA' (4x8-bit pixels, true color with transparency mask)
+    * 'CMYK' (4x8-bit pixels, color separation)
+    * 'YCbCr' (3x8-bit pixels, color video format)
+    * 'I' (32-bit signed integer pixels)
+    * 'F' (32-bit floating point pixels)
+    PIL also provides limited support for a few special modes, including
+    'LA' ('L' with alpha), 'RGBX' (true color with padding) and 'RGBa'
+    (true color with premultiplied alpha).
+    When translating a color image to black and white (mode 'L', 'I' or
+    'F'), the library uses the ITU-R 601-2 luma transform::
+        L = R * 299/1000 + G * 587/1000 + B * 114/1000
+    When `flatten` is True, the image is converted using mode 'F'.
+    When `mode` is not None and `flatten` is True, the image is first
+    converted according to `mode`, and the result is then flattened using
+    mode 'F'.
+    """
+    im = Image.open(name)
+    # Check if image is PIL
+    if not Image.isImageType(im):
+        raise TypeError("Input is not a PIL image.")
+    return np.asarray(im)