diff --git a/Makefile b/Makefile
index 03712fcf..b80eba0d 100644
--- a/Makefile
+++ b/Makefile
@@ -16,5 +16,5 @@ coverage:
 	nosetests skimage --with-coverage --cover-package=skimage
 
 html:
-	pip install sphinx
-	make -C doc html
+	pip install -q sphinx
+	export SPHINXOPTS=-W; make -C doc html
diff --git a/skimage/filters/rank/generic.py b/skimage/filters/rank/generic.py
index 467c54ed..31e80b76 100644
--- a/skimage/filters/rank/generic.py
+++ b/skimage/filters/rank/generic.py
@@ -1,5 +1,5 @@
 """The local histogram is computed using a sliding window similar to the method
-described in [1]_.
+described in [1].
 
 Input image can be 8-bit or 16-bit, for 16-bit input images, the number of
 histogram bins is determined from the maximum value present in the image.
@@ -749,7 +749,7 @@ def tophat(image, selem, out=None, mask=None, shift_x=False, shift_y=False):
 
 def noise_filter(image, selem, out=None, mask=None, shift_x=False,
                  shift_y=False):
-    """Noise feature as described in [1]_.
+    """Noise feature as described in [1].
 
     Parameters
     ----------
@@ -800,7 +800,7 @@ def noise_filter(image, selem, out=None, mask=None, shift_x=False,
 
 
 def entropy(image, selem, out=None, mask=None, shift_x=False, shift_y=False):
-    """Local entropy [1]_.
+    """Local entropy [1].
 
     The entropy is computed using base 2 logarithm i.e. the filter returns the
     minimum number of bits needed to encode the local greylevel distribution.
diff --git a/skimage/io/_plugins/pil_plugin.ini b/skimage/io/_plugins/pil_plugin.ini
index e6382e5e..14034410 100644
--- a/skimage/io/_plugins/pil_plugin.ini
+++ b/skimage/io/_plugins/pil_plugin.ini
@@ -1,3 +1,3 @@
 [pil]
 description = Image reading via the Python Imaging Library
-provides = imread, imsave, imshow, _app_show
+provides = imread, imsave
diff --git a/skimage/restoration/deconvolution.py b/skimage/restoration/deconvolution.py
index d4c51d95..632d6788 100644
--- a/skimage/restoration/deconvolution.py
+++ b/skimage/restoration/deconvolution.py
@@ -363,7 +363,7 @@ def richardson_lucy(image, psf, iterations=50, clip=True):
 
     References
     ----------
-    .. [2] http://en.wikipedia.org/wiki/Richardson%E2%80%93Lucy_deconvolution
+    .. [1] http://en.wikipedia.org/wiki/Richardson%E2%80%93Lucy_deconvolution
     """
     image = image.astype(np.float)
     psf = psf.astype(np.float)
diff --git a/skimage/transform/_geometric.py b/skimage/transform/_geometric.py
index 3a2972c0..c94e3b76 100644
--- a/skimage/transform/_geometric.py
+++ b/skimage/transform/_geometric.py
@@ -332,7 +332,9 @@ class ProjectiveTransform(GeometricTransform):
 
 class AffineTransform(ProjectiveTransform):
 
-    """2D affine transformation of the form::
+    """2D affine transformation of the form:
+
+    ..:math:
 
         X = a0*x + a1*y + a2 =
           = sx*x*cos(rotation) - sy*y*sin(rotation + shear) + a2
@@ -551,7 +553,9 @@ class PiecewiseAffineTransform(GeometricTransform):
 
 
 class SimilarityTransform(ProjectiveTransform):
-    """2D similarity transformation of the form::
+    """2D similarity transformation of the form:
+
+    ..:math:
 
         X = a0 * x - b0 * y + a1 =
           = m * x * cos(rotation) - m * y * sin(rotation) + a1
@@ -715,7 +719,9 @@ class SimilarityTransform(ProjectiveTransform):
 
 
 class PolynomialTransform(GeometricTransform):
-    """2D transformation of the form::
+    """2D transformation of the form:
+
+    ..:math:
 
         X = sum[j=0:order]( sum[i=0:j]( a_ji * x**(j - i) * y**i ))
         Y = sum[j=0:order]( sum[i=0:j]( b_ji * x**(j - i) * y**i ))