scikit-image/scikit-image

Image Processing SciKit (Toolbox for SciPy)

Curtis Rueden

@ctrueden

But it sounds like you have other/better ways of getting the data into Python already. Particularly nibabel which looks pretty tailored to your needs?

It’s just a matter of getting the pixels as a numpy array, right?

E | M

@ewuramaminka

nibabel doesnt even let me create the histograms i want

my current need is to use threshold_otsu to threshold my nifty .. if u could please try that

using simple ITK

Curtis Rueden

@ctrueden

It looks like you need to write:

import nibabel as nib
img = nib.load(filename)
data = img.get_fdata()

and then type(data) will be numpy.ndarray instead of Nifti1Image. And you can compute stuff on the data. Does that help?

https://nipy.org/nibabel/gettingstarted.html

E | M

@ewuramaminka

ok i just tried

i still got this 'AttributeError: 'Nifti1Image' object has no attribute 'get_fdata'

Curtis Rueden

@ctrueden

Which version of nibabel?

We can check the source code.

From the changelog: it looks like the get_fdata was added in version 2.2? Are you using an older version? If so, try upgrading.

Gotta run to a meeting. Good luck.

E | M

@ewuramaminka

2.0.2

nibabel ver - 2.0.2

Curtis Rueden

@ctrueden

See if you can update to 2.2 or newer.

E | M

@ewuramaminka

I finally got stik to load it

Thanks very much

E | M

@ewuramaminka

can anyone help with this ? https://stackoverflow.com/questions/55120404/threshold-otsu-attributeerror-axessubplot-object-has-no-attribute-ravel

Dr .Muhammad Anjum Iqbal

@DrMuhammadAnju1_twitter

Hi i DO NOT KNOW , it is proper platform about my problem ! but if any body knows . please let me know . my question is "to get R in python for window "

Mark Harfouche

@hmaarrfk

Mixing languages is hard.

Hi everyone; we're going to try something new for the chat forum. Please direct your browsers to:

https://skimage.zulipchat.com

(or download the app)

We'll try this forum for a few weeks to see how it goes!

E | M

@ewuramaminka

I have dicom files to auto segment using atlas and CNN approach. I’m looking to measure correspondence between these automatic contours and manual contours created by experts. Kindly advise what techniques are best

-Hausdoff distance
-structural similarity index (SSIM)
-Bidirectional local distance measurement (BLD)
-Mean square errors (MSE)
-Dice similarity coefficient
-Distance transforms

Please advise if there are any I haven’t listed and which ones are best for the operation I want to carry out.

Vishesh Mangla

@XtremeGood

someone here?

E | M

@ewuramaminka

im wondering.. nobody replied to my question

Josh Moore

@joshmoore

Perhaps try on https://forum.image.sc ?

Kira Evans

@kne42

the scikit-image devs have switched to using zulip and no longer monitor this channel

tonyVeco

@tonyVeco

Hi everyone!!

Mark Harfouche

@hmaarrfk

Hi everyone; we're going to try something new for the chat forum. Please direct your browsers to:

https://skimage.zulipchat.com

(or download the app)

We'll try this forum for a few weeks to see how it goes!

tonyVeco

@tonyVeco

ok, so I could submit my question there ;)

Andrew Schaub

@drewschaub

Http://scikit-image.org/docs/0.7.0/api/skimage.feature.peak.htm goes to wrong url if banner is clicked, scikits-image.org. I know its an older version, but i also noticed the banner is edited to say scikits-image and not scikit

Andrew Schaub

@drewschaub

https://scikit-image.org/docs/0.7.0/api/skimage.feature.peak.html

Mark Harfouche

@hmaarrfk

Hi Andrew, Thanks can you please raise an issue on the repo?

Not to ignore your message, but I want this zulip chat message to be the first one people see

Hi everyone; we're going to try something new for the chat forum. Please direct your browsers to:
https://skimage.zulipchat.com
(or download the app)
We'll try this forum for a few weeks to see how it goes!

Andrew Schaub

@drewschaub

will do! Ill switch to the other chatroom as well.

Mark Harfouche

@hmaarrfk

Andrew Chalmers

@chalmersgit

Looking at the SSIM metric, does anyone know much about its parameters? Specifically, I've seen that the default window size = 11 is recommended. But to me, this seems like this variable should be dependent on the resolution of the image. Anyone have any thoughts on this?

Andrew Chalmers

@chalmersgit

Just looking at the original ssim paper, they use ~768x512 resolution images. My intuition is to use this as a way of scaling the window size. That is, using the target resolution against the 768x512 as a ratio to scale the window size lower or higher resolution images appropriately.

Andrew Chalmers

@chalmersgit

Oh i see that you are trying to use zulipchat, ill check it out

winash12

@winash12

Hello I had a very basic question here and please feel to guide me to the appropriate link

http://tropic.ssec.wisc.edu/real-time/indian/winds/wm5conv.GIF i have this satellite image. i need to get the latitude and longitude of the contours in that image and convert that into a KML file so that i can load it on google earth. Is that possible with scikit-image ?

Curtis Rueden

@ctrueden

@winash12 Ask on https://skimage.zulipchat.com please!

Joan Massich

@massich

Did I miss read something in doc here, or those two should be giving the same output?

from matplotlib import pyplot as plt
from skimage.draw import disk

fig, axes = plt.subplots(1, 2)
for ax, shape in zip(axes, [None, (10, 10)]):
    img = np.zeros((10, 10), dtype=np.uint8)
    rr, cc = disk((1, 1), 5, shape=shape)
    img[rr, cc] = 1
    ax.imshow(img)

It is like if one is using a circular buffer and the other one not

Joan Massich

@massich

I mean I don't understand why None gives the full disk and (10,10) does not.

why whouldn't (8,8) give me a partial part of it?

Curtis Rueden

@ctrueden

@massich The scikit-image chat moved from here to https://skimage.zulipchat.com.

Joan Massich

@massich

thx

Where communities thrive

People

Repo info

Activity