1,920 questions
1
vote
1
answer
99
views
How to reduce xarray.coarsen with majority vote?
I'm currently trying to resample a large geotiff file to a coarser resolution. This file contains classes of tree species (indicated by integer values) at each pixel, so I want to resample each block (...
3
votes
2
answers
201
views
How does Local Binary Pattern return an image?
I'm trying to understand how scikit-image's local_binary_pattern() function works. Let's take the simplest setup: input is a grayscale image, radius = 1, n_points = 4, method = "uniform". ...
0
votes
1
answer
90
views
Skeletonized microglial cell branches not reconnecting after binarization, and background structures not removed
I'm working on a Python script for processing immunohistochemistry microscopy images of microglial cells. The goal is to:
Extract the green channel.
Apply CLAHE for contrast enhancement.
Perform Otsu ...
0
votes
1
answer
33
views
Photomosaic library raising TypeError: slice indices must be integers or None or have an __index__ method
I have the following code (a slightly modified version of this) to create a mosaic from many individual images:
import sys
import photomosaic as phmos
from skimage import io
image = io.imread("r....
0
votes
0
answers
86
views
How to speed up calibrating denoiser?
I'm trying to calibrate the denoiser like this:
import numpy as np
from skimage.restoration import (
calibrate_denoiser,
denoise_tv_chambolle,
denoise_invariant,
)
# create random noisy ...
2
votes
0
answers
189
views
Different SSIM Results for 3D Microscopy Slices Using torchmetrics and skimage: Which One Should I Use?
I am working with 3D microscopy data (e.g., stacks of 2D images) and trying to compute the Structural Similarity Index (SSIM) between two 3D images. The goal is to evaluate the similarity between an ...
1
vote
0
answers
93
views
Instance Segmentation of Curved Surfaces
I have a render of four identical objects and need to segment the curved surfaces and classify them (associate similar ones with each other).
All the objects are positioned at the same angle relative ...
0
votes
1
answer
127
views
How to optimize the weight for TV filter?
I have 2d data which has background noise and assembled high values. I'm trying to apply the TV filter to denoise the data. Is there a suitable method to avoid over-denoising the data?
I have tried to ...
3
votes
1
answer
94
views
How to use skimage to denoise 2d array with nan values?
I'm trying to apply the TV filter to 2D array which includes many nan values:
from skimage.restoration import denoise_tv_chambolle
import numpy as np
data_random = np.random.random ([100,100])*100
...
0
votes
0
answers
139
views
Find straight lines in image
I would like to find the locations of some lines in a series of images. The images are exported from GoPro videos, with the camera looking down onto a sloping floor (a beach, so to speak) in a wave ...
3
votes
2
answers
166
views
With Python, how to apply vector operations to a neighborhood in an n-D image?
I have a 3D image with vector components (i.e., a mapping from R3 to R3). My goal is to replace each vector with the vector of maximum norm within its 3x3x3 neighborhood.
This task is proving to be ...
0
votes
3
answers
2k
views
How to solve this ERROR: Could not find a version that satisfies the requirement torch==1.6.0?
I'm using a demo on Colab notebook called Deep Exemplar Based Video Colorization. https://colab.research.google.com/drive/1Y1XTlTdUG-2LzrH1Vnr_osg9BQavfYsz?usp=sharing
Worked swimmingly for four years ...
2
votes
1
answer
608
views
multiprocess with joblib and skimage: PicklingError: Could not pickle the task to send it to the workers
I'm trying to parallelize the task of finding minimum cost paths through a raster cost surface, but I keep bumping into the same PicklingError: Could not pickle the task to send it to the workers.
...
0
votes
1
answer
100
views
Python skimage: Turning grayscale image array into float makes the image use color instead of grayscale
When using the skimage.io module in python to read an image in grayscale, it works as intended. However, doing anything to the numpy array holding the values which results in them changing to float ...
0
votes
0
answers
101
views
Saving region properties from skimage.measure to a pickle file raises RecursionError: maximum recursion depth exceeded
In my analysis code, I am performing some image properties analysis using skimage.measure.regionprops.
In order to save processing time, I would like to save the region properties to a file and I was ...