Skip to content

fancy threshold to intake max foreground #4

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
dsundarraman wants to merge 7 commits into
base: main
Choose a base branch
from
Open

fancy threshold to intake max foreground #4

Changes from 1 commit
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
8ad82f4
modified fancy threshold function to incorporate max foreground to cl…
dsundarraman Mar 12, 2025
49d60b5
Update dexpv2/segmentation.py
dsundarraman Mar 14, 2025
98b2aed
Update dexpv2/segmentation.py
dsundarraman Mar 14, 2025
be1d904
fixed issue with max foreground parameter and adding sigma to alter t…
dsundarraman Mar 14, 2025
1c3a63e
Fix bug of grey_dilation on cp.float16 data
ilan-theodoro May 7, 2025
f334bb2
Improve testing on new reconstruction function
ilan-theodoro May 7, 2025
e137d11
Improve fp16 discretization to reduce memory usage
ilan-theodoro May 9, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
12 changes: 11 additions & 1 deletion dexpv2/segmentation.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -46,7 +46,10 @@ def reconstruction_by_dilation(


def fancy_otsu_threshold(
image: ArrayLike, remove_hist_mode: bool = False, min_foreground: float = 0.0
image: ArrayLike,
remove_hist_mode: bool = False,
min_foreground: float = 0.0,
max_foreground: float = 0.0,
Comment thread
dsundarraman marked this conversation as resolved.
Outdated
) -> float:
"""
Compute Otsu threshold with some additional features.
Expand All @@ -61,6 +64,8 @@ def fancy_otsu_threshold(
Removes histogram mode before computing otsu threshold, useful when background regions are being detected.
min_foreground : float, optional
Minimum threshold value, by default 0.0
max_foreground: float, optional
Maximum threshold value, by default max value of image

Returns
-------
Expand All @@ -86,6 +91,11 @@ def fancy_otsu_threshold(

hist, bin_centers = exposure.histogram(image, nbins)

# clip bins and histogram beyond max_foreground value
if max_foreground != 0.0:
hist = [hist[i] for i in range(len(hist)) if bins[i] < max_foreground]
bins = [bin for bin in bins if bin < max_foreground]
Comment thread
dsundarraman marked this conversation as resolved.
Outdated

# histogram disconsidering pixels we are sure are background
if remove_hist_mode:
remaining_background_idx = hist.argmax() + 1
Expand Down