Skip to content

Add Outlier Remover to CIL processors #2262

@RasmiaKulan

Description

@RasmiaKulan

Description

  • Add Mantid Imaging's Remove Outliers pre-processing operation to CIL's Processors class.
  • Create a Jupyter notebook to test the process on a dataset.

What is Outlier Removal?
It removes pixel values identified as outliers based on configurable parameters. It compares each pixel to the local median and identifies those beyond the threshold.

Key Parameters:

  • diff - Pixel value difference threshold used to detect outliers. It is adjusted depending on the values in your data and how aggressive you want the filter to be.
  • radius - Size of the median filter applied
  • mode - Type of outliers to remove:�Bright or Dark (OUTLIERS_BRIGHT, OUTLIERS_DARK)

When is it used?
As a pre-processing step to reduce very bright or dead pixels in the data.

Environment

import cil, sys
print(cil.version.version, cil.version.commit_hash, sys.version, sys.platform)

Metadata

Metadata

Assignees

No one assigned

    Labels

    enhancementNew feature or request

    Type

    No type

    Projects

    Status

    Todo

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions