Skip to main content

A minimalist toolkit for holographic plankton image segmentation

Project description

HoloContour Logo

A minimalist tool for holographic plankton image segmentation.

HoloContour

This repository provides a pipeline for segmenting holographic particle images using a hybrid region-growing and contour refinement method. It integrates with the MorphoCut framework and exports outputs compatible with EcoTaxa.


🚀 Features

  • Contour-based object detection with:
    • Intensity filtering
    • Histogram matching (optional)
    • Region growing from intensity minima
  • Optional plot saving of initial vs. refined masks
  • Compatible with EcoTaxaWriter
  • YAML-based configuration
  • Safe fallback for empty masks

⚙️ Usage

1. Install Dependencies

pip install -r requirements.txt

python main.py --config configs/sample_config.yaml --input path/to/your/data

🖼 Example

The figure below shows an example of the pipeline's segmentation output:

Segmentation Result

  • Red dashed: Initial region estimate
  • Blue solid: Refined segmentation contour

License

This project is licensed under the MIT License - see the LICENSE file for details.


Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

holocontour-0.1.0.tar.gz (6.3 MB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

holocontour-0.1.0-py3-none-any.whl (6.5 MB view details)

Uploaded Python 3

File details

Details for the file holocontour-0.1.0.tar.gz.

File metadata

  • Download URL: holocontour-0.1.0.tar.gz
  • Upload date:
  • Size: 6.3 MB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.9.7

File hashes

Hashes for holocontour-0.1.0.tar.gz
Algorithm Hash digest
SHA256 71a07dfc402fbbf8a79adb1e2ceff237f247042e7fafaebe147f32bc4022f9d1
MD5 a78c42d0575642b7c7a1ae533edb1ba4
BLAKE2b-256 5ee0357c9c7dd4a410a463cd771f444d71eceb457ad63e7a6d2d1dd347e643b7

See more details on using hashes here.

File details

Details for the file holocontour-0.1.0-py3-none-any.whl.

File metadata

  • Download URL: holocontour-0.1.0-py3-none-any.whl
  • Upload date:
  • Size: 6.5 MB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.9.7

File hashes

Hashes for holocontour-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 8ebfdf07fc12f1514b80638e2474a9d2389d45f55e652a298936cb21613ced7f
MD5 f7418ae239527c595b74a9f87f5d1ce2
BLAKE2b-256 cff173bfb823fd3995e251ffb9b8bf862dafed28b3add45d6eef8ec17e182ecd

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page