Commit 8fce7fe7 authored by Jean-Yves TINEVEZ's avatar Jean-Yves TINEVEZ
Browse files

Add info on what this repo is for.

parent 0478e14a
Implementation of Stardist for detection of small particles.
# Training of a StarDist model for the detection for sub-resolved particles.
This repository contains the scripts, model and parameters used to train a StarDist model on the dataset of the 2014 ISBI Grand Challenge on Single-Particle Tracking.
See for information on the challenge.
We used this model to compare the performance of a tracking implementation based on StarDist, versus its counterpart based on a classic Laplacian of Gaussian (LoG) detector.
Both approaches are subsequently used in TrackMate.
- Raw data: synthetic time-lapses of different particles (microtubules, vesicles) in different SNR and corresponding ground truth coordinates of the particles stored in xml.
- Step 1: generate training data: Image + labeled image. Image will be same as those in the raw dataset, and the labeled image will be generated out of coordinates stored in corresponding xml files.
Supports Markdown
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment