FiberAnnotator

This repository holds a tool for the easy annotation of fibers, as used in the following publication: FibeR-CNN: Expanding Mask R-CNN to improve image-based fiber analysis

Table of Contents

• FiberAnnotator
• Table of Contents
• Setup
• Usage
• Citation

Setup

1. Install conda.
2. Open a command line.
3. Clone this repository: git clone https://github.com/maxfrei750/FiberAnnotator.git
4. Change into the folder of the repository: cd FiberAnnotator
5. Create a new conda environment: conda env create --file environment.yml
6. Change the IMAGE_GLOB constant in FiberAnnotator.py, to a regular expression that matches the images that you want to annotate.
7. Activate the conda environment: activate FiberAnnotator
8. Run the annotation tool: python3 FiberAnnotator.py

Usage

• Left Click: place keypoint/select keypoint
• Right Click: delete last keypoint
• Up / Down / Left / Right: move active keypoint
• W / A / S / D: move active keypoint
• Mouse Wheel Up / Mouse Wheel Down: increase/decrease thickness of active fiber
• Space: end annotation of current fiber
• Del: delete current/last fiber
• Enter / E: end annotation of current image

Annotation data is saved in the same folder as the input image as soon as the annotation of an image is finished (Enter / E).

Citation

If you use this annotation tool for a publication, then please cite it using the following bibtex-entry:

@article{Frei.2020,
	title = {{FibeR}-{CNN}: {Expanding} {Mask} {R}-{CNN} to improve image-based fiber analysis},
	issn = {0032-5910},
	url = {https://doi.org/10.1016/j.powtec.2020.08.034},
	doi = {10.1016/j.powtec.2020.08.034},
	journal = {Powder Technology},
	author = {Frei, M. and Kruis, F. E.},
	year = {2020},
}