A simple image-level annotation tool supporting multi-channel images.
A simple image-level annotation tool supporting multi-channel images for napari.
Start the labeling tool from the menu
Utilities > label tool for classification.
First, click on the Choose directory button to open the folder selection window, and select the folder that contains the images you want to label and annotate.
It will automatically list and display the images of tif, png, jpg, and bmp formats. If you want to view the channels of a multi-channel image separately, check the split channels checkbox.
Initially, all channels will be opened in grayscale, but the pseudo-color and contrast adjustments you specified will be
carried over when you open the next image.
Thanks to napari, you can freely merge channels and turn them on and off.
Label classes can be added, and can be removed by typing the same name as an already added class.
It will automatically save the labels.csv file with the image path and label, and the class.txt file with the class of the label.
If labels.csv and class.txt are already in the folder, they will be loaded and reflected automatically.
You can install
napari-labelimg4classification via pip:
pip install napari-labelimg4classification
To install latest development version :
pip install git+https://github.com/hiroalchem/napari-labelimg4classification.git
Contributions are very welcome. Tests can be run with tox, please ensure the coverage at least stays the same before you submit a pull request.
Distributed under the terms of the MIT license, "napari-labelimg4classification" is free and open source software
If you encounter any problems, please file an issue along with a detailed description.
- 03 December 2021
- 02 December 2021
- Information not submitted
- Stars: 4
- Forks: 2
- Issues + PRs: 1