The utility libraries (required to run certain parts of the other code available here) are available from their GitHub repository.
The libraries can also be installed from the PyPI repositories using the following command:
pip install matej-libs
Alternatively, if you need to install a specific version (e.g. 0.1), use the following command:
pip install matej-libs==0.1
This process requires the pip installer.
The libraries can also be installed into a conda environment by activating the environment
conda activate env-name
and then following the instructions above. The environment env-name must contain pip (this is automatically the case when a conda environment with python is created in non-ancient versions of conda).
The code for the Sclera Segmentation Benchmarking Challenge and Group Evaluation is available from its GitHub repository.
This project requires the utility libraries. Additional python dependencies are listed below:
joblib
matplotlib
numpy
pillow
scikit-learn
scipy
tqdmWe provide a platform-agnostic YAML file, which can be used by conda to automatically install the dependencies listed above:
name: ssbc
dependencies:
- python
- tqdm
- joblib
- numpy
- matplotlib
- scipy
- scikit-learnenvironment.yml. You can then create the conda environment using the following command:
conda env create --file environment.yml
Note that the utility libraries will still have to be installed manually as described above, after the environment is created and activated with:
conda activate ssbc
The code that was used for the experiments in IPAD: Iterative Pruning with Activation Deviation for Sclera Biometrics is available from the archived GitHub repository.
The code that was used for the experiments in Exploring Bias in Sclera Segmentation Models: A Group Evaluation Approach is available from the archived GitHub repository.
The project is an upgrade of the SSBC code so see the instructions there for the project requirements and setup.
The code that was used for the experiments in A Comprehensive Investigation into Sclera Biometrics: A Novel Dataset and Performance Study is available from the archived GitHub repository.