ad-autoevaluation is my UROP and final year project. The aims of this project included: (1) preprocessing of clinical skin images of atopic dermatitis (AD) patients, (2) to evaluate the severity of erythema sign of AD by utilising supervised learning.
Due to privacy reasons, skin image dataset cannot be provided.
Please note some files (e.g. lesion_seg and severity_class) are still outdated as I am moving the files from juypter (.ipynb) to .py.
The scripts require:
- Python (>= 3.5)
- NumPy (>= 1.11.0)
- SciPy (>= 0.17.0)
- scikit-learn (= 0.20.3 if you want to use the trained models)
- scikit-image
- joblib (>= 0.11)
- OpenCV