Dataset and codes for the paper "No-reference quality assessment of dermoscopic images using minimal expert supervision"

Dataset and Source Code for DermaIQA: No-Reference Quality Assessment of Dermoscopic Images

This repository contains:

Test Dataset
- 150 high-quality dermoscopic images
- 150 low-quality dermoscopic images

Inference Code
- Python implementation of DermaIQA
- Inference pipeline for quality assessment
- Requirements and dependencies
- Usage examples (inference.py)

Associated with the paper:
Ferraris A., Branciforti F., Meiburger K., Veronese F., Zavattaro E., Savoia P., and Salvi M., "No-reference quality assessment of dermoscopic images using minimal expert supervision", Applied Sciences, 2026.

Note: The training code and dataset generation pipeline are available upon reasonable request to the corresponding author.