In this work, we present a hair removal benchmark of six state-of-the-art algorithms, each with a different approach to segment and inpaint the hair pixels. To evaluate the algorithms, 13 dermoscopic images without hair were selected from the PH2 database. Next, two different hair simulators, providing hairs with a wide range of characteristics, are applied to these images.
This is a paper for the VipIMAGE 2019 Conference [pdf]
Cite this publication with the following Bibtex code:
@inproceedings{talavera2019comparative,
title={Comparative Study of Dermoscopic Hair Removal Methods},
author={Talavera-Mart{\'\i}nez, Lidia and Bibiloni, Pedro and Gonz{\'a}lez-Hidalgo, Manuel},
booktitle={ECCOMAS Thematic Conference on Computational Vision and Medical Image Processing},
pages={12--21},
year={2019},
organization={Springer}
}
Lidia Talavera-Martínez, Pedro Bibiloni and Manuel González-Hidalgo
If you have any doubt about this work, please, do not hesitate to contact me at [email protected]