Hair Removal (GAN)
Hair Removal benchmark using hairless samples from the PH2 database and the GAN-based deep neural network by Attia et al. to simulate hair on them.Method
Xie
Hair removal algorihm by Xie et al. Implementation provided by the authors Xie, Feng-Ying, et al. "PDE-based unsupervised repair of hair-occluded information in dermoscopy images of melanoma." Computerized Medical Imaging and Graphics 33.4 (2009): 275-282.Results
Sample | Vifp | Uqi | Msssim | P hvs m | P hvs | Mse | Ssim | Psnr | Rmse |
---|---|---|---|---|---|---|---|---|---|
IMD006 | 0.981 | 0.999 | 0.964 | 38.082 | 36.763 | 19.831 | 0.858 | 35.157 | 4.453 |
IMD010 | 0.971 | 0.997 | 0.928 | 31.409 | 30.617 | 55.898 | 0.835 | 30.657 | 7.476 |
IMD017 | 0.976 | 0.998 | 0.970 | 36.911 | 35.578 | 22.790 | 0.866 | 34.553 | 4.774 |
IMD018 | 0.981 | 0.999 | 0.960 | 37.616 | 36.368 | 23.648 | 0.848 | 34.393 | 4.863 |
IMD019 | 0.973 | 0.999 | 0.940 | 30.956 | 30.135 | 51.373 | 0.853 | 31.023 | 7.167 |
IMD020 | 0.975 | 0.999 | 0.960 | 37.274 | 35.498 | 29.561 | 0.840 | 33.424 | 5.437 |
IMD030 | 0.977 | 0.999 | 0.972 | 37.842 | 36.295 | 23.671 | 0.847 | 34.389 | 4.865 |
IMD033 | 0.976 | 0.999 | 0.961 | 36.392 | 35.070 | 27.696 | 0.851 | 33.707 | 5.263 |
IMD044 | 0.970 | 0.998 | 0.972 | 37.093 | 35.577 | 27.085 | 0.874 | 33.804 | 5.204 |
IMD050 | 0.980 | 0.999 | 0.960 | 35.725 | 34.877 | 28.814 | 0.846 | 33.535 | 5.368 |
IMD061 | 0.967 | 0.998 | 0.964 | 34.594 | 33.186 | 39.240 | 0.839 | 32.194 | 6.264 |
IMD063 | 0.973 | 0.997 | 0.970 | 38.218 | 36.686 | 23.189 | 0.842 | 34.478 | 4.816 |
IMD075 | 0.974 | 0.997 | 0.967 | 36.416 | 35.078 | 29.230 | 0.830 | 33.473 | 5.406 |
Mean | 0.975 | 0.998 | 0.961 | 36.041 | 34.748 | 30.925 | 0.848 | 33.445 | 5.489 |