Improving Face Verification using Skin Color Information. Marcel, S. & Bengio, S. In Proceedings of the 16th International Conference on Pattern Recognition, ICPR, volume 2, pages 11–15, 2002. IEEE Computer Society Press.
Improving Face Verification using Skin Color Information [link]Paper  abstract   bibtex   
The performance of face verification systems has steadily improved over the last few years, mainly focusing on models rather than on feature processing. State-of-the-art methods often use the gray-scale face image as input. In this paper, we propose to use an additional feature to the face image: the skin color. The new feature set is tested on a benchmark database, namely XM2VTS, using a simple discriminant artificial neural network. Results show that the skin color information improves the performance.
@inproceedings{marcel:2002:icpr,
  author = {S. Marcel and S. Bengio},
  title = {Improving Face Verification using Skin Color Information},
  booktitle = {Proceedings of the 16th International Conference on Pattern Recognition, {ICPR}},
  year = 2002,
  volume = 2,
  pages = {11--15},
  publisher = {IEEE Computer Society Press},
  url = {publications/ps/marcel_2002_icpr.ps.gz},
  pdf = {publications/pdf/marcel_2002_icpr.pdf},
  djvu = {publications/djvu/marcel_2002_icpr.djvu},
  original= {2002/skin_icpr},
  idiap = {publications/pdf/rr01-44.pdf},
  topics = {biometric_authentication},
  web = {http://dx.doi.org/10.1109/ICPR.2002.1048318},
  abstract = {The performance of face verification systems has steadily improved over the last few years, mainly focusing on models rather than on feature processing.  State-of-the-art methods often use the gray-scale face image as input.  In this paper, we propose to use an additional feature to the face image: the skin color. The new feature set is tested on a benchmark database, namely XM2VTS, using a simple discriminant artificial neural network. Results show that the skin color information improves the performance.},
  categorie = {C}
}

Downloads: 0