A State-of-the-art Neural Network for Robust Face Verification. Marcel, S., Marcel, C., & Bengio, S. In COST275 Workshop on the advent of Biometrics on the Internet, 2002.
A State-of-the-art Neural Network for Robust Face Verification [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 and that the proposed model achieves robust state-of-the-art results.
@inproceedings{marcel:2002:cost,
  author =       {S. Marcel and C. Marcel and S. Bengio},
  title =        {A State-of-the-art Neural Network for Robust Face Verification},
  booktitle = {{COST275} Workshop on the advent of Biometrics on the Internet},
  year =         2002,
  url = {publications/ps/rr02-36.ps.gz},
  pdf = {publications/pdf/rr02-36.pdf},
  djvu = {publications/djvu/rr02-36.djvu},
  original= {2002/face_verif_cost},
  topics = {biometric_authentication},
  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 and that the proposed model achieves robust state-of-the-art results.},
  categorie = {C}
}

Downloads: 0