English

Boosting Generalization with Adaptive Style Techniques for Fingerprint Liveness Detection

Computer Vision and Pattern Recognition 2023-10-25 v3 Artificial Intelligence

Abstract

We introduce a high-performance fingerprint liveness feature extraction technique that secured first place in LivDet 2023 Fingerprint Representation Challenge. Additionally, we developed a practical fingerprint recognition system with 94.68% accuracy, earning second place in LivDet 2023 Liveness Detection in Action. By investigating various methods, particularly style transfer, we demonstrate improvements in accuracy and generalization when faced with limited training data. As a result, our approach achieved state-of-the-art performance in LivDet 2023 Challenges.

Keywords

Cite

@article{arxiv.2310.13573,
  title  = {Boosting Generalization with Adaptive Style Techniques for Fingerprint Liveness Detection},
  author = {Kexin Zhu and Bo Lin and Yang Qiu and Adam Yule and Yao Tang and Jiajun Liang},
  journal= {arXiv preprint arXiv:2310.13573},
  year   = {2023}
}

Comments

1st Place in LivDet2023 Fingerprint Representation Challenge

R2 v1 2026-06-28T12:56:58.067Z