Summary of A Multi-modal Approach For Face Anti-spoofing in Non-calibrated Systems Using Disparity Maps, by Ariel Larey et al.
A Multi-Modal Approach for Face Anti-Spoofing in Non-Calibrated Systems using Disparity Maps
by Ariel Larey, Eyal Rond, Omer Achrack
First submitted to arxiv on: 31 Oct 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Artificial Intelligence (cs.AI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The proposed method overcomes the challenge of detecting face spoof attacks without using stereo-depth cameras by leveraging facial attributes to derive disparity information and estimate relative depth. The Disparity Model, a multi-modal anti-spoofing model, incorporates created disparity maps as a third modality alongside the two original sensor modalities. This approach outperforms existing methods in literature, achieving an Equal Error Rate (EER) of 1.71% and a False Negative Rate (FNR) of 2.77% at a False Positive Rate (FPR) of 1%. The Disparity Model also introduces a model ensemble that addresses 3D spoof attacks, achieving an EER of 2.04% and an FNR of 3.83% at an FPR of 1%. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Face recognition technologies are vulnerable to face spoofing attacks, which involve unique 3D structures like printed papers or mobile device screens. To detect these attacks without using expensive stereo-depth cameras, researchers propose a method that uses facial attributes to derive disparity information and estimate relative depth. This approach works with non-calibrated systems and is more effective than existing methods. |
Keywords
» Artificial intelligence » Face recognition » Multi modal
