HySpeFAS: A Hyperspectral Face Anti-Spoofing Dataset Based on Snapshot Compressive Imaging
- 24 December 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Forensics and Security
- Vol. 21 (15566013) , 669-680
Abstract
Face anti-spoofing, which aims to prevent the attacks of widely-used face recognition systems, is highly related to personal privacy and property security. However, existing benchmarks on face anti-spoofing mainly focus on RGB images, further challenged by consistently developed 3D high-fidelity (HiFi) masks. To facilitate the research on multimodal face anti-spoofing, we construct the HyperSpectral Face Anti-Spoofing (HySpeFAS) dataset. We introduce the newly-developed snapshot spectral imaging (SSI) technology to capture real and spoof faces, as well as identify unknown HiFi masks. Specifically, hyperspectral images (HSIs) acquired by SSI sensor contain rich information about the chemical composition of the targets, which can be used to effectively distinguish live human skin and various spoof materials. The HySpeFAS dataset contains 22,368 multimodal images (i.e., RGB, SSI, HSI) of 17 live subjects and 60 spoof subjects. Moreover, extensive experiments with baseline deep learning models validate the special features of the SSI images and the potential of SSI in FAS. By publishing the dataset as well as the baseline models, we encourage the community to foster the algorithm study associated with hyperspectral images and the development of SSI-equipped intelligent systems.Keywords
Funding Information
- China State key development program in 14th Five-Year (2021YFF0602103)
- National Key Research and Development Program of China (2023YFB2806703)
- National Natural Science Foundation of China (U22A6004)
This publication has 89 references indexed in Scilit:
- YOLO5Face: Why Reinventing a Face Detector2023
- Ultraspectral Imaging Based on Metasurfaces with Freeform Shaped Meta‐AtomsLaser & Photonics Reviews, 2022
- On Disentangling Spoof Trace for Generic Face Anti-spoofing2020
- BIRNAT: Bidirectional Recurrent Neural Networks with Adversarial Training for Video Snapshot Compressive Imaging2020
- Face Anti-Spoofing via Disentangled Representation Learning2020
- Face Anti-Spoofing with Human Material Perception2020
- CelebA-Spoof: Large-Scale Face Anti-spoofing Dataset with Rich Annotations2020
- Hyperspectral Face Databases for Facial Recognition Research2016
- An Overview of Spectral Imaging of Human Skin Toward Face Recognition2016
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015