Multispectral-Spoof (MSSpoof)

Multispectral-Spoof is a dataset for multi-spectral face recognition and presentation attack detection (anti-spoofing). The dataset contains images of Bona Fide VIS and NIR images as well as VIS and NIR printed presentation attacks (spoofing attacks) to VIS and NIR systems. The number of clients in the dataset is 21. The recordings are done using a uEye camera with resolution 1280x1024. When recording the images in NIR, a NIR filter of 800nm has been mounted to the camera.

Multispectral-Spoof 是一款面向多光谱人脸识别与呈现攻击检测（防欺骗）任务的数据集。该数据集包含真实可见光（VIS）与近红外（NIR）人脸图像，以及针对可见光与近红外识别系统的打印式呈现攻击（欺骗攻击）样本。本数据集共涵盖21名受测个体，所有图像均通过分辨率为1280×1024的uEye相机采集。在采集近红外图像时，相机搭载了800nm波长的近红外滤光片。

搜集汇总

背景与挑战

背景概述

Multispectral-Spoof (MSSpoof)数据集包含21个身份的真实面部图像和打印欺骗攻击图像，记录于可见光(VIS)和近红外(NIR)光谱。数据集分为训练、开发和测试子集，提供详细的面部关键点注释，用于研究面部识别系统在欺骗攻击下的性能。