Sense Wax Attack dataset (SWAX)
收藏arXiv2019-10-22 更新2024-08-06 收录
下载链接：
http://arxiv.org/abs/1910.09642v1
下载链接
链接失效反馈官方服务：
资源简介：
Sense Wax Attack数据集（SWAX）由联邦大学米纳斯吉拉斯分校计算机科学系智能感知实验室创建，旨在解决人脸欺骗检测问题。该数据集包含超过1800张人脸图像和110个视频，涵盖55个人/蜡像，分为训练、验证和测试集，具有广泛的表情、光照和姿态变化。数据集通过从不受限制的在线资源中收集真实人类和蜡像图像/视频创建，用于研究无约束环境中的攻击。SWAX数据集的应用领域包括提高反欺骗系统的鲁棒性，特别是针对高质量的蜡像攻击。
The Sense Wax Attack (SWAX) dataset was developed by the Intelligent Perception Laboratory, Department of Computer Science, Federal University of Minas Gerais, to address the task of face spoofing detection. This dataset comprises over 1,800 facial images and 110 videos, covering 55 individuals and wax figures, and is partitioned into training, validation, and test subsets, with comprehensive variations in facial expressions, lighting conditions, and poses. The dataset was constructed by gathering real human and wax figure images/videos from unrestricted online sources, and is utilized for research on spoofing attacks in unconstrained environments. Application areas of the SWAX dataset include enhancing the robustness of anti-spoofing systems, particularly against high-quality wax figure spoofing attacks.
提供机构：
联邦大学米纳斯吉拉斯分校计算机科学系智能感知实验室
创建时间：
2019-10-22
