iBeta-Level-2-Certification-Dataset
收藏资源简介:
iBeta Level 2 PAD反欺骗活体检测训练数据集,用于活体检测训练和反欺骗研究,特别关注3D攻击(面具)和动作。该数据集包含超过25000个视频,每个视频大约10秒,是多帧视频,包含多种攻击类型,如硅胶面具攻击、乳胶面具攻击等,并在iOS和Android手机上进行了捕获,适用于训练和评估活体检测模型。
iBeta Level 2 PAD anti-spoofing liveness detection training dataset, which is designed for liveness detection model training and anti-spoofing research, with particular emphasis on 3D attacks (masks) and motion-based attacks. This dataset contains over 25,000 multi-frame videos, each approximately 10 seconds in duration, covering multiple attack types such as silicone mask attacks, latex mask attacks and more. The videos were captured using iOS and Android smartphones, and is suitable for training and evaluating liveness detection models.
iBeta Level 2 PAD Anti-Spoofing (3D Masks) — Liveness Detection Training Dataset
数据集概述
- 许可证: cc-by-nc-4.0
- 标签: liveness detection, anti-spoofing, biometrics, facial recognition, machine learning, deep learning, AI, paper mask attack, iBeta certification, PAD attack, security, ibeta, face recognition, pad, authentication, fraud
- 任务类别: video-classification
数据集描述
- 攻击类型:
- Silicone Mask Attacks
- Latex Mask Attacks
- Wrapped 3D Paper Mask Attacks
- Advanced Paper Mask Attacks
- Cloth 3D Face Mask Attacks
- 数据规模: 25,000+ 视频(约10秒),多帧
- 采集设备: 每个攻击类型均在iOS和Android手机上捕获
- 特征: 包含放大和缩小阶段以支持Active Liveness
技术规格
- 文件格式: 兼容主流机器学习框架的视频格式
- 分辨率和帧率: 高分辨率,优化帧率以捕捉快速的面具放置
潜在用途
- 活体检测: 训练和评估活体检测模型,区分自拍和欺骗攻击
- iBeta活体测试: 用于iBeta认证前的模型训练和评估
商业用途
- 完整版本: 可通过Axonlabs网站申请购买
关键词
ibeta level 1, ibeta level 2, liveness detection systems, liveness detection dataset, biometric dataset, biometric data dataset, face detection, face identification, face recognition, face id, attacks detection dataset, biometric system attacks, anti-spoofing dataset, face liveness detection, deep learning dataset, face spoofing database, face anti-spoofing, presentation attack detection, presentation attack dataset, 2D print attacks, 3D print attacks, silicone masks attacks, video dataset, video classification, computer vision, deep learning, machine learning, phone attack dataset, face anti spoofing, replay spoof attack, cut prints spoof attack, large-scale face anti spoofing, rich annotations anti spoofing dataset, display spoof attack




