基于多分类及特征融合的静默活体检测算法

黄新宇,游帆,张沛,张昭,张柏礼,吕建华,徐立臻

Silent liveness detection algorithm based on multi classification and feature fusion network

Xin-yu HUANG,Fan YOU,Pei ZHANG,Zhao ZHANG,Bai-li ZHANG,Jian-hua LV,Li-zhen XU

表 6 二分类和多分类方法在CASIA-FASD和Replay-Attack数据集上的交叉测试

Tab.6 Cross-testing between CASIA-FASD and Replay-Attack dataset by binary classification and multiple classification

网络结构 方法 EER/% 训练: CASIA 测试: Replay 训练: Replay 测试: CASIA ResNet-18 二分类 40.8750 48.3333 ResNet-18 多分类 36.7500 47.5926 BaseNet 二分类 47.8750 56.6670 BaseNet 多分类 33.2500 45.3704