Page 477 - 《软件学报》2025年第9期

软件学报 ISSN 1000-9825, CODEN RUXUEW E-mail: jos@iscas.ac.cn
2025,36(9):4388−4402 [doi: 10.13328/j.cnki.jos.007285] [CSTR: 32375.14.jos.007285] http://www.jos.org.cn
©中国科学院软件研究所版权所有. Tel: +86-10-62562563

*
视觉注意力和域特征融合的人脸活体检测方法

朱建秋, 华 阳, 宋晓宁

(江南大学 人工智能与计算机学院, 江苏 无锡 214122)
通信作者: 宋晓宁, E-mail: x.song@jiangnan.edu.cn

摘 要: 人脸活体检测是人脸识别技术安全落地的有力保障. 但活体攻击方式的不断变换, 给现有检测方法带来了
极大的挑战. 为应对层出不穷的未知场景和攻击方式, 提出一种基于视觉注意力和域特征融合的双流人脸活体检
测模型. 首先, 提出基于视觉注意力的特征提取模块, 增强模型提取基于全局信息的内容特征的能力. 接着, 构建一
种新型的风格特征融合模块, 将内容特征和浅层纹理表达的风格特征相融合来优化样本的特征表示. 此外, 设计基
于孪生网络的特征映射策略并修正对比损失函数, 分别强化模型的鲁棒性和规避训练过程中梯度易振荡的问题.
还采用对抗训练来降低模型对样本数据域之间分歧的敏感性, 进一步增强其泛化性. 多项实验结果表明, 所提方法
在主流数据集上跨域表现均优于现有模型, 验证其泛化性和强鲁棒性.
关键词: 人脸活体检测; 域泛化; 特征融合
中图法分类号: TP391

中文引用格式: 朱建秋, 华阳, 宋晓宁. 视觉注意力和域特征融合的人脸活体检测方法. 软件学报, 2025, 36(9): 4388–4402. http://
www.jos.org.cn/1000-9825/7285.htm
英文引用格式: Zhu JQ, Hua Y, Song XN. Face Anti-spoofing Method Based on Visual Attention and Domain Feature Fusion. Ruan
Jian Xue Bao/Journal of Software, 2025, 36(9): 4388–4402 (in Chinese). http://www.jos.org.cn/1000-9825/7285.htm

Face Anti-spoofing Method Based on Visual Attention and Domain Feature Fusion

ZHU Jian-Qiu, HUA Yang, SONG Xiao-Ning
(School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi 214122, China)

Abstract: Face anti-spoofing is a powerful guarantee for the practical security of facial recognition technology. However, the constant
evolution of live attack methods poses significant challenges to existing detection methods. To address the increasing number of unknown
scenarios and attack methods, a two-stream face anti-spoofing model based on visual attention and domain feature fusion is proposed.
First, a visual attention-based feature extraction module is proposed to strengthen the model’s capacity to extract content features based on
global information. Second, a novel style feature fusion module is designed to optimize the feature representation of the sample by fusing
content features with low-level textural style features. Third, a feature mapping strategy based on the Siamese network is developed and
the contrast loss function is modified to improve the model robustness and avoid easy gradient oscillation during training, respectively.
Furthermore, domain adversarial training (DAT) is used to reduce the sensitivity of the model to differences between sample data domains
and further improve its generalization. Extensive experimental results verify the generality and strong robustness of the proposed method,
demonstrating that it outperforms existing models in cross-domain performance on mainstream datasets.
Key words: face anti-spoofing; domain generalization; feature fusion

人脸识别技术凭借其独特优势被广泛应用于各个领域. 而人脸活体检测作为其核心技术, 专用于精准辨别真
实人脸与伪造人脸, 以此防御欺诈攻击, 保障人脸识别系统安全运行. 常见的攻击方式分为图片打印攻击、视频回

* 基金项目: 国家重点研发计划 (2023YFF1105102, 2023YFF1105105); 国家社科基金重大项目 (21&ZD166); 江苏省自然科学基金
(BK20221535); 江苏省研究生研究与实践创新计划 (KYCX23_2438)
收稿时间: 2023-06-20; 修改时间: 2023-12-25, 2024-07-30; 采用时间: 2024-08-29; jos 在线出版时间: 2025-01-08
CNKI 网络首发时间: 2025-01-16