多模态数据融合的活体检测算法  

A LIVENESS DETECTION ALGORITHM BASED ON MULTI-MODAL DATA FUSION

作　　者：吴凤娇 孙收余 罗子江[1] 马原东 崔潇 刘宽 候红涛 徐斌 赵凯 Wu Fengjiao;Sun Shouyu;Luo Zijiang;Ma Yuandong;Cui Xiao;Liu Kuan;Hou Hongtao;Xu Bin;Zhao Kai(School of Information,Guizhou University of Finance and Economics,Guiyang 550025,Guizhou,China;Beijing Interjoy Technology,Beijing 101300,China;PipeChina South China Branch,Guangzhou 510000,Guangdong,China)

机构地区：[1]贵州财经大学信息学院,贵州贵阳550025 [2]北京盛开智联科技有限公司,北京101300 [3]国家石油天然气管网集团有限公司华南分公司,广东广州510000

出　　处：《计算机应用与软件》2024年第11期288-296,349,共10页Computer Applications and Software

基　　金：国家自然科学基金项目(11664005);贵州省科技计划项目(黔科合基础[2020]1Y021);贵州省研究生科研基金项目(黔科合YJSCXJH[2020]120)。

摘　　要：基于神经网络的活体检测算法有效防止各类欺诈攻击,但当前的活体检测算法无法兼顾检测速度、检测精度和成本。对此,在MobileNetv2的基础上提出一种多模态数据融合的活体检测算法,该算法引进跨阶段部分网络(Cross Stage Partial Network,CSPNet)和提出DDConvBlock,实现检测速度、检测精度和成本之间相平衡的设计目标。为验证该算法的有效性,先在公共数据集Msspoof和CASIA-SURF上进行实验验证。接着根据实际需求,构建私有数据集,并在该数据集上用该检测算法进行建模和实验验证。验证结果表明该方法在不同遮挡和不同攻击方式下能有效地进行活体检测,该检测模型具有可移植性强的特点,能够推广到对安全性和便利性要求较高的平台中。The live detection algorithm based on neural network can prevent all kinds of spoofing attacks,but can not take into account the detection speed,detection accuracy and cost.Aiming this problem,we propose a multi-modal data fusion live detection algorithm based on MobileNetv2.It introduced cross stage partial network(CSPNet)and DDConvBlock to achieve the design goal of balancing detection speed,detection accuracy and cost.In order to verify its effectiveness,experiments were carried out on public dataset Msspoof and CASIA-SURF.According to actual needs,a private dataset was constructed,and the same detection algorithm was used for modeling and experimental verification on this dataset.The verification results show that it can perform liveness detection under different occlusions and different spoofing attacks.At the same time,the detection model has the characteristics of portability,and can be extended to platforms with high requirements for security and convenience.

关 键 词：活体检测 反欺诈攻击 图像处理 数据融合 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]