基于纹理特征增强和轻量级网络的人脸防伪算法

doi:10.11896/jsjkx.210600217

计算机科学 ›› 2022, Vol. 49 ›› Issue (6A): 390-396.doi: 10.11896/jsjkx.210600217

• 图像处理&多媒体技术 • 上一篇下一篇

基于纹理特征增强和轻量级网络的人脸防伪算法

沈超^1,2, 何希平^1,2,3

1 重庆工商大学管理科学与工程学院重庆 400067
2 重庆工商大学智能制造服务国际科技合作基地重庆 400067
3 重庆工商大学人工智能学院检测控制集成系统重庆市工程实验室重庆 400067

出版日期:2022-06-10 发布日期:2022-06-08
通讯作者: 何希平(jsjhxp@ctbu.edu.cn)
作者简介:(617192571@qq.com)
基金资助:
重庆市教育委员会科学技术研究项目(KJQN201900833);重庆市研究生科研创新项目(CYS21398)

Face Anti-spoofing Algorithm Based on Texture Feature Enhancement and Light Neural Network

SHEN Chao^1,2, HE Xi-ping^1,2,3

1 School of Management Science and Engineering,Chongqing Technology and Business University,Chongqing 400067,China
2 National Research Base of Intelligent Manufacturing Service,Chongqing Technology and Business University,Chongqing 400067,China
3 School of Artificial Intelligence,Chongqing Technology and Business University,Chongqing Engineering Laboratory for Detection,Control and Integrated System,Chongqing 400067,China

Online:2022-06-10 Published:2022-06-08
About author:SHEN Chao,born in 1996,postgra-duate.His main research interests include face anti-spoofing and deep lear-ning.
HE Xi-ping,born in 1968,Ph.D,professor.His main research interests include machine learning,data analysis and processing,computer vision,and information system security.
Supported by:
Science and Technology Research Foundation of Chongqing Education Commission(KJQN201900833) and Scientific Research and Innovation Foundation of Chongqing,China(CYS21398).

摘要/Abstract

摘要： 人脸防伪检测是人脸识别中较为重要的一环,对现实中的相关行业,如身份验证、安全密钥、金融支付等有着重大的意义。目前主流的基于深度学习的人脸防伪算法已经取得较为先进的效果,但仍存在部分问题,如模型参数过多,增加了实际部署的难度,而轻量级的网络结构的泛化性能并不好等。针对相关人脸防伪算法泛化能力差、参数量过大等问题,提出了一种人脸纹理信息增强方法和基于改进FeatherNet网络的人脸防伪检测算法,通过对真伪人脸信息纹理差异特征的筛选并增强作为骨干网络的输入,在骨干网络的设计上引入了DropBlock模块以及加入了多通道注意力特征图分支,在保持速度的前提下实现了泛化性能的增强。所提算法在库内测试和跨库测试上均显示出了良好的性能提升。

关键词: 多通道注意力, 轻量级网络, 人脸防伪, 纹理特征增强

Abstract: Face anti-spoofing is an important part of face recognition,which is of great significance to the safety of related industries in reality,such as authentication,security key,financial payment and so on.The mainstream face anti-counterfeiting algorithm based on deep learning has achieved quite advanced results,but there are still some problems,such as too many model parameters increases the difficulty of actual deployment,and the generalization performance of light neural network structure is not good,etc.Aiming at the problems of poor generalization ability and too large parameters of the related face anti-spoofing algorithm.This paper proposes a texture feature enhancement method and a face anti-spoofing detection algorithm based on improved FeatherNet network.By enhancing the texture difference features of real and fake face information as the input of the backbone network.In the design of the backbone network,DropBlock module and multi-channel attention feature map branch are introduced.The generalization performance is enhanced while maintaining the speed.The designed algorithm shows good performance improvement in both data-set test and cross data-set test.

Key words: Face anti-spoofing, Light neural network, Multi-channel attention map, Texture enhancement

中图分类号:

TP399

沈超, 何希平. 基于纹理特征增强和轻量级网络的人脸防伪算法[J]. 计算机科学, 2022, 49(6A): 390-396. https://doi.org/10.11896/jsjkx.210600217

SHEN Chao, HE Xi-ping. Face Anti-spoofing Algorithm Based on Texture Feature Enhancement and Light Neural Network[J]. Computer Science, 2022, 49(6A): 390-396. https://doi.org/10.11896/jsjkx.210600217

参考文献

[1] WANG Z,ZHAO C,QIN Y,et al.Exploiting temporaland depth information for multi-frame face anti-spoofing[J].arXiv:abs/1811.05118,2018.
[2] ZHANG P,ZOU F H,WU Z W,et al.FeatherNets:Convolutional Neural Networks as Light as Feather[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops(CVPRW).Long Beach,CA,USA,2019:1574-1583.
[3] ZHANG X,ZHOU X,LIN M,et al.ShuffleNet:An Extremely Efficient Convolutional Neural Network for Mobile Devices[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.Salt Lake City,UT,USA,2018:6848-6856.
[4] HOWARD A G,ZHU M,CHEN B,et al.MobileNets:Efficient Convolutional Neural Networks for Mobile Vision Applications[J].arXiv:abs/1704.04861,2017.
[5] PARKIN A,GRINCHUK O.Recognizing Multi-Modal FaceSpoofing With Face Recognition Networks[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops(CVPRW).Long Beach,CA,USA,2019:1617-1623.
[6] SHEN T,HUANG Y,TONG Z.FaceBagNet:Bag-Of-Local-Features Model for Multi-Modal Face Anti-Spoofing[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops(CVPRW).Long Beach,CA,USA,2019:1611-1616.
[7] PARKIN A,GRINCHUK O.Creating Artificial Modalities to Solve RGB Liveness[J].arXiv:abs/2006.16028,2020.
[8] SAJJADI M S M,SCHÖLKOPF B,HIRSCH M.EnhanceNet:Single Image Super-Resolution Through Automated Texture Synthesis[C]//2017 IEEE International Conference on Compu-ter Vision(ICCV).Venice,Italy,2017:4501-4510.
[9] IANDOLA F,MOSKEWICZ M,KARAYEV S,et al.DenseNet:Implementing Efficient ConvNet Descriptor Pyramids[J].arXiv:abs/1404.1869.2014.
[10] GHIASI G,LIN T Y,LE Q V.DropBlock:A regularizationmethod for convolutional networks[J].arXiv:abs/1810.12890,2018.
[11] SANDLER M,HOWARD A,ZHU M,et al.MobileNetV2:Inverted Residuals and Linear Bottlenecks[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.Salt Lake City,UT,USA,2018:4510-4520.
[12] HU J,SHEN L,ALBANIE S,et al.Squeeze-and-Excitation Networks[C]//IEEE Transactions on Pattern Analysis and Machine Intelligence.2020:2011-2023.
[13] BHARADWAJ S,DHAMECHA T I,VATSA M,et al.Computationally efficient face spoofing detection with motion magnification[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops.2013:105-110.
[14] DE FREITAS PEREIRA T,ANJOS A,DE MARTINO J M,et al.Can face anti-spoofing counter measures work in a real world scenario? [C]//2013 International Conference on Biome-trics(ICB).2013:1-8.
[15] JOURABLOO A,LIU Y J,LIU X M.Face despoofing:Anti-spoofing via noise modeling[C]//Proceedings of the European Conference on Computer Vision(ECCV).2018:290-306.
[16] BOULKENAFET Z,KOMULAINEN J,HADID A.Face anti-spoofing based on color texture analysis[C]//IEEE IntelnationalConference on Image Processing(ICIP).2015:2636-2640.
[17] PINTO A,PEDRINI H,SCHWARTZ W R,et al.Face spoofing detection through visual codebooks of spectral temporal cubes[J].IEEE Transactions on Image Processing,2015,24(12):4726-4740.
[18] BOULKENAFET Z,KOMULAINEN J,HADID A.Facespoo-fing detection using colour texture analysis[J].IEEE Transactions on Information Forensics and Security,2016,11(8):1818-1830.
[19] LIU Y J,JOURABLOO A,LIU X M.Learning deep models for face anti-spoofing:Binary or auxiliary supervision[C]//Procee-dings of the IEEE Conference on Computer Vision and Pattern Recognition.2018:389-398.
[20] YANG X,LUO W H,BAO L C,et al.Face anti-spoofing:Model matters,so does data[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2019.
[21] WANG Z Z,ZHAO C X,QIN Y X,et al.Exploiting temporal and depth information for multi-frame face anti-spoofing[J].arXiv:abs/1811.05118,2018.
[22] SHARMA V,DIBA A,NEVEN D,et al.Classification DrivenDynamic Image Enhancement[J].arXiv:1710.07558,2018.
[23] HUANG J,ZHU P F,GENG M R,et al.Range Scaling Global U-Net for Perceptual Image Enhancement on Mobile Devices[C]//Computer Vision-ECCV 2018 Workshops.2018:230-242.
[24] KIM T,KIM Y,KIM I,et al.Basn:Enriching feature representation usingbipartite auxiliary supervisions for face anti-spoofing[C]//ICCV Workshops.2019.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

基于纹理特征增强和轻量级网络的人脸防伪算法

Face Anti-spoofing Algorithm Based on Texture Feature Enhancement and Light Neural Network

PDF (PC)

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 3

Metrics

本文评价

推荐阅读 0

[1]	卓雅倩, 欧博. 噪声环境下的人脸防伪识别算法研究 Face Anti-spoofing Algorithm for Noisy Environment 计算机科学, 2021, 48(6A): 443-447. https://doi.org/10.11896/jsjkx.200900207
[2]	吴晓丽, 胡伟. 基于注意力的热点块和显著像素卷积神经网络的人脸防伪方法 Attention-based Hot Block and Saliency Pixel Convolutional Neural Network Method for Face Anti-spoofing 计算机科学, 2021, 48(4): 316-324. https://doi.org/10.11896/jsjkx.200300128
[3]	刘彦, 秦品乐, 曾建朝. 基于YOLOv3与分层数据关联的多目标跟踪算法 Multi-object Tracking Algorithm Based on YOLOv3 and Hierarchical Data Association 计算机科学, 2021, 48(11A): 370-375. https://doi.org/10.11896/jsjkx.201000115