首页 > 论文 > 激光与光电子学进展 > 56卷 > 3期(pp:31002--1)

基于多特征融合的3D打印面具攻击检测

3D Printing Mask Attacks Detection Based on Multi-Feature Fusion

  • 摘要
  • 论文信息
  • 参考文献
  • 被引情况
  • PDF全文
分享:

摘要

针对人脸认证系统的欺骗攻击,传统欺骗攻击方式主要包括照片和视频攻击。随着三维(3D)打印技术的快速发展, 使用3D面具进行欺骗攻击逐渐成为新威胁。在剪切波变换基础上, 结合人脸3D几何特征和局部区域纹理变化, 针对3D面具欺骗攻击提出一种利用多层自编码网络进行特征融合分类来识别攻击面具的方法。通过非下采样剪切波变换从目标人脸3D图像中提取低频子带和高频子带。在低频子带上利用尺度空间函数对特征点进行检测、定位及方向分配, 生成特征描述子。将所生成的特征描述子与高频子带上提取的纹理特征输入栈式自编码器和softmax分类器进行瓶颈特征融合分类。在基于柔性TPU材质3D打印面具BFFD数据库上的实验结果表明, 相比于以往单独使用纹理特征的方法, 加入3D几何特征的多特征融合方法对反3D面具攻击的准确率有显著提升。

Abstract

Aiming at the spoofing attacks for the current face authentication systems, the traditional spoofing attacks include displaying printed photos and replaying recorded videos. With the rapid development of three-dimensional (3D) printing technology, the 3D mask spoofing attack is becoming a new threat. On the basis of the shearlet transform and combining with the 3D geometric attributes and the local regional texture changes, a method by utilizing the multilayer autoencoder network to conduct the feature fusion-based classification to identify the attack mask is proposed for the 3D mask spoofing attack. The low-frequency sub-band and several high-frequency sub-bands are extracted from the 3D image of the target face by the non sub-sampled shearlet transform method. The scale space function is used to detect, locate and distribute the feature points and then to generate feature operators in the low-frequency sub-band . Then, the generated feature operators and the texture features extracted from the high-frequency sub-band are combined in series and fed into the stacked autoencoder network and the softmax classifier to conduct the bottleneck feature fusion-based classification. The experimental results in the BFFD database based on the flexible TPU material 3D print mask shows that, the multi-feature fusion method added the 3D geometric feature has an obvious improvement for the accuracy of the anti-spoofing performance against 3D mask attacks to compare with the previous method of using the texture feature alone.

Newport宣传-MKS新实验室计划
补充资料

中图分类号:TP391

DOI:10.3788/lop56.031002

所属栏目:图像处理

基金项目:北京市自然科学基金重大项目(Z140002)

收稿日期:2018-07-04

修改稿日期:2018-08-04

网络出版日期:2018-08-13

作者单位    点击查看

陆经纬:北京工业大学北京未来网络科技高精尖创新中心, 北京 100124
陈鹤天:北京工业大学北京市数字化医疗3D打印工程技术研究中心, 北京 100124
马肖攀:北京工业大学北京未来网络科技高精尖创新中心, 北京 100124
陈继民:北京工业大学北京市数字化医疗3D打印工程技术研究中心, 北京 100124

联系人作者:陆经纬(18810815230@126.com)

【1】Zhang M G, Zhou D L, Pan Q, et al. Biometrics and its situation of present study[J]. Acta Biophysica Sinica, 2002, 18(2): 156-162.
张敏贵, 周德龙, 潘泉, 等. 生物特征识别及研究现状[J]. 生物物理学报, 2002, 18(2): 156-162.

【2】Nixon K A, Aimale V, Rowe R K. Spoof detection schemes[M]∥Boston: Springer US, 2008: 403-423.

【3】Chetty G, Wagner M. Multi-level liveness verification for face-voice biometric authentication[C]∥Biometrics Symposium: Special Session on Research at the Biometric Consortium Conference, 2006: 1-6.

【4】Pan G, Sun L, Wu Z H, et al. Eyeblink-based anti-spoofing in face recognition from a generic webcamera[C]∥IEEE 11th International Conference on Computer Vision, 2007: 1-8.

【5】Kollreider K, Fronthaler H, Bigun J. Evaluating liveness by face images and the structure tensor[C]//Fourth IEEE Workshop on Automatic Identification Advanced Technologies (AutoID′05), 2005: 75-80.

【6】de Marsico M, Nappi M, Riccio D, et al. Moving face spoofing detection via 3D projective invariants[C]∥2012 5th IAPR International Conference on Biometrics (ICB), 2012: 73-78.

【7】Kong Y P, Liu X, Xie X Q, et al. Face liveness detection method based on histogram of oriented gradient[J]. Laser & Optoelectronics Progress, 2018, 55(3): 031009.
孔月萍, 刘霞, 谢心谦, 等. 基于梯度方向直方图的人脸活体检测方法[J]. 激光与光电子学进展, 2018, 55(3): 031009.

【8】Mtt J, Hadid A, Pietikinen M. Face spoofing detection from single images using micro-texture analysis[C]∥International Joint Conference on Biometrics (IJCB), 2011: 1-7.

【9】Gu X J, Fu C Q, Gu X S. Facial vital sign based countermeasure against 3D mask attacks[J]. Journal of System Simulation, 2016, 28(2): 361-368.
谷小婧, 付传卿, 顾幸生. 基于面部生命特征的3D假面欺骗攻击检测方法[J]. 系统仿真学报, 2016, 28(2): 361-368.

【10】Wallace R, McLaren M, McCool C, et al. Inter-session variability modelling and joint factor analysis for face authentication[C]∥International Joint Conference on Biometrics (IJCB), 2011: 1-8.

【11】Erdogmus N, Marcel S. Spoofing in 2D face recognition with 3D masks and anti-spoofing with Kinect[C]∥IEEE Sixth International Conference on Biometrics: Theory, Applications and Systems (BTAS), 2013: 1-6.

【12】Li S Z, Chu R F, Liao S C, et al. Illumination invariant face recognition using near-infrared images[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2007, 29(4): 627-639.

【13】Zhang Z W, Yi D, Lei Z, et al. Face liveness detection by learning multispectral reflectance distributions[C]∥Face and Gesture, 2011: 436-441.

【14】Kose N, Dugelay J L. Countermeasure for the protection of face recognition systems against mask attacks[C]∥10th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition (FG), 2013: 1-6.

【15】Menotti D, Chiachia G, Pinto A, et al. Deep representations for iris, face, and fingerprint spoofing detection[J]. IEEE Transactions on Information Forensics and Security, 2015, 10(4): 864-879.

【16】Agarwal A, Singh R, Vatsa M. Face anti-spoofing using Haralick features[C]∥IEEE 8th International Conference on Biometrics Theory, Applications and Systems (BTAS), 2016: 1-6.

【17】Guo K H, Labate D. Optimally sparse multidimensional representation using shearlets[J]. SIAM Journal on Mathematical Analysis, 2007, 39(1): 298-318.

【18】Sun X, Morvan J M. Curvature measures, normal cycles and asymptotic cones[J]. Actes des Rencontres Du CIRM, 2013, 3(1): 3-10.

【19】Sun X, Morvan J M. Asymptotic cones of embedded singular spaces[J]. Geometry, Imaging and Computing, 2015, 2(1): 47-76.

【20】Cohen-Steiner D, Morvan J M. Restricted delaunay triangulations and normal cycle[C]∥Proceedings of the nineteenth Conference on Computational Geometry - SCG ''03, the Nineteenth Conference, 2003.

【21】Lowe D G. Distinctiveimage features from scale-invariant keypoints[J]. International Journal of Computer Vision, 2004, 60(2): 91-110.

【22】Hou Y M, Sui W X, Sun X X. SIFT feature dimension reduction method and its application in image retrieval[J]. Chinese Journal of Lasers, 2015, 42(s1): s108002.
侯一民, 隋文秀, 孙晓雪. SIFT特征降维方法及其在图像检索中的应用[J]. 中国激光, 2015, 42(s1): s108002.

【23】Smeets D, Keustermans J, Vandermeulen D, et al. meshSIFT: local surface features for 3D face recognition under expression variations and partial data[J]. Computer Vision and Image Understanding, 2013, 117(2): 158-169.

【24】Xiong F G, Huo W, Han X, et al. Removal method of mismatching keypoints in 3D point cloud[J]. Acta Optica Sinica, 2018, 38(2): 0210003.
熊风光, 霍旺, 韩燮, 等. 三维点云中关键点误匹配剔除方法[J]. 光学学报, 2018, 38(2): 0210003.

【25】Tola E, Lepetit V, Fua P. DAISY: an efficient dense descriptor applied to wide-baseline stereo[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2010, 32(5): 815-830.

引用该论文

Lu Jingwei,Chen Hetian,Ma Xiaopan,Chen Jimin. 3D Printing Mask Attacks Detection Based on Multi-Feature Fusion[J]. Laser & Optoelectronics Progress, 2019, 56(3): 031002

陆经纬,陈鹤天,马肖攀,陈继民. 基于多特征融合的3D打印面具攻击检测[J]. 激光与光电子学进展, 2019, 56(3): 031002

您的浏览器不支持PDF插件,请使用最新的(Chrome/Fire Fox等)浏览器.或者您还可以点击此处下载该论文PDF