《计算机应用》唯一官方网站 ›› 2022, Vol. 42 ›› Issue (7): 2037-2042.DOI: 10.11772/j.issn.1001-9081.2021050814
所属专题: 人工智能
收稿日期:
2021-05-18
修回日期:
2022-02-23
接受日期:
2022-02-25
发布日期:
2022-07-15
出版日期:
2022-07-10
通讯作者:
杨瑞杰
作者简介:
郑贵林(1963—),男,湖北武汉人,教授,博士,主要研究方向:智能家居、物联网、计算机视觉。
Received:
2021-05-18
Revised:
2022-02-23
Accepted:
2022-02-25
Online:
2022-07-15
Published:
2022-07-10
Contact:
Ruijie YANG
About author:
ZHENG Guilin, born in 1963, Ph. D., professor. His research interests include smart home, internet of things, computer vision.
摘要:
针对身份验证中经常出现的照片欺诈问题,提出了一种基于InceptionV3和特征融合的人脸活体检测模型——InceptionV3_FF。首先,在ImageNet数据集上预训练InceptionV3模型;其次,从InceptionV3模型的不同层得到图像的浅层、中层和深层特征;然后,将不同的特征进行融合得到最终的特征;最后,使用全连接层对特征进行分类,从而实现端到端的训练。InceptionV3_FF模型在NUAA数据集和自制的STAR数据集上进行仿真实验,实验结果表明,InceptionV3_FF模型在NUAA数据集和STAR数据集上分别取得了99.96%和98.85%的准确率,高于InceptionV3迁移学习和迁移微调模型;而与非线性扩散卷积神经网络(ND-CNN)、扩散核(DK)、异构内核卷积神经网络(HK-CNN)等模型相比,InceptionV3_FF模型在NUAA数据集上的准确率更高,具备一定的优越性。InceptionV3_FF模型对数据集中随机抽取的单张图片进行识别时,仅需4 ms。InceptionV3_FF模型和OpenCV结合构成的活体检测系统可以对真假人脸进行识别。
中图分类号:
杨瑞杰, 郑贵林. 基于InceptionV3和特征融合的人脸活体检测[J]. 计算机应用, 2022, 42(7): 2037-2042.
Ruijie YANG, Guilin ZHENG. Face liveness detection based on InceptionV3 and feature fusion[J]. Journal of Computer Applications, 2022, 42(7): 2037-2042.
数据集 | 训练集样本数 | 验证集样本数 | 测试集样本数 |
---|---|---|---|
NUAA | 7 563 | 2 521 | 2 521 |
STAR | 2 402 | 800 | 800 |
表1 数据集的划分
Tab.1 Dataset partitioning
数据集 | 训练集样本数 | 验证集样本数 | 测试集样本数 |
---|---|---|---|
NUAA | 7 563 | 2 521 | 2 521 |
STAR | 2 402 | 800 | 800 |
参数 | 值 |
---|---|
Zoom_range | 0.25 |
Rotation_range | 15 |
Channel_shift_range | 25 |
rescale | 1/255 |
Width_shift_range | 0.02 |
Height_shift_range | 0.02 |
Horizontal_flip | True |
表2 数据增强参数
Tab.2 Data augmentation parameters
参数 | 值 |
---|---|
Zoom_range | 0.25 |
Rotation_range | 15 |
Channel_shift_range | 25 |
rescale | 1/255 |
Width_shift_range | 0.02 |
Height_shift_range | 0.02 |
Horizontal_flip | True |
模型 | 数据集 | 准确率 | AUC |
---|---|---|---|
InceptionV3_FF | STAR | 0.988 5 | 0.998 0 |
NUAA | 0.999 6 | 0.999 8 | |
InceptionV3_T | STAR | 0.905 0 | 0.956 2 |
NUAA | 0.995 2 | 0.999 6 | |
InceptionV3_TL | STAR | 0.970 5 | 0.987 7 |
NUAA | 0.997 5 | 0.999 3 |
表3 3种模型的测试结果对比
Tab.3 Comparison of test results of three models
模型 | 数据集 | 准确率 | AUC |
---|---|---|---|
InceptionV3_FF | STAR | 0.988 5 | 0.998 0 |
NUAA | 0.999 6 | 0.999 8 | |
InceptionV3_T | STAR | 0.905 0 | 0.956 2 |
NUAA | 0.995 2 | 0.999 6 | |
InceptionV3_TL | STAR | 0.970 5 | 0.987 7 |
NUAA | 0.997 5 | 0.999 3 |
模型 | 准确率 |
---|---|
ND-CNN[ | 99.00 |
DK[ | 99.30 |
ELM-LRF[ | 99.67 |
Resnet50+depth+se[ | 95.91 |
HK-CNN[ | 99.82 |
GLCM+DT-CWT+GS+LBP[ | 99.76 |
LBP+模糊特征+色彩纹理特征[ | 99.27 |
本文模型 | 99.96 |
表4 不同模型的准确率结果对比 (%)
Tab.4 Accuracy results comparison of different models
模型 | 准确率 |
---|---|
ND-CNN[ | 99.00 |
DK[ | 99.30 |
ELM-LRF[ | 99.67 |
Resnet50+depth+se[ | 95.91 |
HK-CNN[ | 99.82 |
GLCM+DT-CWT+GS+LBP[ | 99.76 |
LBP+模糊特征+色彩纹理特征[ | 99.27 |
本文模型 | 99.96 |
1 | BOULKENAFET Z, KOMULAINE J, HADID A. Face anti-spoofing based on color texture analysis[C]// Proceedings of the 2015 IEEE International Conference on Image Processing. Piscataway: IEEE, 2015: 2636-2640. 10.1109/icip.2015.7351280 |
2 | BOULKENAFET Z, KOMULAINEN J, HADID A. Face spoofing detection using colour texture analysis[J]. IEEE Transactions on Information Forensics and Security, 2016, 11(8):1818-1830. 10.1109/tifs.2016.2555286 |
3 | LI X B, KOMULAINEN J, ZHAO G Y, et al. Generalized face anti-spoofing by detecting pulse from face videos[C]// Proceedings of the 23rd International Conference on Pattern Recognition. Piscataway: IEEE, 2016: 4244-4249. 10.1109/icpr.2016.7900300 |
4 | CHINGOVSKA I, ERDOGMUS N, ANJOS A, et al. Face recognition systems under spoofing attacks [M]// BOURLAI T. Face Recognition Across the Imaging Spectrum. Cham: Springer, 2016:165-194. 10.1007/978-3-319-28501-6_8 |
5 | LIU S Q, LAN X Y, YUEN P C. Remote photoplethysmography correspondence feature for 3D mask face presentation attack detection[C]// Proceedings of the 2018 European Conference on Computer Vision, LNCS 11220. Cham: Springer, 2018:577-594. |
6 | COSTA-PAZO A, BHATTACHARJEE S, VAZQUEZ-FERNANDEZ E, et al. The replay-mobile face presentation-attack database[C]// Proceedings of the 2016 International Conference of the Biometrics Special Interest Group. Piscataway: IEEE, 2016:1-7. 10.1109/biosig.2016.7736936 |
7 | KIM Y, NA J, YOON S, et al. Masked fake face detection using radiance measurements[J]. Journal of the Optical Society of America A, 2009, 26(4):760-766. 10.1364/josaa.26.000760 |
8 | ATOUM Y, LIU Y J, JOURABLOO A, et al. Face anti-spoofing using patch and depth-based CNNs[C]// Proceedings of the 2017 IEEE International Joint Conference on Biometrics. Piscataway: IEEE, 2017: 319-328. 10.1109/btas.2017.8272713 |
9 | LIU Y J, JOURABLOO A, LIU X M. Learning deep models for face anti-spoofing: binary or auxiliary supervision[C]// Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2018: 389-398. 10.1109/cvpr.2018.00048 |
10 | DE FREITAS PEREIRA T, ANJOS A, DE MARTINO J M, et al. LBP-TOP based countermeasure against face spoofing attacks[C]// Proceedings of the 2012 Asian Conference on Computer Vision, LNCS 7728. Berlin: Springer, 2013:121-132. |
11 | TANG Y, WANG X, JIA X, et al. Fusing multiple deep features for face anti-spoofing[C]// Proceedings of the 2018 Chinese Conference on Biometric Recognition, LNCS 10996. Cham: Springer, 2018: 321-330. |
12 | LUCENA O, JUNIOR A, MOIA V, et al. Transfer learning using convolutional neural networks for face anti-spoofing[C]// Proceedings of the 2017 International Conference on Image Analysis and Recognition, LNCS 10317. Cham: Springer, 2017: 27-34. |
13 | 邓雄,王洪春. 基于深度学习和特征融合的人脸活体检测算法[J]. 计算机应用, 2020, 40(4):1009-1015. 10.11772/j.issn.1001-9081.2019091595 |
DENG X, WANG H C. Face liveness detection algorithm based on deep learning and feature fusion[J]. Journal of Computer Applications, 2020, 40(4):1009-1015. 10.11772/j.issn.1001-9081.2019091595 | |
14 | 栾晓,李晓双. 基于多特征融合的人脸活体检测算法[J]. 计算机科学, 2021, 48(11A):409-415. 10.11896/jsjkx.210100181 |
LUAN X, LI X S. Face anti-spoofing algorithm based on multi-feature fusion[J]. Computer Science, 2021, 48(11A):409-415. 10.11896/jsjkx.210100181 | |
15 | TRONCI R, MUNTONI D, FADDA G, et al. Fusion of multiple clues for photo-attack detection in face recognition systems[C]// Proceedings of the 2011 International Joint Conference on Biometrics. Piscataway: IEEE, 2011:1-6. 10.1109/ijcb.2011.6117522 |
16 | YAN J J, ZHANG Z W, LEI Z, et al. Face liveness detection by exploring multiple scenic clues[C]// Proceedings of the 12th International Conference on Control Automation Robotics and Vision. Piscataway: IEEE, 2012: 188-193. 10.1109/icarcv.2012.6485156 |
17 | WANG Y, NIAN F D, LI T, et al. Robust face anti-spoofing with depth information[J]. Journal of Visual Communication and Image Representation, 2017, 49: 332-337. 10.1016/j.jvcir.2017.09.002 |
18 | CAI P, QUAN H M. Face anti-spoofing algorithm combined with CNN and brightness equalization[J]. Journal of Central South University, 2021, 28(1):194-204. 10.1007/s11771-021-4596-y |
19 | 封筠,董祉怡,刘甜甜,等. 融合DQ_CoALBP和LPQ算子的人脸活体检测[J/OL]. 计算机工程与应用. (2021-04-19) [2021-05-10].. 10.3778/j.issn.1002-8331.2012-0123 |
FENG J, DONG Z Y, LIU T T, et al. Face anti-spoofing liveness detection based on combining DQ_CoALBP with LPQ descriptors[J/OL]. Computer Engineering and Applications. (2021-04-19) [2021-05-10].. 10.3778/j.issn.1002-8331.2012-0123 | |
20 | LI C Y, LI R, SUN J H. CNN face live detection algorithm based on binocular camera[J]. Journal of Physics: Conference Series, 2021, 1881(2): No.022015. 10.1088/1742-6596/1881/2/022015 |
21 | SZEGEDY C, LIU W, JIA Y Q, et al. Going deeper with convolutions[C]// Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2015: 1-9. 10.1109/cvpr.2015.7298594 |
22 | PAN S J, YANG Q. A survey on transfer learning[J]. IEEE Transactions on Knowledge and Data Engineering, 2010, 22(10): 1345-1359. 10.1109/tkde.2009.191 |
23 | ZEILER M D, FERGUS R. Visualizing and understanding convolutional networks[C]// Proceedings of the 2014 European Conference on Computer Vision, LNCS 8689. Cham: Springer, 2014: 818-833. |
24 | ALOTAIBI A, MAHMOOD A. Deep face liveness detection based on nonlinear diffusion using convolution neural network[J]. Signal, Image and Video Processing, 2017, 11(4): 713-720. 10.1007/s11760-016-1014-2 |
25 | YU C Y, JIA Y D. Anisotropic diffusion-based kernel matrix model for face liveness detection[EB/OL]. (2017-07-10) [2021-05-22].. 10.1016/j.imavis.2019.06.009 |
26 | 蔡祥云. 人脸识别中的活体检测及应用研究[D]. 兰州:兰州交通大学, 2020:34-48. |
CAI X Y. Research on spoofing detection and application in face recognition[D]. Lanzhou: Lanzhou Jiaotong University, 2020:34-48. | |
27 | 陈路燕. 人脸识别中的活体检测算法研究[D]. 北京:北京邮电大学, 2020:23-38. |
CHEN L Y. Research on face anti-spoofing algorithm in face recognition[D]. Beijing: Beijing University of Posts and Telecommunications, 2020:23-38. | |
28 | 卢鑫. 基于改进卷积神经网络的人脸活体检测研究[D]. 鞍山:辽宁科技大学, 2020:39-48. 10.1007/978-981-15-3415-7_32 |
LU X. Research of face liveness detection based on improved convolutional neural network[D]. Anshan: University of Science and Technology Liaoning, 2020:39-48. 10.1007/978-981-15-3415-7_32 | |
29 | 曲啸枫. 基于多特征融合的活体人脸检测算法研究及应用[D]. 济南:济南大学, 2019:21-28. |
QU X F. Research and application of face liveness detection based on multi-feature fusion[D]. Jinan: University of Jinan, 2019:21-28. | |
30 | 李新豆,高陈强,周风顺,等. 基于图像扩散速度模型和纹理信息的人脸活体检测[J]. 计算机科学, 2020, 47(2):112-117. 10.11896/jsjkx.181202339 |
LI X D, GAO C Q, ZHOU F S, et al. Face liveness detection based on image diffusion speed model and texture information[J]. Computer Science, 2020, 47(2):112-117. 10.11896/jsjkx.181202339 |
[1] | 潘烨新, 杨哲. 基于多级特征双向融合的小目标检测优化模型[J]. 《计算机应用》唯一官方网站, 2024, 44(9): 2871-2877. |
[2] | 刘瑞华, 郝子赫, 邹洋杨. 基于多层级精细特征融合的步态识别算法[J]. 《计算机应用》唯一官方网站, 2024, 44(7): 2250-2257. |
[3] | 翟飞宇, 马汉达. 基于DenseNet的经典-量子混合分类模型[J]. 《计算机应用》唯一官方网站, 2024, 44(6): 1905-1910. |
[4] | 黄梦源, 常侃, 凌铭阳, 韦新杰, 覃团发. 基于层间引导的低光照图像渐进增强算法[J]. 《计算机应用》唯一官方网站, 2024, 44(6): 1911-1919. |
[5] | 刘越, 刘芳, 武奥运, 柴秋月, 王天笑. 基于自注意力机制与图卷积的3D目标检测网络[J]. 《计算机应用》唯一官方网站, 2024, 44(6): 1972-1977. |
[6] | 李鸿天, 史鑫昊, 潘卫国, 徐成, 徐冰心, 袁家政. 融合多尺度和注意力机制的小样本目标检测[J]. 《计算机应用》唯一官方网站, 2024, 44(5): 1437-1444. |
[7] | 韩贵金, 张馨渊, 张文涛, 黄娅. 基于多特征融合的自监督图像配准算法[J]. 《计算机应用》唯一官方网站, 2024, 44(5): 1597-1604. |
[8] | 时旺军, 王晶, 宁晓军, 林友芳. 小样本场景下的元迁移学习睡眠分期模型[J]. 《计算机应用》唯一官方网站, 2024, 44(5): 1445-1451. |
[9] | 李鑫, 孟乔, 皇甫俊逸, 孟令辰. 基于分离式标签协同学习的YOLOv5多属性分类[J]. 《计算机应用》唯一官方网站, 2024, 44(5): 1619-1628. |
[10] | 王昊冉, 于丹, 杨玉丽, 马垚, 陈永乐. 面向工控系统未知攻击的域迁移入侵检测方法[J]. 《计算机应用》唯一官方网站, 2024, 44(4): 1158-1165. |
[11] | 蒋占军, 吴佰靖, 马龙, 廉敬. 多尺度特征和极化自注意力的Faster-RCNN水漂垃圾识别[J]. 《计算机应用》唯一官方网站, 2024, 44(3): 938-944. |
[12] | 吴宁, 罗杨洋, 许华杰. 基于多尺度特征融合的遥感图像语义分割方法[J]. 《计算机应用》唯一官方网站, 2024, 44(3): 737-744. |
[13] | 郑宇亮, 陈云华, 白伟杰, 陈平华. 融合事件数据和图像帧的车辆目标检测[J]. 《计算机应用》唯一官方网站, 2024, 44(3): 931-937. |
[14] | 贾宗泽, 高鹏飞, 马应龙, 刘晓峰, 夏海鑫. 基于注意力机制的多特征融合对话行为层次化分类方法[J]. 《计算机应用》唯一官方网站, 2024, 44(3): 715-721. |
[15] | 李新叶, 侯晔凝, 孔英会, 燕志旗. 结合特征融合与增强注意力的少样本目标检测[J]. 《计算机应用》唯一官方网站, 2024, 44(3): 745-751. |
阅读次数 | ||||||
全文 |
|
|||||
摘要 |
|
|||||