三维人脸建模及在跨姿态人脸匹配中的有效性验证

doi:10.11772/j.issn.1001-9081.2017.01.0262

计算机应用 ›› 2017, Vol. 37 ›› Issue (1): 262-267.DOI: 10.11772/j.issn.1001-9081.2017.01.0262

• 计算机视觉与虚拟现实 • 上一篇下一篇

三维人脸建模及在跨姿态人脸匹配中的有效性验证

李昕昕¹, 龚勋²

1. 四川大学锦城学院计算机科学与软件工程系, 成都 611731;
2. 西南交通大学信息科学与技术学院, 成都 610031

收稿日期:2016-08-30 修回日期:2016-09-24 出版日期:2017-01-10 发布日期:2017-01-09
通讯作者: 龚勋
作者简介:李昕昕(1981-),女,四川乐至人,副教授,硕士,主要研究方向:人工智能、模式识别、网络协议测试;龚勋(1980-),男,湖南永顺人,副教授,博士,CCF会员,主要研究方向:人工智能、模式识别、三维建模。
基金资助:
国家自然科学基金资助项目（61202191）；四川省教育厅自然科学重点课题（16ZA0422）。

3D face modeling and validation in cross-pose face matching

LI Xinxin¹, GONG Xun²

1. Department of Computer Science and Software Engineering, Jincheng College of Sichuan University, Chengdu Sichuan 611731, China;
2. College of Information Science and Technology, Southwest Jiaotong University, Chengdu Sichuan 610031, China

Received:2016-08-30 Revised:2016-09-24 Online:2017-01-10 Published:2017-01-09
Supported by:
This work is partially supported by the National Natural Science Foundation of China (61202191), the Natural Science Key Projects of Sichuan Provincial Department of Education (16ZA0422).

摘要/Abstract

摘要： 针对现有三维人脸采集技术对采集场景存在诸多限制，提出了自由场景下基于多张图像的三维人脸建模技术，并对其进行了有效性验证。首先，提出一个姿态及深度值迭代计算模型，实现了特征点深度值的准确估计；然后，进行了基于多张图像的深度值融合及整体形状建模；最后，将深度迭代优化算法（IPDO）与目前最优的非线性最小二乘法（NLS1_SR）在Bosphorus Database数据集上进行了对比，建模精度提高了9%，所重建的三维人脸模型投影图像与二维图像具有较高的相似度。实验结果表明，在大姿态变化条件下，该识别算法借助三维信息相较于未借助的情况下，其识别率可以提高50%以上。

关键词: 三维人脸, 人脸建模, 人脸识别, 多姿态, 跨模态

Abstract: Since the existing 3D face acquisition technology has many restrictions on gathering scene, a 3D face reconstruction technology based on several images was proposed, and its validation was verified. First, an iterative computing model of pose and depth value estimation was proposed to implement the accurate estimation of feature depth. Then the depth values integration based on several images and shape modeling were further investigated. Finally, the Iterative Pose and Depth Optimization (IPDO) algorithm was compared with Nonlinear Least-Squares Model with Symmetry and Regularization terms (NLS1_SR) on Bosphorus database, the modeling precision was improved by 9%, and the projected image of 3D model is similar to the 2D inputted image. The experimental results show that under the condition of big pose change, the proposed recognition algorithm assisted by 3D information can improve the recognition rate of more than 50%.

Key words: 3D face, face modeling, face recognition, multiple view, cross-modality

中图分类号:

TP391.413

李昕昕, 龚勋. 三维人脸建模及在跨姿态人脸匹配中的有效性验证[J]. 计算机应用, 2017, 37(1): 262-267.

LI Xinxin, GONG Xun. 3D face modeling and validation in cross-pose face matching[J]. Journal of Computer Applications, 2017, 37(1): 262-267.

参考文献

[1] ROWDEN L B, BISHT S, KLONTZ J C, et al. Unconstrained face recognition:establishing baseline human performance via crowdsourcing[C]//Proceedings of the 2014 IEEE International Joint Conference on Biometrics. Piscataway, NJ:IEEE, 2014:1-8.
[2] PHILLIPS P J, SCRUGGS W T, O'TOOLE A J, et al. FRVT 2006 and ICE 2006 large-scale experimental results[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2010, 32(5):831-846.
[3] MOHAMMADZADE H, HATZINAKOS D. Iterative closest normal point for 3D face recognition[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013, 35(2):381-397.
[4] YI D, LEI Z, LI S Z. Towards pose robust face recognition[C]//Proceedings of the 2013 IEEE International Conference on Computer Vision and Pattern Recognition. Piscataway, NJ:IEEE, 2013:3539-3545.
[5] BLANZ V, VETTER T. A morphable model for the synthesis of 3D faces[C]//Proceedings of the 26th Annual Conference on Computer Graphics and Interactive Techniques. New York:ACM, 1999:187-194.
[6] PATEL A, SMITH W A P. 3D morphable face models revisited[C]//Proceedings of the 2009 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway, NJ:IEEE, 2009:1327-1334.
[7] WANG S, LAI S. Reconstructing 3D face model with associated expression deformation from a single face image via constructing a low-dimensional expression deformation manifold[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33(10):2115-2121.
[8] BUSTARD J D, NIXON M S. 3D morphable model construction for robust ear and face recognition[C]//Proceedings of the 2010 IEEE Conference Computer Vision and Pattern Recognition. Piscataway, NJ:IEEE, 2010:2582-2589.
[9] 龚勋,王国胤.基于特征点的三维人脸形变模型[J].软件学报,2009,20(3):724-733.(GONG X, WANG G Y. 3D face deformable model based on feature points[J]. Journal of Software, 2009, 20(3):724-733.)
[10] KEMELMACHER-SHLIZERMAN I, BASRI R. 3D face recon-struction from a single image using a single reference face shape[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33(2):394-405.
[11] KEMELMACHER-SHLIZERMAN I. Internet-based morphable model[C]//Proceedings of the 2013 IEEE International Conference on Computer Vision. Piscataway, NJ:IEEE, 2013:3256-3263.
[12] SUWAJANAKORN S, KEMELMACHER-SHLIZERMAN I, SEITZ S. Total moving face reconstruction[C]//Proceedings of the 2014 European Conference on Computer Vision. Berlin:Springer, 2014:796-812.
[13] LIN Y, MEDIONI G, CHOI J. Accurate 3D face reconstruction from weakly calibrated wide baseline images with profile contours[C]//Proceedings of the 2010 IEEE International Conference on Computer Vision and Pattern Recognition. Piscataway, NJ:IEEE, 2010:1490-1497.
[14] GONZALEZ-MORA J, DE LA TORRE F, GUIL N, et al. Learning a generic 3D face model from 2D image databases using incremental structure from motion[J]. Image and Vision Computing, 2010, 28(7):1117-1129.
[15] GONG X, WANG G Y. Example-based learning for depth estimation of facial landmarks and its application in face modeling[J]. Chinese Journal of Electronics, 2010, 19(4):676-680.
[16] GONG X, WANG G Y, LI X X, et al. A statistical two-step method for 3D face reconstruction from single image[J]. Chinese Journal of Electronics, 2011, 20(4):671-675.
[17] KENNEDY J, EBERHART R. Particle swarm optimization[C]//Proceedings of the 2013 IEEE International Conference on Neural Networks. Piscataway, NJ:IEEE, 1995:1942-1948.
[18] KOO H, LAM K. Recovering the 3D shape and poses of face images based on the similarity transform[J]. Pattern Recognition Letters, 2008, 29(6):712-723.
[19] SUN Z, LAM K, GAO Q. Depth estimation of face images using the nonlinear least-squares model[J]. IEEE Transactions on Image Processing, 2013, 22(1):17-30.
[20] DE MARSICO M, NAPPI M, RICCIO D, et al. Robust face recognition for uncontrolled pose and illumination changes[J]. IEEE Transactions on Systems, Man, and Cybernetics, Part A:Systems and Humans, 2013, 43(1):149-163.
[21] NORDSTROM M M, LARSEN M, SIERAKOWSKI J, et al. The IMM face database-an annotated dataset of 240 face images[R]. Copenhagen, Denmark:Technical University of Denmark, 2004.
[22] PHILLIPS P J, WECHSLER H, HUANG J, et al. The FERET database and evaluation procedure for face-recognition algorithms[J]. Image and Vision Computing, 1998, 16(5):295-306.
[23] SAVRAN A, ALYUZ N, DIBEKLIOGLU H, et al. Bosphorus database for 3D face analysis[M]//Biometrics and Identity Management. Berlin:Springer, 2008:47-56.
[24] BLANZ V, MEHL A, VETTER T, et al. A statistical method for robust 3D surface reconstruction from sparse data[C]//Proceedings of the 2nd International Symposium on 3D Data Processing, Visualization. Washington, DC:IEEE Computer Society, 2004:293-300.
[25] HEO J, SAVVIDES M. Rapid 3D face modeling using a frontal face and a profile face for accurate 2D pose synthesis[C]//Proceedings of the 2011 IEEE International Conference on Automatic Face & Gesture Recognition. Piscataway, NJ:IEEE, 2011:632-638.
[26] XIE S, SHAN S, CHEN X, et al. Fusing local patterns of Gabor magnitude and phase for face recognition[J]. IEEE Transactions on Image Processing, 2010, 19(5):1349-1361.

三维人脸建模及在跨姿态人脸匹配中的有效性验证

3D face modeling and validation in cross-pose face matching

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	张成, 万源, 强浩鹏. 基于知识蒸馏的深度无监督离散跨模态哈希[J]. 计算机应用, 2021, 41(9): 2523-2531.
[2]	高工, 杨红雨, 刘洪. 基于深度学习的三维点云人脸识别[J]. 计算机应用, 2021, 41(9): 2736-2740.
[3]	刘芳名, 张鸿. 基于多级语义的判别式跨模态哈希检索算法[J]. 计算机应用, 2021, 41(8): 2187-2192.
[4]	李虹霞, 秦品乐, 闫寒梅, 曾建潮, 鲍骞月, 柴锐. 基于面部特征图对称的人脸正面化生成对抗网络算法[J]. 计算机应用, 2021, 41(3): 714-720.
[5]	方书雅, 刘守印. 基于学生人体检测的无感知课堂考勤方法[J]. 计算机应用, 2020, 40(9): 2519-2524.
[6]	赵青, 余元辉. 基于分层特征化网络的三维人脸识别[J]. 计算机应用, 2020, 40(9): 2514-2518.
[7]	李东博, 黄铝文. 重加权稀疏主成分分析算法及其在人脸识别中的应用[J]. 计算机应用, 2020, 40(3): 717-722.
[8]	龚锐, 丁胜, 章超华, 苏浩. 基于深度学习的轻量级和多姿态人脸识别方法[J]. 计算机应用, 2020, 40(3): 704-709.
[9]	陈放, 刘晓瑞, 杨明业. 基于活体检测和身份认证的人脸识别安防系统[J]. 计算机应用, 2020, 40(12): 3666-3672.
[10]	周健, 黄章进. 基于改进三维形变模型的三维人脸重建和密集人脸对齐方法[J]. 计算机应用, 2020, 40(11): 3306-3313.
[11]	林乐平, 李三凤, 欧阳宁. 基于多姿态特征融合生成对抗网络的人脸校正方法[J]. 计算机应用, 2020, 40(10): 2856-2862.
[12]	任珍文, 吴明娜. 基于熵自加权联合正则化最近点的图像集分类算法[J]. 计算机应用, 2019, 39(9): 2547-2551.
[13]	丁莲静, 刘光帅, 李旭瑞, 陈晓文. 加权信息熵与增强局部二值模式结合的人脸识别[J]. 计算机应用, 2019, 39(8): 2210-2216.
[14]	方国康, 李俊, 王垚儒. 基于深度学习的ARM平台实时人脸识别[J]. 计算机应用, 2019, 39(8): 2217-2222.
[15]	桑高丽, 闫超, 朱蓉. 基于多区域融合的表情鲁棒三维人脸识别算法[J]. 计算机应用, 2019, 39(6): 1685-1689.