Frontal Face Image Synthesis Based on Pose Estimation

doi:10.3969/j.issn.1000-3428.2015.10.045

Abstract

Abstract: In order to process the face image in different poses,this paper proposes a frontal face image synthesis method based on pose estimation.The method is based on the idea of statistical modeling to reconstruct the missing face shape and texture.Firstly,3D average model is applied to estimate the pose parameters of the test face image.Compressed sensing theory is used to filter prototype samples and then a more accurate model of deformation is built up.Secondly,the test face image is separately expressed by texture vector and shape vector.The deformation model theory is used to reconstruct front texture and shape.Finally,synthesis texture is produced according to the original texture and reconstructed texture.Experimental result shows that this method can be used to synthesize natural frontal face image from non-frontal face image with effectiveness and higher recognition rate.

Key words: frontal face image synthesis, average 3D model, pose estimation, compressed sensing, deformable model

摘要： 为对不同姿态下的人脸图像进行处理,提出一种基于姿态估计的正面人脸图像合成方法。利用统计建模的思想重构缺失的人脸形状和纹理。运用平均三维模型估计测试图像的姿态参数,结合压缩感知理论构建形变模型。应用稀疏形变模型理论分别重构测试人脸的三维形状和纹理,根据测试图像与重构模型生成正面人脸图像。实验结果表明,该方法能够由一幅姿态人脸图像合成出精确、自然的正脸图像,并具有较高的识别率。

关键词: 正面人脸图像合成, 平均三维模型, 姿态估计, 压缩感知, 形变模型

CLC Number:

TP18

FANG Sanyong,ZHOU Dake,CAO Yuanpeng,YANG Xin. Frontal Face Image Synthesis Based on Pose Estimation[J]. Computer Engineering, doi: 10.3969/j.issn.1000-3428.2015.10.045.

方三勇,周大可,曹元鹏,杨欣. 基于姿态估计的正面人脸图像合成[J]. 计算机工程, doi: 10.3969/j.issn.1000-3428.2015.10.045.

/ / Recommend / Download Citations

URL: http://www.ecice06.com/EN/10.3969/j.issn.1000-3428.2015.10.045

http://www.ecice06.com/EN/Y2015/V41/I10/240

References

参考文献［1］Zhao W,Chellappa R,Rosenfeld A,et al.Face Recogni-tion:A Literature Survey［J］.ACM Computing Survey,2003,35(4):399-458. ［2］赵林,高新波,田春娜.正面人脸图像合成方法综述［J］.中国图象图形学报,2013,18(1):1-10. ［3］Vetter T.Synthesis of Novel Views from a Simple Face Image［J］.International Journal of Computer Vision,1998,28(2):103-116. ［4］Blanz V,Grother P,Philips P J,et al.Face Recognition Based on Frontal Views Generated from Non-frontal Image［C］//Proceed-ings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.Los Alamitos,USA:IEEE Press,2005:454-461. (下转第249页) (上接第244页) ［5］Xiao Jing,Baker S.Real-time Combined 2D+3D Active Appearance Models［C］//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.New York,USA:IEEE Press,2004:535-542. ［6］Huang Xinyu,Gao Jizhou,Cheung S S,et al.Manifold Estimation in View-based Feature Space for Face Synthesis Across Poses［C］//Proceedings of the 9th Asian Conference on Computer Vision.Heidelberg,Germany:Springer-Verlag,2010:37-47. ［7］Li Yingchun.Face Pose Estimation and Synthesis by 2D Morphable Model［C］//Proceedings of International Conference on Computational Intelligence and Security.Heidelberg,Germany:Springer-Verlag,2007:1001-1008. ［8］杜成,苏光大,林行刚,等.多姿态人脸图像合成［J］.光电子·激光,2005,15(12):1498-1501. ［9］Chai Xiujuan.Locally Linear Regression for Pose-invariant Face Recogni-tion［J］.IEEE Transactions on Image Processing,2007,16(7):1716-1725. ［10］Li Xi,Takahashi T,Deguchi D,et al.Virtual View Generation Using Clustering Based Local View Transition Model［C］//Proceedings of the 11th Inter-national Conference on Computer Vision.Heidelberg,Germany:Springer-Verlag,2013:260- 271. ［11］熊黎丽,王国胤.基于三维重建的人脸姿态估计［J］.重庆邮电大学学报:自然科学版,2010,22(3):375-380. ［12］胡阳明,周大可,鹿乐.基于改进ASM的三维人脸自动对齐算法［J］.计算机工程,2013,39(3):250-253. ［13］Blanz V.Reconstructing the Complete 3D Shape of Faces from Partial Information［J］.Informations Tech-nikund Technische Informatik,2002,44(6):295-302. ［14］Donoho D L.Fast Solution of l1-norm Minimization Problems When the Solution May Be Sparse［J］.IEEE Tran-sactions on Information Theory,2008,54(11):4789-4812. ［15］尹宝才.BJUT-3D 三维人脸数据库及其处理技术［J］.计算机研究与发展,2009,46(6):1009-1018. ［16］张晓华,山世光,曹波,等.CAS-PEAL 大规模中国人脸图像数据库及其基本评测介绍［J］.计算机辅助设计与图形学学报,2005,17(1):9-17. 编辑金胡考

[1]	Hao LIU, Honglan WU, Yuxuan FANG. Efficient Human Pose Estimation Combining Global Contextual Information [J]. Computer Engineering, 2023, 49(7): 102-109.
[2]	Kuan WANG, Shibin XUAN, Xuedong HE, Ziwei LI, Jiaxiang LI. Human Pose Estimation Method Based on Cross Attention Transformer [J]. Computer Engineering, 2023, 49(7): 223-231.
[3]	ZHONG Baorong, WU Xialing. Research on Lightweight Human Pose Estimation Based on High-Resolution Network [J]. Computer Engineering, 2023, 49(4): 226-232,239.
[4]	FU Qi, XIE Kai, WEN Chang, HE Jianbiao. Head Pose Estimation Method Under Occlusion and Geometric Perception Models [J]. Computer Engineering, 2023, 49(3): 296-303,311.
[5]	ZHANG Wenwen, XU Yang, BAI Rui, CHEN Na. Animal Pose Estimation Based on Improved Stacked Hourglass Network [J]. Computer Engineering, 2023, 49(2): 263-270.
[6]	JIANG Ming, CHEN Yu, ZHOU Qinghua, YUAN Yuan, HE Shiqiong. Lightweight Pose Estimation Network for Non-Cooperative Target Acquisition [J]. Computer Engineering, 2022, 48(6): 235-242.
[7]	LUO Mengshi, XU Yang, YE Xingxin. Human Pose Estimation Using High Resolution Network with Dual Attention [J]. Computer Engineering, 2022, 48(2): 314-320.
[8]	LIU Yuhong, CHEN Manyin, LIU Xiaoyan. Multi-Scale Fully Convolutional Compressed Sensing Reconstruction Based on Channel Attention [J]. Computer Engineering, 2022, 48(12): 189-195.
[9]	FANG Haitao, LI Mingqi, BIAN Xin. Improved Algorithm for Compressed Sensing Channel Estimation Based on DFT Path Searching [J]. Computer Engineering, 2022, 48(1): 182-187.
[10]	JIANG Xueyuan, CHEN Qingmei, HUANG Chuhua. Hierarchical Feature Network for Visual Localization Based on Dynamic Traversal [J]. Computer Engineering, 2021, 47(9): 197-202.
[11]	WANG Liucheng, OUYANG Chengtian, LIANG Wen. Human Pose Estimation Based on Improved Pyramid Feature Network [J]. Computer Engineering, 2021, 47(8): 251-259,270.
[12]	LI Shaofei, SHI Zelin, ZHUANG Chungang. Deep Learning-Based 6D Object Pose Estimation Method from Point Clouds [J]. Computer Engineering, 2021, 47(8): 216-223.
[13]	FU Youjia. Facial Pose Estimation Method on Single Image Based on Facial Feature Points [J]. Computer Engineering, 2021, 47(4): 197-203,210.
[14]	LIU Yong, LI Jie, ZHANG Jianlin, XU Zhiyong, WEI Yuxing. Research Progress of Two-Dimensional Human Pose Estimation Based on Deep Learning [J]. Computer Engineering, 2021, 47(3): 1-16.
[15]	MA Kewei, ZHANG Qieshi, KANG Yuhang, REN Ziliang, CHENG Jun. Overview of Visual Odometry Technology in Mobile Robots [J]. Computer Engineering, 2021, 47(11): 1-10.

Please choose a citation manager

Content to export