基于多任务学习的多姿态人脸重建与识别

doi:10.11772/j.issn.1001-9081.2017.03.896

计算机应用 ›› 2017, Vol. 37 ›› Issue (3): 896-900.DOI: 10.11772/j.issn.1001-9081.2017.03.896

• 应用前沿、交叉与综合 • 上一篇下一篇

基于多任务学习的多姿态人脸重建与识别

欧阳宁^1,2, 马玉涛², 林乐平^1,2

1. 认知无线电与信息处理省部共建教育部重点实验室(桂林电子科技大学), 广西桂林 541004;
2. 桂林电子科技大学信息与通信学院, 广西桂林 541004

收稿日期:2016-08-01 修回日期:2016-09-07 出版日期:2017-03-10 发布日期:2017-03-22
通讯作者: 林乐平
作者简介:欧阳宁(1972-),男,湖南宁远人,教授,硕士,主要研究方向:数字图像处理、智能信息处理;马玉涛(1991-),女,内蒙古乌兰察布人,硕士研究生,主要研究方向:人脸识别、深度学习;林乐平(1980-),女,广西桂平人,博士,主要研究方向:模式识别、智能信息处理、图像信号处理。
基金资助:
国家自然科学基金资助项目（61362021，61661017）；广西自然科学基金资助项目（2013GXNSFDA019030，2014GXNSFDA118035）；广西科技创新能力与条件建设计划项目（桂科能1598025-21）；桂林科技开发项目（20150103-6）。

Multi-pose face reconstruction and recognition based on multi-task learning

OUYANG Ning^1,2, MA Yutao², LIN Leping^1,2

1. Key Laboratory of Cognitive Radio and Information Processing, Ministry of Education(Guilin University of Electronic Technology), Guilin Guangxi 541004, China;
2. School of Information and Communication, Guilin University of Electronic Technology, Guilin Guangxi 541004, China

Received:2016-08-01 Revised:2016-09-07 Online:2017-03-10 Published:2017-03-22
Supported by:
This work is partially supported by the Natural Science Foundation of China (61362021, 61661017), the Natural Science Foundation of Guangxi (2013GXNSFDA019030, 2014GXNSFDA118035), the Scientific and Technological Innovation Ability and Condition Construction Plan of Guangxi (1598025-21), the Scientific and Technological Development Project of Guilin (20150103-6).

摘要/Abstract

摘要： 针对当前人脸识别中姿态变化会影响识别性能，以及姿态恢复过程中脸部局部细节信息容易丢失的问题，提出一种基于多任务学习的多姿态人脸重建与识别方法——多任务学习堆叠自编码器（MtLSAE）。该方法通过运用多任务学习机制，联合考虑人脸姿态恢复和脸部局部细节信息保留这两个相关的任务，在步进逐层恢复正面人脸姿态的同时，引入非负约束稀疏自编码器，使得非负约束稀疏自编码器能够学习到人脸部的部分特征；其次在姿态恢复和局部信息保留两个任务之间通过共享参数的方式来学习整个网络框架；最后将重建出来的正脸图像通过Fisherface进行降维并提取具有判别信息的特征，并用最近邻分类器来识别。实验结果表明，MtLSAE方法获得了较好的姿态重建质量，保留的局部纹理信息清晰，而且与局部Gabor二值模式（LGBP）、基于视角的主动外观模型（VAAM）以及堆叠步进自编码器（SPAE）等经典方法相比，识别率性能得以提升。

关键词: 多任务学习, 姿态恢复, 局部细节信息, 自编码器, 共享参数

Abstract: To circumvent the influence of pose variance on face recognition performance and considerable probability of losing the facial local detail information in the process of pose recovery, a multi-pose face reconstruction and recognition method based on multi-task learning was proposed, namely Multi-task Learning Stacked Auto-encoder (MtLSAE). Considering the correlation between pose recovery and retaining local detail information, multi-task learning mechanism was used and sparse auto-encoder with non-negativity constraints was introduced by MtLSAE to learn part features of the face when recovering frontal images using step-wise approach. And then the whole net framework was learned by sharing parameters between above two related tasks. Finally, Fisherface was used for dimensionality reduction and extracting discriminative features of reconstructed positive face image, and the nearest neighbor classifier was used for recognition. The experimental results demonstrate that MtLSAE achieves good pose reconstruction quality and makes facial local texture information clear; on the other hand, it also achieves higher recognition rate than some classical methods such as Local Gabor Binary Pattern(LGBP), View-Based Active Appearance (VAAM) and Stacked Progressive Auto-encoder (SPAE).

Key words: multi-task learning, pose recovery, local detail information, auto-encoder, sharing parameter

中图分类号:

TP391.3

欧阳宁, 马玉涛, 林乐平. 基于多任务学习的多姿态人脸重建与识别[J]. 计算机应用, 2017, 37(3): 896-900.

OUYANG Ning, MA Yutao, LIN Leping. Multi-pose face reconstruction and recognition based on multi-task learning[J]. Journal of Computer Applications, 2017, 37(3): 896-900.

参考文献

[1] TAN X, TRIGGS B. Enhanced local texture feature sets for face recognition under difficult lighting conditions[J]. IEEE Transactions on Image Processing, 2010, 19(6):1635-1650.
[2] HUANG G B, RAMESH M, BERG T, et al. Labeled faces in the wild:a database for studying face recognition in unconstrained environments[R]. Cambridge:University of Massachusetts, 2007:49.
[3] GÜNTHER M, COSTA-PAZO A, DING C, et al. The 2013 face recognition evaluation in mobile environment[C]//ICB 2013:Proceedings of the 2013 International Conference on Biometrics. Piscataway, NJ:IEEE, 2013:1-7.
[4] ZHANG W, SHAN S, GAO W, et al. Local Gabor Binary Pattern Histogram Sequence (LGBPHS):a novel non-statistical model for face representation and recognition[C]//ICCV'05:Proceedings of the Tenth IEEE International Conference on Computer Vision. Washington, DC:IEEE Computer Society, 2005, 1:786-791.
[5] ASTHANA A, MARKS T K, JONES M J, et al. Fully automatic pose-invariant face recognition via 3D pose normalization[C]//ICCV'11:Proceedings of the 2011 International Conference on Computer Vision. Washington, DC:IEEE Computer Society, 2011:937-944.
[6] HO H T, CHELLAPPA R. Pose-invariant face recognition using Markov random fields[J]. IEEE Transactions on Image Processing, 2013, 22(4):1573-1584.
[7] ZHU Z, LUO P, WANG X, et al. Deep learning identity-preserving face space[C]//ICCV'13:Proceedings of the 2013 IEEE International Conference on Computer Vision. Washington, DC:IEEE Computer Society, 2013:113-120.
[8] ZHU Z, LUO P, WANG X, et al. Multi-view perceptron:a deep model for learning face identity and view representations[C]//NIPS 2014:Advances in Neural Information Processing Systems. Cambridge, MA:MIT Press, 2014:217-225.
[9] BENGIO Y. Learning deep architectures for AI[J]. Foundations and Trends in Machine Learning, 2009, 2(1):1-127.
[10] KAN M, SHAN S, CHANG H, et al. Stacked Progressive Auto-Encoders (SPAE) for face recognition across poses[C]//CVPR'14:Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition.Washington, DC:IEEE Computer Society, 2014:1883-1890.
[11] SHIELDS T J, AMER M R, EHRLICH M, et al. Action-affect classification and morphing using multi-task representation learning[J/OL]. arXiv preprint arXiv:1603.06554, 2016[2016-03-21]. https://arxiv.org/abs/1603.06554.
[12] ARGYRIOU A, EVGENIOU T, PONTIL M. Multi-task feature learning[C]//NIPS 2006:Advances in Neural Information Processing Systems. Cambridge, MA:MIT Press, 2007, 19:41-48.
[13] HOSSEINI-ASL E, ZURADA J M, NASRAOUI O. Deep learning of part-based representation of data using sparse autoencoders with nonnegativity constraints[J]. IEEE Transactions on Neural Networks and Learning Systems, 2015, 27(12):1-13.
[14] BELHUMEUR P N, HESPANHA J P, KRIEGMAN D J. Eigenfaces vs. fisherfaces:recognition using class specific linear projection[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1997, 19(7):711-720.
[15] NAIR V, HINTON G E. Rectified linear units improve restricted Holtzmann machines[C]//ICML-10:Proceedings of the 27th International Conference on Machine Learning. Haifa:Omnipress, 2010:807-814.
[16] GRAVELINES C. Deep learning via stacked sparse autoencoders for automated voxel-wise brain parcellation based on functional connectivity[D]. Ontario, Canada:The University of Western Ontario, 2014:1-76.
[17] LEE H, EKANADHAM C, NG A Y. Sparse deep belief net model for visual area V2[C]//NIPS 2007:Advances in Neural Information Processing Systems. Cambridge, MA:MIT Press, 2008:873-880.
[18] NG A, NGIAM J, FOO C Y, et al. UFLDL Tutorial[EB/OL]. (2013-04-07)[2016-08-26].http://deeplearning.stanford.edu/wiki/index.php/Gradient_checking_and_advanced_optimization.
[19] GROSS R, MATTHEWS I, COHN J, et al. The CMU multi-pose, illumination, and expression (Multi-PIE) face database, TR-07-08[R]. Pittsburgh:CMU Robotics Institute, 2007.
[20] 李航.统计学习方法[M].北京:清华大学出版社,2012:14-15. (LI H. Statical Learning Methods[M]. Beijing:Tsinghua University Press, 2012:14-15.)

基于多任务学习的多姿态人脸重建与识别

Multi-pose face reconstruction and recognition based on multi-task learning

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]	武国亮, 徐继宁. 基于命名实体识别任务反馈增强的中文突发事件抽取方法[J]. 计算机应用, 2021, 41(7): 1891-1896.
[2]	张元钧, 张曦煌. 基于图卷积与长短期记忆网络的动态网络表示学习模型[J]. 计算机应用, 2021, 41(7): 1857-1864.
[3]	姚杰, 程春玲, 韩静, 刘峥. 云工作流中基于多任务时序卷积网络的异常检测方法[J]. 计算机应用, 2021, 41(6): 1701-1708.
[4]	章荪, 尹春勇. 基于多任务学习的时序多模态情感分析模型[J]. 计算机应用, 2021, 41(6): 1631-1639.
[5]	孙鹤立, 孙玉柱, 张晓云. 基于生成对抗网络的事件描述生成[J]. 计算机应用, 2021, 41(5): 1256-1261.
[6]	樊玮, 王慧敏, 邢艳. 基于自编码器的多视图属性网络表示学习模型[J]. 计算机应用, 2021, 41(4): 1064-1070.
[7]	刘太亨, 何昭水. 基于自编码和知识蒸馏的表面缺陷检测方法[J]. 《计算机应用》唯一官方网站, 2021, 41(11): 3200-3205.
[8]	屠红艳, 张挺, 夏鹏飞, 杜奕. 基于改进型变分自编码器的不确定性空间信息重建方法[J]. 计算机应用, 2021, 41(10): 2959-2963.
[9]	黄晓祥, 胡咏梅, 吴丹, 任力杰. 基于变分自编码器的异常颈动脉早期识别和预测[J]. 计算机应用, 2021, 41(10): 3082-3088.
[10]	李自强, 王正勇, 陈洪刚, 李林怡, 何小海. 基于外观和动作特征双预测模型的视频异常行为检测[J]. 计算机应用, 2021, 41(10): 2997-3003.
[11]	罗俊, 陈黎飞. 基于BERT的不完全数据情感分类[J]. 计算机应用, 2021, 41(1): 139-144.
[12]	阮灿华, 林甲祥. 动态事件时间数据的多任务Logistic生存预测方法[J]. 计算机应用, 2020, 40(5): 1284-1290.
[13]	霍纬纲, 王慧芳. 基于自编码器和隐马尔可夫模型的时间序列异常检测方法[J]. 计算机应用, 2020, 40(5): 1329-1334.
[14]	朱喆, 许少华. 降噪自编码器深度卷积过程神经网络及在时变信号分类中的应用[J]. 计算机应用, 2020, 40(3): 698-703.
[15]	傅洪亮, 雷沛之. 基于去噪自编码器和长短时记忆网络的语音测谎算法[J]. 计算机应用, 2020, 40(2): 589-594.