首页 > 论文 > 激光与光电子学进展 > 56卷 > 18期(pp:181005--1)

基于多任务学习的深层人脸识别算法

Deep Face Recognition Algorithm Based on Multitask Learning

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

摘要

针对传统的归一化指数损失(Softmax损失)函数缺乏区别特征能力,对人脸特征无法进行判别性学习的问题,提出一种聚合判别多任务学习算法。首先,利用多任务级联卷积神经网络方法对目标图像进行人脸检测和对齐,剔除与人脸识别区域无关的图像;然后,利用深层卷积神经网络提取对齐后的人脸图像特征,同时使用聚合判别多任务学习算法将提取的人脸特征向量分解为学习类内特征的向量和判别类间身份的向量,加强对类内特征的约束,提高类间特征可分离性;最终分别采用最近邻分类器和十折交叉验证法进行人脸的识别和验证。实验结果表明:该算法在LFW人脸库中的验证准确率可达99.68%,改善了人脸识别性能,且在光照、姿势、表情和年龄变化测试中具有较好的稳健性,能有效应用于人脸识别的工程实践中。

Abstract

Aim

ing at the problems that the traditional normalized exponential loss (Softmax) function lacks the ability to distinguish features and facial features cannot be learned discriminatively, an aggregation and discriminant multitask learning algorithm is proposed. First, the multitask cascaded convolutional neural network is used to detect and align the face of the target images, eliminating the images that are not related with the face recognition region. Then, the deep convolutional neural network is used to extract the aligned facial features. The aggregation and discriminant multitask learning algorithm is used to decompose the vectors of extracted facial feature into learning intra-class features and discriminating inter-class identities, which strengthens the constraint of intra-class features and improves the separability of inter-class features. Finally, the nearest neighbor classifier and ten-fold cross-validation method are used for face recognition and verification respectively. Experimental results show that the verification accuracy of the proposed algorithm in LFW face database can reach 99.68%. The proposed algorithm improves the performance of face recognition, and has good robustness in illumination, pose, expression, and age change test. It can be effectively used in face recognition engineering practice.

Newport宣传-MKS新实验室计划
补充资料

DOI:10.3788/LOP56.181005

所属栏目:图像处理

收稿日期:2019-02-25

修改稿日期:2019-04-04

网络出版日期:2019-09-01

作者单位    点击查看

杨恢先:湘潭大学物理与光电工程学院, 湖南 湘潭 411105
陈凡:湘潭大学物理与光电工程学院, 湖南 湘潭 411105
甘伟发:湘潭大学物理与光电工程学院, 湖南 湘潭 411105

联系人作者:杨恢先(yanghx@xtu.edu.cn)

【1】Lowe D G. Distinctive image features from scale-invariant keypoints. International Journal of Computer Vision. 60(2), 91-110(2004).

【2】Yang H X, Xu C G, Zeng J F et al. Face recognition based on multi-directional Weber gradient histograms. Laser & Optoelectronics Progress. 55(11), (2018).
杨恢先, 徐唱, 曾金芳 等. 基于多方向韦伯梯度直方图的人脸识别. 激光与光电子学进展. 55(11), (2018).

【3】Yang H X, Chen Y, Zhang F et al. Face recognition based on improved gradient local binary pattern. Laser & Optoelectronics Progress. 55(6), (2018).
杨恢先, 陈永, 张翡 等. 基于改进梯度局部二值模式的人脸识别. 激光与光电子学进展. 55(6), (2018).

【4】Xia J, Pei D, Wang Q Z et al. Face recognition based on local adaptive ternary derivative pattern coupled with Gabor feature. Laser & Optoelectronics Progress. 53(11), (2016).
夏军, 裴东, 王全州 等. 融合Gabor特征的局部自适应三值微分模式的人脸识别. 激光与光电子学进展. 53(11), (2016).

【5】Turk M A and Pentland A P. Face recognition using eigenfaces. [C]∥1991 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, June 3-6, 1991, Maui, HI, USA. New York: IEEE. 586-591(1991).

【6】Belhumeur P N, Hespanha J P and Kriegman D J. Eigenfaces vs. Fisherfaces: recognition using class specific linear projection. ∥Buxton B, Cipolla R. Computer vision-ECCV''''96. Lecture notes in computer science. Berlin, Heidelberg: Springer. 1064, 43-58(1996).

【7】Wright J, Yang A Y, Ganesh A et al. Robust face recognition via sparse representation. IEEE Transactions on Pattern Analysis and Machine Intelligence. 31(2), 210-227(2009).

【8】Long X, Su H S, Liu G H et al. A face recognition algorithm based on angular distance loss function and convolutional neural network. Laser & Optoelectronics Progress. 55(12), (2018).
龙鑫, 苏寒松, 刘高华 等. 一种基于角度距离损失函数和卷积神经网络的人脸识别算法. 激光与光电子学进展. 55(12), (2018).

【9】Wang H, Wang Y T, Zhou Z et al. CosFace: large margin cosine loss for deep face recognition. [C]∥2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, June 18-23, 2018, Salt Lake City, UT, USA. New York: IEEE. 5265-5274(2018).

【10】Wen Y D, Zhang K P, Li Z F et al. A discriminative feature learning approach for deep face recognition. ∥Leibe B, Matas J, Sebe N, et al. Computer vision-ECCV 2016. Lecture notes in computer science. Cham: Springer. 9911, 499-515(2016).

【11】Liu W Y, Wen Y D, Yu Z D et al. Large-margin softmax loss for convolutional neural networks. [C]∥ICML''''16 Proceedings of the 33rd International Conference on International Conference on Machine Learning, June 19-24, 2016, New York, NY, USA. USA: JMLR.org. 48, 507-516(2016).

【12】Liu W Y, Wen Y D, Yu Z D et al. SphereFace: deep hypersphere embedding for face recognition. [C]∥2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), July 21-26, 2017, Honolulu, HI, USA. New York: IEEE. 6738-6746(2017).

【13】Wang F, Cheng J, Liu W Y et al. Additive margin softmax for face verification. IEEE Signal Processing Letters. 25(7), 926-930(2018).

【14】Xiao H and Rasul K. -09-15)[2019-02-10]. https:∥arxiv. org/abs/1708, (2017).

【15】LeCun Y, Bottou L, Bengio Y et al. . Gradient-based learning applied to document recognition. Proceedings of the IEEE. 86(11), 2278-2324(1998).

【16】Huang G B, Mattar M, Berg T et al. Labeled faces in the wild: a database forstudying face recognition in unconstrained environments. [C]∥Workshop on faces in ''''Real-Life'''' Images: detection, alignment, and recognition. October, 2008, Marseille, France. France: Inria. 00321923, (2008).

【17】Sengupta S, Chen J C, Castillo C et al. Frontal to profile face verification in the wild. [C]∥2016 IEEE Winter Conference on Applications of Computer Vision (WACV), March 7-10, 2016, Lake Placid, NY, USA. New York: IEEE. 16051830, (2016).

【18】Moschoglou S, Papaioannou A, Sagonas C et al. AgeDB: the first manually collected, in-the-wild age database. [C]∥2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), July 21-26, 2017, Honolulu, HI, USA. New York: IEEE. 1997-2005(2017).

【19】Cao Q, Shen L, Xie W D et al. VGGFace2: a dataset for recognising faces across pose and age. [C]∥2018 13th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2018), May 15-19, 2018, Xi''''an, China. New York: IEEE. 67-74(2018).

【20】Zhang K P, Zhang Z P, Li Z F et al. Joint face detection and alignment using multitask cascaded convolutional networks. IEEE Signal Processing Letters. 23(10), 1499-1503(2016).

【21】Deng J K, Guo J, Xue N N et al. ArcFace: additive angular margin loss for deep face recognition. -02-09)[2019-02-10]. https:∥arxiv. org/abs/1801, (2019).

【22】He K M, Zhang X Y, Ren S Q et al. Deep residual learning for image recognition. [C]∥2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 27-30, 2016, Las Vegas, NV, USA. New York: IEEE. 770-778(2016).

【23】Deng J K, Zhou Y X and Zafeiriou S. Marginal loss for deep face recognition. [C]∥2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), July 21-26, 2017, Honolulu, HI, USA. New York: IEEE. 2006-2014(2017).

【24】Parkhi O M, Vedaldi A and Zisserman A. Deep face recognition[C]∥Proceedings of the British Machine Vision Conference 2015, September 7-10, 2015, Swansea, UK. Durham, England,. 41, (2015).

引用该论文

Huixian Yang,Fan Chen,Weifa Gan. Deep Face Recognition Algorithm Based on Multitask Learning[J]. Laser & Optoelectronics Progress, 2019, 56(18): 181005

杨恢先,陈凡,甘伟发. 基于多任务学习的深层人脸识别算法[J]. 激光与光电子学进展, 2019, 56(18): 181005

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