一种利用年龄编辑改进年龄估计的方法

doi:10.12066/j.issn.1007-2861.2250

上海大学学报(自然科学版) ›› 2021, Vol. 27 ›› Issue (1): 28-38.doi: 10.12066/j.issn.1007-2861.2250

一种利用年龄编辑改进年龄估计的方法

张辰昱¹^,², 徐树公², 黄剑波¹^,³()

1.上海大学上海电影学院, 上海 200072
2.上海大学上海先进通信与数据科学研究院, 上海 200444
3.上海大学上海电影特效工程技术研究中心, 上海 200072

收稿日期:2020-03-23 出版日期:2021-02-28 发布日期:2020-09-13
通讯作者: 黄剑波 E-mail:huangjianbo110@shu.edu.cn
作者简介:黄剑波(1980---), 男, 博士, 研究方向为艺术学理论、图像处理等. E-mail: huangjianbo110@shu.edu.cn
基金资助:
上海大学电影学高峰学科和上海电影特效工程技术研究中心资助项目(16dz2251300)

Method for improving age estimation using age editing

ZHANG Chenyu¹^,², XU Shugong², HUANG Jianbo¹^,³()

1. Shanghai Film Academy, Shanghai University, Shanghai 200072, China
2. Shanghai Institute for Advanced Communication and Data Science, Shanghai University, Shanghai 200444, China
3. Shanghai Film Special Effects Engineering Technology Research Center, Shanghai University, Shanghai 200072, China

Received:2020-03-23 Online:2021-02-28 Published:2020-09-13
Contact: HUANG Jianbo E-mail:huangjianbo110@shu.edu.cn

摘要/Abstract

摘要：

人脸年龄估计(face age estimation)作为一种新兴的生物特征识别技术, 是计算机视觉中一个经典的学习问题. 基于生成对抗网络(generative adversarial network, GAN) 强大的数据生成能力, 提出了一种利用年龄编辑改进年龄估计的方法, 并通过分阶段联合训练年龄编辑网络 StarGAN 和年龄估计软阶段回归网络 (soft stagewise regression network, SSR-Net), 扩增适用于年龄估计的训练数据. 实验证明, 在非受限条件下, 该方法取得了年龄估计较好的结果.

关键词: 年龄编辑, 年龄估计, 生成对抗网络, 数据扩增

Abstract:

As an emerging biometric identification technology, face age estimation is a classic learning problem in computer vision. Based on the powerful data generation ability of a generative adversarial network (GAN), a method to improve age estimation by using age editing is proposed. The training data suitable for age estimation were amplified by combining the training age editing network-StarGAN and the age estimation network-soft stagewise regression network (SSR-Net), in stages. Experimental results show that the method achieves the better age estimation results under unrestricted conditions.

Key words: age editing, age estimation, generative adversarial network (GAN), data amplification

中图分类号:

TP391.4

张辰昱, 徐树公, 黄剑波. 一种利用年龄编辑改进年龄估计的方法[J]. 上海大学学报(自然科学版), 2021, 27(1): 28-38.

ZHANG Chenyu, XU Shugong, HUANG Jianbo. Method for improving age estimation using age editing[J]. Journal of Shanghai University（Natural Science Edition）, 2021, 27(1): 28-38.

图/表 9

图1

图2

图3

图4

表1

表2

表3

表4

图5

参考文献 22

[1]	Yousaf A, Khan M J, Khan M J, et al. A robust and efficient convolutional deep learning framework for age-invariant face recognition[J]. Expert Systems, 2020,37(3):e12503.
[2]	Chen Y, Zhou X S, Huang T S. One-class SVM for learning in image retrieval[C] // International Conference on Image Processing. 2001. DOI: 10.1109/ICIP.2001.958946.
[3]	Zhu S C, Yuille A L. Region competition: unifying snakes, region growing, and Bayes/MDL for multiband image segmentation[J]. IEEE Transactions on Pattern Analysis $\&$ Machine Intelligence, 1996,18(9):884-900.
[4]	Zhang K, Wang X S, Guo Y R, et al. Survey of deep learning methods for face age estimation[J]. Journal of Image and Graphics, 2019,24(8):1215-1230.
[5]	Mirza M, Osindero S. Conditional generative adversarial nets [EB/OL]. (2014-11-06) [2020-03-23]. https://arxiv.org/pdf/1411.1784v1.pdf.
[6]	Levi G, Hassner T. Age and gender classification using convolutional neural networks[C] // IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). 2015. DOI: 10.1109/CVPRW.2015.7301352.
[7]	Rothe R, Timofte R, van Gool L. Deep expectation of real and apparent age from a single image without facial landmarks[J]. International Journal of Computer Vision, 2016,126:144-157. doi: 10.1007/s11263-016-0940-3
[8]	Zhang Y, Liu L, Li C, et al. Quantifying facial age by posterior of age comparisons [EB/OL]. (2017-10-13) [2020-03-23]. https://arxiv.org/abs/1708.09687v2.
[9]	Yang T Y, Huang Y H, Lin Y Y, et al. SSR-Net: a compact soft stagewise regression network for age estimation[C] // International Joint Conference on Artificial Intelligence (IJCAI). 2018: 1078-1084.
[10]	Zhang C, Liu S, Xu X, et al. C3AE: exploring the limits of compact model for age estimation [EB/OL]. ( 2019-04-11) [2020-03-23]. https://arxiv.org/abs/1904.05059.
[11]	Schroff F, Kalenichenko D, Philbin J. FaceNet: a unified embedding for face recognition and clustering[C] // IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2015. DOI: 10.1109/CVPR.2015.7298682.
[12]	Niu Z X, Zhou M, Wang L, et al. Ordinal regression with multiple output CNN for age estimation[C] // IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2016. DOI: 10.1109/CVPR.2016.52.
[13]	Isola P, Zhu J Y, Zhou T H, et al. Image-to-image translation with conditional adversarial networks [EB/OL]. (2018-11-26) [2020-03-23]. https://arxiv.org/abs/1611.07004.
[14]	Zhu J Y, Park T, Isola P, et al. Unpaired image-to-image translation using cycle-consistent adversarial networks[J]. IEEE International Conference on Computer Vision (ICCV). 2017. DOI: 10.1109/ICCV.2017.244.
[15]	Karras T, Aila T, Laine S, et al. Progressive growing of GANs for improved quality, stability, and variation[EB/OL]. (2018-02-26) [2020-03-23]. https://arxiv.1710.10196.
[16]	Liu Z, Luo P, Wang X, et al. Deep learning face attributes in the wild[C] // IEEE International Conference on Computer Vision (ICCV). 2015: 3730-3738.
[17]	Choi, Y J, Choi M J, Kim, M Y, et al. StarGAN: unified generative adversarial networks for multi-domain image-to-image translation[C] // IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2018. DOI: 10.1109/CVPR.2018.00916.
[18]	Yin, X Yu, X Sohn K, et al. Feature transfer learning for deep face recognition with long-tail data [EB/OL]. (2019-08-19) [2020-03-23]. https://arxiv.org/abs/1803.09014.
[19]	Gulrajani I, Ahmed F, Arjovsky M, et al. Improved training of wasserstein gans[C] // Advances in Neural Information Processing Systems. 2017: 5769-5779.
[20]	Eidinger E, Enbar R, Hassner T. Age and gender estimation of unfiltered faces[J]. IEEE Transactions on Information Forensics and Security, 2014,9(12):2170-2179.
[21]	Zhang K, Gao C, Guo L R, et al. Age group and gender estimation in the wild with deep RoR architecture[J]. IEEE Access, 2017,5:22492-22503.
[22]	Zhang K, Liu N, Yuan X F, et al. Fine-grained age group classification in the wild[C] // Proceedings of the 24th International Conference on Pattern Recognition. 2018. DOI: 10.1109/ICPR.2018.8545333.

一种利用年龄编辑改进年龄估计的方法

Method for improving age estimation using age editing

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

图/表 9

参考文献 22

相关文章 1

编辑推荐

Metrics

本文评价