[1]TIAN Qing,MAO Junxiang,CAO Meng.Research on the coupled-relationships self-learning human facial age estimation[J].CAAI Transactions on Intelligent Systems,2022,17(2):257-265.[doi:10.11992/tis.202101020]
Copy

Research on the coupled-relationships self-learning human facial age estimation

CAAI Transactions on Intelligent Systems[ISSN 1673-4785/CN 23-1538/TP] Volume: 17 Number of periods: 2022 2 Page number: 257-265 Column: 学术论文—机器学习 Public date: 2022-03-05
Title:
Research on the coupled-relationships self-learning human facial age estimation
Author(s):
TIAN Qing1; 2;  MAO Junxiang1; 3;  CAO Meng1
1. School of Computer and Software, Nanjing University of Information Science & Technology, Nanjing 210044, China;
2. Engineering Research Center of Digital Forensics, Ministry of Education, Nanjing University of Information Science & Technology, Nanjing 210044, China;
3. School of Computer Science and Engineering, Southeast University, Nanjing 210096, China
Keywords:
human facial age estimation; coupled relationship; feature relationship; coding relationship; input-output relationship; relationships self-learning; alternating optimization; deep architecture
CLC:
TP391
DOI:
10.11992/tis.202101020
Abstract:
Although a variety of human facial age estimation (AE) potential relationship-exploiting works have been proposed, most of them are limited to exploiting one-sided potential relationships, rarely considering multi-sided coupled relationships. Therefore, we propose a coupled relationships self-learning age estimation model—CRSAE, which can exploit three kinds of potential relationships, i.e., input feature relationships, output coding relationships, and input-output relationships, to improve the generalization of AE models. Specifically, the row and column covariance matrices of the projection matrix are modeled to construct the regularizer of the feature and coding relationships. The input-output relationships are then exploited through a structure matrix. To solve our proposed CRSAE model effectively, we present an alternating optimization algorithm. In view of the highly nonlinear characteristics of facial features, we also extend our proposed model with a deep architecture to further enhance its generalization. Finally, evaluation experiments are conducted to demonstrate the effectiveness and superiority of our proposed methods on multiple human facial datasets.
References:
[1] WU Yongdong, WEI Zhuo, DENG R H. Attribute-based access to scalable media in cloud-assisted content sharing networks[J]. IEEE transactions on multimedia, 2013, 15(4): 778–788.
[2] LINOFF G S, BERRY M J A. Data mining techniques: for marketing, sales, and customer relationship management[M]. 3rd ed. New York: Wiley, 2011: 45-49.
[3] SHASHIDHAR K K, MANJAIAH D H. Electronic Customer Relationship Management (e-CRM): Data Integration for Technical Institutions[C]//2012 International Conference on Internet Computing and Information Communications.[S.1.], 2014: 169-178.
[4] ALASHKAR T, JIANG Songyao, FU Yun. Rule-based facial makeup recommendation system[C]//Proceedings of 2017 12th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2017). Washington, USA, 2017: 325-330.
[5] LU Jiwen, LIONG V E, ZHOU Jie. Cost-sensitive local binary feature learning for facial age estimation[J]. IEEE transactions on image processing, 2015, 24(12): 5356–5368.
[6] LI Changsheng, LIU Qingshan, LIU Jing, et al. Learning ordinal discriminative features for age estimation[C]//Proceedings of 2012 IEEE Conference on Computer Vision and Pattern Recognition. Providence, USA, 2012: 2570-2577.
[7] TIAN Qing, ZHANG Wenqiang, WANG Liping, et al. Robust ordinal regression induced by lp-centroid[J]. Neurocomputing, 2018, 313: 184–195.
[8] NIU Zhenxing, ZHOU Mo, WANG Le, et al. Ordinal regression with multiple output CNN for age estimation[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas, USA, 2016: 4920-4928.
[9] LIU Hao, LU Jiwen, FENG Jianjiang, et al. Ordinal deep learning for facial age estimation[J]. IEEE transactions on circuits and systems for video technology, 2019, 29(2): 486–501.
[10] GENG Xin, YIN Chao, ZHOU Zhihua. Facial age estimation by learning from label distributions[J]. IEEE transactions on pattern analysis and machine intelligence, 2013, 35(10): 2401–2412.
[11] YANG Xu, GAO Binbin, XING Chao, et al. Deep label distribution learning for apparent age estimation[C]//2015 IEEE International Conference on Computer Vision Workshops. Santiago, Chile, 2015: 344-350.
[12] HUO Zengwei, YANG Xu, XING Chao, et al. Deep age distribution learning for apparent age estimation[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition Workshops. Las Vegas, USA, 2016: 722-729.
[13] GAO Binbin, ZHOU Hongyu, WU Jianxin, et al. Age Estimation Using Expectation of Label Distribution Learning[C]//Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence. Stockholm, Sweden, 2018: 712-718.
[14] SHEN Wei, GUO Yilu, WANG Yan, et al. Deep regression forests for age estimation[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City, USA, 2018, 2304-2313.
[15] TIAN Qing, CHEN Songcan. Cumulative attribute relation regularization learning for human age estimation[J]. Neurocomputing, 2015, 165: 456–467.
[16] TIAN Qing, CAO Meng, CHEN Songcan, et al. Relationships self-learning based gender-aware age estimation[J]. Neural processing letters, 2019, 50(3): 2141–2160.
[17] CHEN Ke, GONG Shaogang, XIANG Tao, et al. Cumulative attribute space for age and crowd density estimation[C]//2013 IEEE Conference on Computer Vision and Pattern Recognition. Portland, USA, 2013: 2467-2474.
[18] BOCKLET T, MAIER A, BAUER J G, et al. Age and gender recognition for telephone applications based on gmm supervectors and support vector machines[C]//2008 IEEE International Conference on Acoustics, Speech and Signal Processing. Las Vegas, USA, 2008: 1605-1608.
[19] HE Yunhui. Real-Time Nonlinear facial feature extraction using cholesky decomposition and QR decomposition for face recognition[C]//2009 International Conference on Electronic Computer Technology. Macau, China, 2009: 306-310.
[20] COATES A, NG A Y. The importance of encoding versus training with sparse coding and vector quantization[C]//Proceedings of the 28th International Conference on Machine Learning. Washington, USA, 2011: 921-928.
[21] ZHANG Yu, YEUNG D Y. A convex formulation for learning task relationships in multi-task learning[C]//Proceddings of the Twenty-Sixth Conference on Uncertainty in Artificial Intelligence. Catalina Island, USA, 2010: 733-742.
[22] RECHT B, FAZEL M, PARRILO P A. Guaranteed minimum-rank solutions of linear matrix equations via nuclear norm minimization[J]. SIAM review, 2010, 52(3): 471–501.
[23] LIU Guangcan, LIN Zhouchen, YAN Shuicheng, et al. Robust recovery of subspace structures by low-rank representation[J]. IEEE transactions on pattern analysis and machine intelligence, 2013, 35(1): 171–184.
[24] ZHONG Xiaowei, XU Linli, LI Yitan, et al. A nonconvex relaxation approach for rank minimization problems[C]//Proceedings of the Twenty-Ninth AAAI Conference on Artificial Intelligence. Austin, USA, 2015: 1980-1986.
[25] NIE Feiping, HUANG Heng, DING C. Low-rank matrix recovery via efficient schatten p-norm minimization[C]//Proceedings of the Twenty-Sixth AAAI Conference on Artificial Intelligence. New York, USA, 2012: 655-661.
[26] GAO Guangwei, YANG Jian, JING Xiaoyuan, et al. Learning robust and discriminative low-rank representations for face recognition with occlusion[J]. Pattern recognition, 2017, 66: 129–143.
[27] MONTILLO A, LING Haibin. Age regression from faces using random forests[C]//Proceedings of 2009 16th IEEE International Conference on Image Processing (ICIP). Cairo, Egypt, 2009: 2465-2468.
[28] RICANEK K, TESAFAYE T. MORPH: a longitudinal image database of normal adult age-progression[C]//Proceedings of 7th International Conference on Automatic Face and Gesture Recognition (FGR06). Southampton, UK, 2006: 341-345.
[29] CHEN B C, CHEN Chusong, HSU W H. Cross-age reference coding for age-invariant face recognition and retrieval[C]//Proceedings of 13th European Conference. Zurich, Switzerland, 2014: 768-783.
[30] COOTES T F, EDWARDS G J, TAYLOR C J. Active appearance models[J]. IEEE transactions on pattern analysis and machine intelligence, 2001, 23(6): 681–685.
[31] GUO Guodong, MU Guowang, FU Yun, et al. Human age estimation using bio-inspired features[C]//Proceedings of 2009 IEEE Conference on Computer Vision and Pattern Recognition. Miami, USA, 2009: 112-119.
[32] FERNáNDEZ C, HUERTA I, PRATI A. A comparative evaluation of regression learning algorithms for facial age estimation[C]//Proceedings of International Workshop on Face and Facial Expression Recognition from Real World Videos 2014. Stockholm, Sweden, 2014: 133-144.
[33] LI Kai, XING Junliang, HU Weiming, et al. D2C: deep cumulatively and comparatively learning for human age estimation[J]. Pattern recognition, 2017, 66: 95–105.
[34] ZHANG Chao, LIU Shuaicheng, XU Xun, et al. C3AE: exploring the limits of compact model for age estimation[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Long Beach, USA, 2019: 12579-12588.
[35] LIM K, SHIN N H, LEE Y Y, et al. Order learning and its application to age estimation[C]//8th International Conference on Learning Representations. Addis Ababa, Ethiopia, 2020.
Similar References:

Memo

-

Last Update: 1900-01-01

Copyright © CAAI Transactions on Intelligent Systems