Skip to main content
SpringerLink
Log in

A new discriminative sparse parameter classifier with iterative removal for face recognition

基于迭代剔除稀疏表示的人脸识别方法

  • Published:
Journal of Central South University Aims and scope Submit manuscript

Abstract

Face recognition has been widely used and developed rapidly in recent years. The methods based on sparse representation have made great breakthroughs, and collaborative representation-based classification (CRC) is the typical representative. However, CRC cannot distinguish similar samples well, leading to a wrong classification easily. As an improved method based on CRC, the two-phase test sample sparse representation (TPTSSR) removes the samples that make little contribution to the representation of the testing sample. Nevertheless, only one removal is not sufficient, since some useless samples may still be retained, along with some useful samples maybe being removed randomly. In this work, a novel classifier, called discriminative sparse parameter (DSP) classifier with iterative removal, is proposed for face recognition. The proposed DSP classifier utilizes sparse parameter to measure the representation ability of training samples straight-forward. Moreover, to avoid some useful samples being removed randomly with only one removal, DSP classifier removes most uncorrelated samples gradually with iterations. Extensive experiments on different typical poses, expressions and noisy face datasets are conducted to assess the performance of the proposed DSP classifier. The experimental results demonstrate that DSP classifier achieves a better recognition rate than the well-known SRC, CRC, RRC, RCR, SRMVS, RFSR and TPTSSR classifiers for face recognition in various situations.

摘要

近年来, 人脸识别得到了广泛应用和快速发展. 以协作表示分类(CRC)算法为代表的基于稀疏 表示的分类方法取得了重大突破. 然而, CRC因不能有效区分相似样本, 从而非常容易分类错误. 作 为CRC的改进方法, 两阶段测试样本稀疏表示方法(TPTSSR)剔除了那些对描述测试样本贡献不大的 训练样本. 但在TPTSSR中, 仅进行一次剔除操作是远远不够的, 因为某些无用样本仍可能被保留下 来, 同时那些有用样本可能会被随机删除. 本文提出一种新的基于迭代剔除判别稀疏表示(DSP)方法, DSP 利用稀疏参数直接度量训练样本的表示能力, 同时通过多次迭代把大部分不相关的样本逐步剔 除, 从而避免误删有效样本. 再通过在不同姿态、表情和噪声下的代表性人脸数据集进行实验, 以评 估DSP 的性能. 大量实验结果表明, 在大部分情况下DSP 比典型的SRC、CRC、RRC、RCR、 SRMVS、RFSR和TPTSSR等算法具有更好的人脸识别效果.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  1. CAI Pei, QUAN Hui-min. Face anti-spoofing algorithm combined with CNN and brightness equalization [J]. Journal of Central South University, 2021, 28(1): 194–204. DOI: https://doi.org/10.1007/s11771-021-4596-y.

    Article  Google Scholar 

  2. TIAN Chun-wei, XU Yong, LI Zuo-yong, et al. Attention-guided CNN for image denoising [J]. Neural Networks, 2020, 124: 117–129. DOI: https://doi.org/10.1016/j.neunet.2019.12.024.

    Article  Google Scholar 

  3. MANJU V, MADHUMATHI S. Improving net banking security with face recognition based bio-metric verification [J]. International Journal of Scientific Research in Computer Science, Engineering and Information Technology, 2019, 5(3): 82–91. DOI: https://doi.org/10.32628/cseit195335.

    Article  Google Scholar 

  4. YALAGI P S, MANE P V. Smart library automation using face recognition [J]. Journal of Physics: Conference Series, 2021, 1854(1): 012041. DOI: https://doi.org/10.1088/1742-6596/1854/1/012041.

    Google Scholar 

  5. MEHRASA N, ALI A, HOMAYUN M. A supervised multimanifold method with locality preserving for face recognition using single sample per person [J]. Journal of Central South University, 2017, 24(12): 2853–2861. DOI: https://doi.org/10.1007/s11771-017-3700-9.

    Article  Google Scholar 

  6. KASAEI S H, LOPES L S, TOME A M. Local-LDA: Open-ended learning of latent topics for 3D object recognition [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020, 42(10): 2567–2580. DOI: https://doi.org/10.1109/TPAMI.2019.2926459.

    Article  Google Scholar 

  7. HEMALATHA C, LOGASHANMUGAM E. Analysis of different M-band wavelet filters for face recognition using nearest neighbor classifier [J]. Indonesian Journal of Electrical Engineering and Computer Science, 2018, 12(2): 824–831. DOI: https://doi.org/10.11591/ijeecs.v12.i2.pp824-831.

    Article  Google Scholar 

  8. WANG Y G. Consistency and convergence rate for nearest subspace classifier [J]. Information and Inference, 2016: iaw006. DOI: https://doi.org/10.1093/imaiai/iaw006.

  9. DING Yu-hua, LIU Fan, RUI Ting, et al. Patch based semi-supervised linear regression for face recognition [J]. KSII Transactions on Internet and Information Systems (TIIS), 2019, 13(8): 3962–3980. DOI: https://doi.org/10.3837/tiis.2019.08.008.

    Google Scholar 

  10. ZHOU Si-wang, HE Yan, LIU Yong-he, et al. Multi-channel deep networks for block-based image compressive sensing [J]. IEEE Transactions on Multimedia, 2021, 23: 2627–2640. DOI: https://doi.org/10.1109/TMM.2020.3014561.

    Article  Google Scholar 

  11. ZHOU Si-wang, HE Yan, XIANG Shu-zhen, et al. Region-based compressive networked storage with lazy encoding [J]. IEEE Transactions on Parallel and Distributed Systems, 2019, 30(6): 1390–1402. DOI: https://doi.org/10.1109/TPDS.2018.2883550.

    Article  Google Scholar 

  12. ZHOU Si-wang, CHEN Zhi-neng, ZHONG Qian, et al. Block compressed sampling of image signals by saliency based adaptive partitioning [J]. Multimedia Tools and Applications, 2019, 78(1): 537–553. DOI: https://doi.org/10.1007/s11042-017-5249-x.

    Article  Google Scholar 

  13. WRIGHT J, YANG A Y, GANESH A, et al. Robust face recognition via sparse representation [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2009, 31(2): 210–227. DOI: https://doi.org/10.1109/TPAMI.2008.79.

    Article  Google Scholar 

  14. ZHANG Lei, YANG Meng, FENG Xiang-chu. Sparse representation or collaborative representation: Which helps face recognition? [C]// 2011 International Conference on Computer Vision. Barcelona, Spain: IEEE, 2011: 471–478. DOI: https://doi.org/10.1109/ICCV.2011.6126277.

    Google Scholar 

  15. ZHENG Zhi-chao, SUN Huai-jiang, ZHOU Ying. Multiple discriminant analysis for collaborative representation-based classification [J]. Pattern Recognition, 2021, 112: 107819. DOI: https://doi.org/10.1016/j.patcog.2021.107819.

    Article  Google Scholar 

  16. XU Yong, ZHANG David, YANG Jian, et al. A two-phase test sample sparse representation method for use with face recognition [J]. IEEE Transactions on Circuits and Systems for Video Technology, 2011, 21(9): 1255–1262. DOI: https://doi.org/10.1109/TCSVT.2011.2138790.

    Article  MathSciNet  Google Scholar 

  17. LI Wen, YANG Jun, MA Yi-de. Target recognition of synthetic aperture radar images based on two-phase sparse representation [J]. Journal of Sensors, 2020, 2020: 2032645. DOI: https://doi.org/10.1155/2020/2032645.

    Google Scholar 

  18. TANG De-yan, ZHOU Si-wang, YANG Wen-juan, et al. A two-phase representation based face recognition method with ‘random-filtering’ virtual samples [C]//2017 International Joint Conference on Neural Networks (IJCNN). Anchorage, AK, USA: IEEE, 2017: 101–107. DOI: https://doi.org/10.1109/IJCNN.2017.7965842.

    Google Scholar 

  19. TANG De-yan, ZHU Ning-bo, YU Fu, et al. A novel sparse representation method based on virtual samples for face recognition [J]. Neural Computing and Applications, 2014, 24(3, 4): 513–519. DOI: https://doi.org/10.1007/s00521-012-1252-3.

    Article  Google Scholar 

  20. TANG De-yan, ZHOU Si-wang, YANG Wen-juan. Random-filtering based sparse representation parallel face recognition [J]. Multimedia Tools and Applications, 2019, 78(2): 1419–1439. DOI: https://doi.org/10.1007/s11042-018-6166-3.

    Article  Google Scholar 

  21. YANG Meng, ZHANG Lei, YANG Jian, et al. Regularized robust coding for face recognition [J]. IEEE Transactions on Image Processing, 2013, 22(5): 1753–1766. DOI: https://doi.org/10.1109/TIP.2012.2235849.

    Article  MathSciNet  Google Scholar 

  22. YANG Meng, ZHANG Lei, ZHANG D, et al. Relaxed collaborative representation for pattern classification [C]// 2012 IEEE Conference on Computer Vision and Pattern Recognition. Providence, RI, USA: IEEE, 2012: 2224–2231. DOI: https://doi.org/10.1109/CVPR.2012.6247931.

    Google Scholar 

  23. QIN Yong-bin, TIAN Chun-wei. Weighted feature space representation with kernel for image classification [J]. Arabian Journal for Science and Engineering, 2018, 43(12): 7113–7125. DOI: https://doi.org/10.1007/s13369-017-2952-x.

    Article  Google Scholar 

  24. TIAN Chun-wei, ZHANG Qi, SUN Guang-lu, et al. FFT consolidated sparse and collaborative representation for image classification [J]. Arabian Journal for Science and Engineering, 2018, 43(2): 741–758. DOI: https://doi.org/10.1007/s13369-017-2696-7.

    Article  Google Scholar 

  25. TIAN Chun-wei, SUN Guang-lu, ZHANG Qi, et al. Integrating sparse and collaborative representation classifications for image classification [J]. International Journal of Image and Graphics, 2017, 17(2): 1750007. DOI: https://doi.org/10.1142/s0219467817500073.

    Article  Google Scholar 

  26. Georgia tech face database [EB/OL]. [2021-03-18]. http://www.anefian.com/research/face_reco.Htm.

  27. MARTINEZ A M, BENAVENTE R. The AR face database [R]. Barcelona, Spain: Centre de Visio per Comp., Univ. Autonoma de Barcelona, CVC Tech, 1998.

    Google Scholar 

  28. The Olivetti and Oracle Research Laboratory. The ORL database of faces [EB/OL]. [2021-03-18]. http://www.cl.cam.ac.uk/research/dgt/attarchive/facedatabase.html.

Download references

Author information

Authors and Affiliations

  1. College of Computer Science and Electronic Engineering, Hunan University, Changsha, 410082, China

    De-yan Tang  (唐德燕), Si-wang Zhou  (周四望), Hao-wen Chen  (陈浩文) & Hui Tang  (唐晖)

  2. Library, Central South University, Changsha, 410083, China

    Meng-ru Luo  (罗孟儒)

Authors
  1. De-yan Tang  (唐德燕)
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Si-wang Zhou  (周四望)
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Meng-ru Luo  (罗孟儒)
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Hao-wen Chen  (陈浩文)
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Hui Tang  (唐晖)
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Meng-ru Luo  (罗孟儒).

Additional information

Foundation item

Project(2019JJ40047) supported by the Hunan Provincial Natural Science Foundation of China; Project(kq2014057) supported by the Changsha Municipal Natural Science Foundation, China

Contributors

The overarching research goals were developed by all the authors. TANG De-yan and ZHOU Si-wang provided the concept. TANG De-yan and LUO Meng-ru conducted the literature review and wrote the first draft of the manuscript. LUO Meng-ru analyzed the measured data. CHEN Hao-wen and TANG Hui edited the draft of manuscript. All authors replied to reviewers’ comments and revised the final version.

Conflict of interest

TANG De-yan, ZHOU Si-wang, LUO Meng-ru, CHEN Hao-wen, and TANG Hui declare that they have no conflict of interest.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Tang, Dy., Zhou, Sw., Luo, Mr. et al. A new discriminative sparse parameter classifier with iterative removal for face recognition. J. Cent. South Univ. 29, 1226–1238 (2022). https://doi.org/10.1007/s11771-022-4995-8

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11771-022-4995-8

Key words

关键词

Search

Navigation