Skip to main content
SpringerLink
Log in

A recognition–verification system for noisy faces based on an empirical mode decomposition with Green’s functions

  • Methodologies and Application
  • Published:
Soft Computing Aims and scope Submit manuscript

Abstract

Face recognition or verification remains a real challenge in the area of pattern recognition and image processing. The image acquisition process is a crucial step in which noise will inevitably be introduced, and in most cases this noise drastically decreases the accuracy of the classification rate of recognition systems, making them ineffective. This paper presents a novel approach to face recognition or verification, which increases the recognition rate in noisy environmental conditions. The latter is achieved by using the intrinsic face mode functions that result from applying a bi-dimensional empirical mode decomposition with Green’s functions in tension to noisy images. Each image is individually decomposed, and noisy modes are discarded or filtered during reconstruction. Then, the extracted modes are used for classification purposes with canonical classifiers such as vector support machines or k-nearest neighbor classifiers. Experimental results show that this method achieves very stable results, almost independently of the amount of noise added to the image, due to the ability of decomposition to capture the noise in the first mode. Classification results using noisy images are at the same level as other algorithms proposed for the same databases but working on clean images and therefore are better than those obtained using classic image filters in noisy images. Moreover, unlike most of the available algorithms, the algorithm proposed in this paper is based on the input data (without the need to adjust parameters), making it transparent to the user. Finally, the proposed new approach achieves good results independently of the type of noise, the level of noise and the type of the database, which is not possible with other classical methods requiring parameter adjustment.

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

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12

Similar content being viewed by others

References

  • Al-Baddai S, Al-Subari K, Tomé A, Volberg G, Hanslmayr S, Hammwöhner R, Lang E (2014) Bidimensional ensemble empirical mode decomposition of functional biomedical images taken during a contour integration task. Biomed Signal Process Control 13:218–236

    Article  Google Scholar 

  • Al-Baddai S, Al-Subari K, Tomé A, Solé-Casals J, Lang E (2016) A Green’s function-based bi-dimensional empirical mode decomposition. Inf Sci 348:305–321

    Article  Google Scholar 

  • Allwein EL, Schapire RE, Singer Y (2000) Reducing multiclass to binary: a unifying approach for margin classifiers. J Mach Learn Res 2:263–286

    MATH  Google Scholar 

  • Bhuiyan S, Adhami R, Khan J (2008) A novel approach of fast and adaptive bidimensional empirical mode decomposition. In: IEEE international conference on acoustics, speech and signal processing ICASSP, pp 1313 –1316. https://doi.org/10.1109/ICASSP.2008.4517859

  • Bhuiyan S, Khan J, Adhami NA-ORR (2009) Study of bidimensional empirical mode decomposition method for various radial basis function surface interpolators. In: International conference on machine learning and applications. IEEE, pp 18–24

  • Bremner D, Demaine E, Erickson J, Iacono J, Langerman S, Morin P, Toussaint G (2005) Output sensitive algorithms for computing nearest neighbor decision boundaries. Discrete Comput Geom 33:593–604

    Article  MathSciNet  Google Scholar 

  • Brown RG, Hwang PYC (1996) Introduction to random signals and applied Kalman filtering, 3rd edn. Wiley, New York

    MATH  Google Scholar 

  • Burgers CJC (1998) A tutorial on support vector machines for pattern recognition. Data Min Knowl Discov 2:121–167

    Article  Google Scholar 

  • Chang KM (2010) Ensemble empirical mode decomposition for high frequency ECG noise reduction. Biomed Tech/Biomed Eng 55:193–201

    Article  Google Scholar 

  • Cover T, Hart P (1967) Nearest-neighbor pattern classification. IEEE Trans Inf Theory 13:21–27

    Article  Google Scholar 

  • Damerval C, Meignen S, Perrier V (2005) A fast algorithm for bidimensional EMD. IEEE Signal Process Lett 12(10):701–704

    Article  Google Scholar 

  • Deng W, Zhao H, Zou L et al (2017a) A novel collaborative optimization algorithm in solving complex optimization problems. Soft Comput 21:4387. https://doi.org/10.1007/s00500-016-2071-8

    Article  Google Scholar 

  • Deng W, Zhao H, Yang X, Xiong J, Sun M, Li B (2017b) Study on an improved adaptive PSO algorithm for solving multi-objective gate assignment. Appl Soft Comput 59:288–302. https://doi.org/10.1016/j.asoc.2017.06.004

    Article  Google Scholar 

  • Deng W, Xu J, Zhao H (2019a) An improved ant colony optimization algorithm based on hybrid strategies for scheduling problem. IEEE Access 7:20281–20292. https://doi.org/10.1109/ACCESS.2019.2897580

    Article  Google Scholar 

  • Deng W, Yao R, Zhao H et al (2019b) A novel intelligent diagnosis method using optimal LS-SVM with improved PSO algorithm. Soft Comput 23:2445. https://doi.org/10.1007/s00500-017-2940-9

    Article  Google Scholar 

  • Devroye L, Györfi L, Lugosi G (2013) A probabilistic theory of pattern recognition, vol 31. Springer, Berlin

    MATH  Google Scholar 

  • Dinarès-Ferran J, Ortner R, Guger C, Solé-Casals J (2018) A new method to generate artificial frames using the empirical mode decomposition for an EEG-based motor imagery BCI. Front Neurosci. https://doi.org/10.3389/fnins.2018.00308

    Article  Google Scholar 

  • Ding Y, Cheng Y, Cheng X, Li B (2017) Noise-resistant network: a deep-learning method for face recognition under noise. EURASIP J Image Video Process. https://doi.org/10.1186/s13640-017-0188-z

    Article  Google Scholar 

  • Duda RO, Hart PE (1973) Pattern classification and scene analysis. Wiley, New York

    MATH  Google Scholar 

  • Fàbregas J, Faundez-Zanuy M (2009) Biometric recognition performing in a bioinspired system. Cogn Comput 1(3):257–267. https://doi.org/10.1007/s12559-009-9018-7

    Article  MATH  Google Scholar 

  • Gallego-Jutglà E, Solé-Casals J, Rutkowski TM, Cichocki A (2011) Application of multivariate empirical mode decomposition for cleaning eye blinks artifacts from EEG signals. In: Proceedings of international conference on neural computation theory and applications

  • Gilles J (2013) Empirical wavelet transform. IEEE Trans Signal Process 61(16):3999–4010

    Article  MathSciNet  Google Scholar 

  • Gonzalez R (2002) Digital image processing, 3rd edn. Prentice Hall, Englewood Cliffs

    Google Scholar 

  • Guo T, Zhang L, Tan X (2017) Neuron pruning-based discriminative extreme learning machine for pattern classification. Cogn Comput 9:581–595. https://doi.org/10.1007/s12559-017-9474-4

    Article  Google Scholar 

  • He B, Xu D, Nian R, Heeswijk MV, Yu Q, Miche Y, Lenasse A (2014) Fast face recognition via sparse coding and extreme learning machine. Cogn Comput 6(2):264–277. https://doi.org/10.1007/s12559-013-9224-1

    Article  Google Scholar 

  • Hsu C-W, Lin C-J (2002) A comparison of methods for multi-class support vector machines. IEEE Trans Neural Netw 13:414–425

    Article  Google Scholar 

  • Hu H, Gu J (2016) Multi-manifolds discriminative canonical correlation analysis for image set-based face recognition. Cogn Comput 8(5):900–909. https://doi.org/10.1007/s12559-016-9403-y

    Article  Google Scholar 

  • Huang NE, Shen Z, Long SR, Wu ML, Shih HH, Zheng Q, Yen NC, Tung CC, Liu HH (1998) The empirical mode decomposition and Hilbert spectrum for nonlinear and non-stationary time series analysis. Proc R Soc Lond A 454:903–995

    Article  MathSciNet  Google Scholar 

  • Humeau-Heurtier A, Mahe G, Abraham P (2015) Multi-dimensional complete ensemble empirical mode decomposition with adaptive noise applied to laser speckle contrast images. IEEE Trans Med Imaging PP(99):1

    Google Scholar 

  • Iancu PCC, Costache G (2007) A review of face recognition techniques for in-camera applications. international symposium on signals. Circuits Syst 1:1–4

    Google Scholar 

  • Jafri R, Arabnia HR (2009) A survey of face recognition techniques. J Inf Process Syst 5(2):41–68

    Article  Google Scholar 

  • Jain AK (1989) Fundamentals of digital image processing. Prentice Hall, Englewood Cliffs, pp 150–153

    MATH  Google Scholar 

  • Linderhed A (2002) 2-D empirical mode decompositions in the spirit of image compression. In: Wavelet and independent component analysis applications IX, proceedings of SPIE, vol 4738, pp 1–8

  • Liu Z, Peng S (2005) Boundary processing of bidimensional EMD using texture synthesis. IEEE Signal Process Lett 12:33–36

    Article  Google Scholar 

  • Liu X, Tanaka M, Okutomi M (2013) Single-image noise level estimation for blind denoising. IEEE Trans Image Process 22:5226–5237

    Article  Google Scholar 

  • Liu Z, Wang H, Peng S (2004) Texture classification through directional empirical mode decomposition. In: Proceedings of 17th IEEE international conference on pattern recognition (ICPR ’04), pp 803–806

  • Lyons MJ, Akemastu Sh, Kamachi M, Gyoba J (1998) Coding facial expressions with gabor wavelets. In: 3rd IEEE international conference on automatic face and gesture recognition, pp 200–205

  • Maiorana E, Solé-Casals J, Campisi P (2016) EEG signal preprocessing for biometric recognition. Mach Vis Appl 27:1351. https://doi.org/10.1007/s00138-016-0804-4

    Article  Google Scholar 

  • Mi J-X, Li C, Li C, Liu T, Liu Y (2016) A human visual experience-inspired similarity metric for face recognition under occlusion. Cogn Comput 8:818–827. https://doi.org/10.1007/s12559-016-9420-x

    Article  Google Scholar 

  • Min-Sung K, Rodriguez-Marek E, Fischer T (2010) A new two dimensional empirical mode decomposition for images using inpainting. In: IEEE 10th international conference on signal processing (ICSP), pp 13–16

  • Nunes J, Deléchelle E (2009) Empirical mode decomposition: applications on signal and image processing. Adv Adapt Data Anal 1:125–75

    Article  Google Scholar 

  • Nunes J, Bouaoune Y, Delechelle E, Niang O, Bunel P (2003) Image analysis by bidimensional empirical mode decomposition. Image Vis Comput 21(12):1019–1026

    Article  Google Scholar 

  • Nunes J, Guyot S, Deléchelle E (2005) Texture analysis based on local analysis of the bidimensional empirical mode decomposition. Mach Vis Appl 16:177–188

    Article  Google Scholar 

  • Oravec M, Mazanec J, Pavlovicova J, Eiben P, Lehocki F (2010) Face recognition in ideal and noisy conditions using support vector machines, PCA and IDA, Ch. 8. https://doi.org/10.5772/8943

    Chapter  Google Scholar 

  • Pennebaker B, William J, Mitchell J (1993) JPEG: still image data compression standard. Van Nostrand Reinhold, New York

    Google Scholar 

  • Rehman N, Park C, Huang NE, Mandic DP (2013) EMD via MEMD: multivariate noise-aided computation of standard EMD. Adv Adapt Data Anal 5(2):1–25

    Article  MathSciNet  Google Scholar 

  • Rilling G, Flandrin P, Goncalves P, Lilly JM (2007) Bivariate empirical mode decomposition. IEEE Signal Process Lett 14:936–939

    Article  Google Scholar 

  • Schölkopf B, Smola AJ (2002) Learning with kernels. The MIT Press, Cambridge

    MATH  Google Scholar 

  • Tomasi C, Manduchi R (1998) Bilateral filtering for gray and color images. In: Proceedings of IEEE international conference on computer vision, pp 836–846

  • Torres ME, Colominas MA, Schlotthauer G, Flandrin P (2011) A complete ensemble empirical mode decomposition with adaptive noise. In: IEEE international conference on acoustics, speech and signal processing (ICASSP), pp 4144–4147

  • Tukey JW (1977) Exploratory data analysis. Addison Wesley, Reading

    MATH  Google Scholar 

  • Wessel P (2009) A general-purpose Green’s function-based interpolator. Comput Geosci 35(6):1247–1254

    Article  Google Scholar 

  • Wessel P, Bercovici D (1998) Interpolation with splines in tension: a Green’s function approach. Math Geol 30(1):77–93

    Article  Google Scholar 

  • Woodward JD, Orlans NM, Higgins PT (2003) Biometrics. McGraw-Hill, New York

    Google Scholar 

  • Wright J, Yang A, Ganesh A, Sastry S, Ma Y (2009) Robust face recognition via sparse representation. IEEE Trans Pattern Anal Mach Intell 31(2):210–227

    Article  Google Scholar 

  • Wu Z, Huang NE, Chen X (2009) The multidimensional ensemble empirical mode decomposition method. Adv Adapt Data Anal 1:339–372

    Article  MathSciNet  Google Scholar 

  • Xiao Q (2007) Technology review—biometrics-technology, application, challenge, and computational intelligence solutions. IEEE Comput Intell Mag 2:5–25

    Article  Google Scholar 

  • Xiong C-Z, Xu JY, Zou J-C, Qi D-X (2006) Texture classification based on EMD and FFT. J Zhejiang Univ Sci A 7:1516–1521. https://doi.org/10.1631/jzus.2006.A1516

    Article  MATH  Google Scholar 

  • Yang Z, He X, Xiong W, Nie X (2016) Face recognition under varying illumination using green’s function based bidimensional empirical mode decomposition and gradient faces. In: ITM Web of Conferences 7,

    Article  Google Scholar 

  • Zhang Z, Duan F, Solé-Casals J, Dinarès-Ferran J, Cichocki A, Yang Z et al (2019) A novel deep learning approach with data augmentation to classify motor imagery signals. IEEE Access 7:15945–15954. https://doi.org/10.1109/ACCESS.2019.2895133

    Article  Google Scholar 

  • Zhao H, Sun M, Deng W, Yang X (2017) A new feature extraction method based on EEMD and multi-scale fuzzy entropy for motor bearing. Entropy 19:14

    Article  Google Scholar 

  • Zhao H, Yao R, Xu L, Yuan Y, Li G, Deng W (2018) Study on a novel fault damage degree identification method using high-order differential mathematical morphology gradient spectrum entropy. Entropy 20:682

    Article  Google Scholar 

Download references

Acknowledgements

The authors would like to thank anonymous reviewers for their detailed and helpful comments to the manuscript. Support by the DAAD, Acciones Integradas Hispano - Alemanas, and by the Ministerio de Economía y Competividad under the Grant TEC2016-77791-C4-2-R, is gratefully acknowledged.

Author information

Author notes

  1. Saad Al-Baddai and Jordi Solé-Casals have contributed equally to this work.

Authors and Affiliations

  1. CIML Lab, Department of Biophysics, University of Regensburg, 93040, Regensburg, Germany

    Saad Al-Baddai, Karema Al-Subari & Elmar Wolfgang Lang

  2. Chair of Information Sciences, University of Regensburg, 93040, Regensburg, Germany

    Saad Al-Baddai, Karema Al-Subari & Bernd Ludwig

  3. Infineon Technologies AG, Automation and Equipment Technology, 93049, Regensburg, Germany

    Saad Al-Baddai

  4. Data and Signal Processing Research Group, University of Vic - Central University of Catalonia, 08500, Vic, Catalonia, Spain

    Pere Marti-Puig, Esteve Gallego-Jutglà & Jordi Solé-Casals

  5. DETI - IEETA, Universidade de Aveiro, 3810-193, Aveiro, Portugal

    Ana Maria Tomé

  6. Tensor Learning Unit, RIKEN Center for Advanced Intelligence Project, Chuo-ku, Tokyo, 103-0027, Japan

    Jordi Solé-Casals

Authors
  1. Saad Al-Baddai
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Pere Marti-Puig
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Esteve Gallego-Jutglà
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Karema Al-Subari
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Ana Maria Tomé
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Bernd Ludwig
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Elmar Wolfgang Lang
    View author publications

    You can also search for this author in PubMed Google Scholar

  8. Jordi Solé-Casals
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Jordi Solé-Casals.

Ethics declarations

Conflict of interest

All authors declare that they have no conflict of interest.

Human and animal rights

This article does not contain any studies with human participants or animals performed by any of the authors.

Informed consent

Informed consent was not required as no humans or animals were involved.

Additional information

Communicated by V. Loia.

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Al-Baddai, S., Marti-Puig, P., Gallego-Jutglà, E. et al. A recognition–verification system for noisy faces based on an empirical mode decomposition with Green’s functions. Soft Comput 24, 3809–3827 (2020). https://doi.org/10.1007/s00500-019-04150-9

Download citation

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00500-019-04150-9

Keywords

Search

Navigation