Skip to main content
SpringerLink
Log in

Tensor-Based Subspace Learning for Multi-pose Face Synthesis

  • Chapter
Subspace Methods for Pattern Recognition in Intelligent Environment

Part of the book series: Studies in Computational Intelligence ((SCI,volume 552))

  • 1073 Accesses

Abstract

Facial pose synthesis is applied to generatemuch required information for several applications, such as public security, facial cosmetology, etc. How to synthesize facial pose images from one image accurately without spatial information is still a challenging problem. In this chapter we propose a tensor-based subspace learning method (TSL) for synthesizing human multi-pose facial images from a single twodimensional image. In the proposed TSL method, two-dimensional multi-pose images in the database are previously organized into a tensor form and a tensor decomposition technique is applied to build projection subspaces. In synthesis processing, the input two-dimensional image is first projected into its corresponding projection subspace to get an identity vector and then the identity vector is used to generate other novel pose images. Our technique is applied onKAO-RitsumeikanMulti-angleView, Illumination and Cosmetic Facial Database(MaVIC) and experimental results show the effectiveness of our proposed method for facial pose synthesis.

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

Access this chapter

Log in via an institution
eBook
USD 16.99
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
Hardcover Book
USD 109.99
Price excludes VAT (USA)
  • Durable hardcover edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Vasilescu, M.A.O., Terzopoulos, D.: Multilinear Analysis of Image Ensembles: TensorFaces. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002, Part I. LNCS, vol. 2350, pp. 447–460. Springer, Heidelberg (2002)

    Chapter  Google Scholar 

  2. Vasilescu, M.A.O., Terzopoulos, D.: Multilinear Analysis for Facial Image Recognition. In: 16th International Conference on Pattern Recognition (ICPR 2002), vol. 2, pp. 511–514 (2002)

    Google Scholar 

  3. Chellappa, R., Wilson, C.L., Sirohey, S.: Human and Machine Recognition of Faces: A Survey. Proceedings of the IEEE 83(5), 705–740 (1995)

    Article  Google Scholar 

  4. Igarashi, T., Nishino, K., Nayar, S.K.: The Appearance of Human Skin: A Survey. Foundations and Trends in Computer Graphics and Vision 3(1), 1–95 (2007)

    Article  Google Scholar 

  5. Terzopoulos, D., Waters, K.: Physically-based Facial Modeling, Analysis and Animation. Visualization and Computer Animation 1, 73–80 (1990)

    Article  Google Scholar 

  6. Castelan, M., Hancock, E.R.: A Simple Coupled Statistical Model for 3d Face Shape Recovery. In: 18th International Conference on Pattern Recognition (ICPR 2006), vol. 1, pp. 231–234 (2006)

    Google Scholar 

  7. Horn, B.K.P., Brooks, M.J.: Shape From Shading. NIT Press (1989)

    Google Scholar 

  8. Vetter, T., Poggio, T.: Linear Object Classed and Image Synthesis From A Single Example Image. IEEE Transactions on Pattern Analysis and Machine Intelligence 19(7), 733–742 (1995)

    Article  Google Scholar 

  9. Wang, J., Zhang, C.S., Kou, Z.B.: An Analytical Mapping for LLE and Its Applications in Multi-Pose Face Synthesis. In: 14th British Machine Vision Conference, pp. 285–294 (2003)

    Google Scholar 

  10. Blana, V., Vetter, T.: A Morphable Model for the Synthesis of 3d Faces. In: Siggraph 1999, Computer Graphics Proceedings, pp. 187–194 (1999)

    Google Scholar 

  11. Tsai, Y., Lin, H.J., Yang, F.W.: Facial Expression Synthesis Based on Imitation. In: Dornaika, F. (ed.) International Journal of Advanced Robotic Systems. InTech (2012) ISBN: 1729-8806, doi:10.5772/51906, 2012

    Google Scholar 

  12. Wang, H.C., Ahuja, N.: Facial Expression Decomposition. In: 9th IEEE International Conference on Computer Vision (ICCV 2003), vol. 2, pp. 958–965 (2003)

    Google Scholar 

  13. Chen, Y.-W., Fukui, T., Qiao, X., Igarashi, T., Nakao, K., Kashimoto, A.: Multi-angle view, illumination and cosmetic facial image database (MaVIC) and quantitative analysis of facial appearance. In: da Vitoria Lobo, N., Kasparis, T., Roli, F., Kwok, J.T., Georgiopoulos, M., Anagnostopoulos, G.C., Loog, M. (eds.) SSPR&SPR 2008. LNCS, vol. 5342, pp. 411–420. Springer, Heidelberg (2008)

    Chapter  Google Scholar 

  14. Tucker, L.R.: Some Mathematical Notes of Three-mode Factor Analysis. Psychometrika 31(3), 279–322 (1996)

    Article  Google Scholar 

  15. Bader, B.W., Kolda, T.G.: Algorithm 862: Matlab Tensor Classes for Fast Algorithm Prototyping. ACM Transactions on Mathematical Software 32(4), 635–653 (2006)

    Article  MATH  MathSciNet  Google Scholar 

  16. Lathauwer, L.D., Moor, B.D., Vandewalle, J.: A Multilinear Singular Value Decomposition. SIAM Journal of Matrix Analysis and Application 21, 1253–1278 (2001)

    Article  Google Scholar 

  17. Yu, H.C., Bennamoun, M.: 1D-PCA,2D-PCA to nD-PCA. In: 18th International Conference on Pattern Recognition (ICPR 2006), vol. 4, pp. 181–184 (2006)

    Google Scholar 

  18. Xu, R., Chen, Y.W.: Generalized N-dimensional Principal Component Analysis (GND-PCA) and Its Application on Construction of Statistical Appearance Models for Medical Volumes with Fewer Samples. Neurocomputing 72(10), 2276–2287 (2009)

    Article  Google Scholar 

  19. Qiao, X., Xu, R., Chen, Y.W., Igarashi, T., Nakao, K., Kashimoto, A.: Generalized N-Dimensional Principal Component Analysis (GND-PCA) Based Statistical Appearance Modeling of Facial Images with Multipal Modes. IPSJ Transtractions on Computer Vision and Applications 1, 231–241 (2009)

    Article  Google Scholar 

  20. Kolda, T.G.: Orthogonal Tensor Decompositions. SIAM Journal on Matrix Analysis and Applications 3(1), 243–255 (2001)

    Article  MathSciNet  Google Scholar 

  21. Levin, J.: Three-Mode Factor Analysis, Ph.D Thesis, University of Illinois (1963)

    Google Scholar 

  22. Hitchcock, F.L.: The Expression of A Tensor or A Polyadic as A Sum of Products. J. Math. Phys. 7, 164–189 (1927)

    Google Scholar 

  23. Lee, H.S., Tensor-Based, D.J.K.: AAM with Continuous Variation Estimation: Application to Variation-Robust Face Recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence 31(6), 1102–1116 (2009)

    Article  Google Scholar 

  24. Hitchcock, F.L.: Multiple Invariants and Generalized Rank of a P-Way Matrix or Tensor. J. Math. Phys. 7, 39–79 (1927)

    MATH  Google Scholar 

  25. Cattell, R.B.: Parallel Proportional Profiles and Other Principles for Determining the Choice of Factors by Rotation. Psychometrika 9, 267–283 (1944)

    Article  Google Scholar 

  26. Cattell, R.B.: The Three Basic Factor-Analytic Research Designs - Their Interrelations and Derivatives. Psych. Bull. 49, 499–520 (1952)

    Article  Google Scholar 

  27. Tucker, L.R.: Implications of Factor Analysis of Three-Way Matrices for Measurement of Change. In: Problems in Measuring Change, pp. 122–137. University of Wisconsin Press (1963)

    Google Scholar 

  28. Kapteyn, A., Neudecker, H., Wansbeek, T.: An Approach to n-Mode Component Analysis. Psychometrika 51 (1986)

    Google Scholar 

  29. Cootes, T.F., Edwards, G.J., Taylor, C.J.: Active Appearance Models. In: Burkhardt, H., Neumann, B. (eds.) ECCV 1998. LNCS, vol. 1407, pp. 484–498. Springer, Heidelberg (1998)

    Google Scholar 

  30. Xiong, P., Huang, L., Liu, C.: Initialization and pose alignment in active shape model. In: IEEE International Conference on Pattern Recognition 2010, pp. 3971–3974 (2010)

    Google Scholar 

  31. Terada, T., Fukui, T., Igarashi, T., Nakao, K., Kashimoto, A., Chen, Y.W.: Automatic Facial Image Manipulation System and Facial Texture Analysis. In: 5th International Conference on Natural Computation (ICNC 2009), pp. 1–5 (2009)

    Google Scholar 

  32. Igarashi, T., Nishino, K., Nayar, S.K.: The Appearance of Human Skin: A Survey. Foundations and Trends in Computer Graphics and Vision 3(1), 1–95 (2007)

    Article  Google Scholar 

  33. Tucker, L.R.: The Extension of Factor Analysis to Three-Dimensional Matrices. In: Contributions to Mathematical Psychology, pp. 110–127 (1964)

    Google Scholar 

  34. Carroll, J.D., Chang, J.J.: Analysis of Individual Differences in Multidimensional Scaling via An N-Way Generalization of “Eckart-Young” Decomposition. Psychometrika 35, 283–319 (1970)

    Article  MATH  Google Scholar 

  35. Harshman, R.A.: Foundations of the PARAFAC Procedure: Model and Conditions for An “Explanatory” Multi-Mode Factor Analysis. UCLA Working Papers in Phonetics 16, 1–84 (1970)

    Google Scholar 

  36. Henrion, R.: Body Diagonalization of Core Matrices in Three-Way Principal Components Analysis: Theoretical Bounds and Simulation. Journal of Chemometrics 7, 477–494 (1993)

    Article  Google Scholar 

  37. Smilde, A.K., Wang, Y., Kowalski, B.R.: Theory of Medium-Rank Second-Order Calibration with Restricted-Tucker Models. Journal of Chemometrics 8, 21–36 (1994)

    Article  Google Scholar 

  38. Bro, R.: Multi-Way Analysis in the Food Industry: Models, Algorithms, and Applications, Ph.D Thesis, University of Amsterdam (1998)

    Google Scholar 

  39. Bro, R., Andersson, C.A., Kiers, H.A.L.: PARAFAC2: Modeling Chromatographic Data with Retention Time Shifts. J. Chemometrics 13, 295–309 (1999)

    Article  Google Scholar 

  40. Lathauwer, L.D., Moor, B.D., Vandewalle, J.: From Matrix to Tensor: Multilinear Algebra ans Signal Processing. Mathematics in Signal Processing, 1–15 (1998)

    Google Scholar 

  41. Comon, P.: Tensor Decompositions: State of the Art and Applications. In: IMA Conference Mathematics in Signal Processing, pp. 18–20 (2000)

    Google Scholar 

  42. Chen, B., Petropolu, A., Lathauwer, L.D.: Blind Identification of Convolutive Mim systems with 3 Sources and 2 Sensors. Appl. Signal Processing 5, 487–496 (2002)

    Article  Google Scholar 

  43. Lathauwer, L.D., Moor, B.D., Vandewalle, J.: A Multilinear Singular Value Decomposition. SIAM Journal on Matrix Analysis and Applications 21(4), 1253–1278 (2000)

    Article  MATH  MathSciNet  Google Scholar 

  44. Lathauwer, L.D., Moor, B.D., Vandewalle, J.: On the Best Rank-1 and Rank-(R 1,R 2, ⋯ ,R N ) Approximation of Higher-Order Tensors. SIAM Journal on Matrix Analysis and Applications 21(4), 1324–1342 (2000)

    Article  MATH  MathSciNet  Google Scholar 

  45. Liu, N., Zhang, B., Yan, J., Chen, Z., Liu, W., Bai, F., Chien, L.: Text Representation: From Vector to Tensor. In: Proceedings of the 5th IEEE International Conference on Data Mining, pp. 725–728 (2005)

    Google Scholar 

  46. Sun, J.T., Zeng, H.J., Liu, H., Yu, Y., Chen, Z.: CubeSVD: A Novel Approach to Personalized Web Search. In: Proceedings of the 14th Internatinoal Conference on World Wide Web, pp. 382–390 (2005)

    Google Scholar 

  47. Beckmann, C., Smith, S.: Tensorial Extensions of Independent Component Analysis for Multisubject FMRI Analysis. NeuroImage 25, 294–311 (2005)

    Article  Google Scholar 

  48. Morup, M., Harsen, L.K., Herrmann, C.S., Parnas, J., Arnfred, S.M.: Parallel Factor Analysis as An Exploratory Tool for Wavelet Transformed Event-Related EEG. SIAM Journal on Matrix Analysis and Applications 29, 938–947 (2006)

    Google Scholar 

  49. Kroonenberg, P.M.: Three-Mode Principal Component Anslysis: Theory and Applications. DOW Press (1983)

    Google Scholar 

  50. Henrion, R.: N-way Component Analysis Theory, Algorithms and Applications. Chemometrics and Intelligent Laboratory Systems 25, 1–23 (1983)

    Article  Google Scholar 

  51. Coppi, R., Bolasco, S.: Multiway Data Analysis. North-Holland (1989)

    Google Scholar 

  52. Kroonenberg, P.M.: Applied Multiway Data Analysis. Wiley (2008)

    Google Scholar 

  53. Paatero, P.: The Multilinear Engine: A Table-Driven, Least Squares Program for Solving Multilinear Problems, Including the N-Way Parallel Factor Analysis Model. J. Comput. Graphical Statist. 8, 854–888 (1999)

    MathSciNet  Google Scholar 

  54. Andersson, C.A., Rao, R.: The N-Way Toolbox for MATLAB. Chemometrics and Intelligent Laboratory Systems 52, 1–4 (2000)

    Article  Google Scholar 

  55. Landry, W.: Implementing A High Performance Tensor Libernary. Sci. Programming 11, 273–290 (2003)

    Google Scholar 

  56. Bader, B.W., Kolda, T.G.: Algorithm 862: MATLAB Tensor Classes for Fast Algorithm Prototyping. ACM Trans. Math. Software 32, 635–653 (2006)

    Article  MATH  MathSciNet  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. School of Control Science and Engineering, Shandong University, Jinan, China

    Xu Qiao

  2. Beauty Cosmetic Research Lab, Kao Corporation, Tokyo, Japan

    Takanori Igarashi

  3. College of Information Science and Engineering, Ritsumeikan University, Shiga, Japan

    Yen-Wei Chen

Authors
  1. Xu Qiao
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Takanori Igarashi
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Yen-Wei Chen
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Xu Qiao .

Editor information

Editors and Affiliations

  1. Ritsumeikan University College of Science & Engineering, Kusuatsu, Shiga, Japan

    Yen-Wei Chen

  2. Faculty of Education, Science, Technology & Mathematics, University of Canberra, Canberra, South Australia, Australia

    Lakhmi C. Jain

Rights and permissions

Reprints and permissions

Copyright information

© 2014 Springer-Verlag Berlin Heidelberg

About this chapter

Cite this chapter

Qiao, X., Igarashi, T., Chen, YW. (2014). Tensor-Based Subspace Learning for Multi-pose Face Synthesis. In: Chen, YW., C. Jain, L. (eds) Subspace Methods for Pattern Recognition in Intelligent Environment. Studies in Computational Intelligence, vol 552. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-54851-2_8

Download citation

  • DOI: https://doi.org/10.1007/978-3-642-54851-2_8

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-642-54850-5

  • Online ISBN: 978-3-642-54851-2

  • eBook Packages: EngineeringEngineering (R0)

Publish with us

Policies and ethics

Search

Navigation