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.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
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)
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)
Chellappa, R., Wilson, C.L., Sirohey, S.: Human and Machine Recognition of Faces: A Survey. Proceedings of the IEEE 83(5), 705–740 (1995)
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)
Terzopoulos, D., Waters, K.: Physically-based Facial Modeling, Analysis and Animation. Visualization and Computer Animation 1, 73–80 (1990)
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)
Horn, B.K.P., Brooks, M.J.: Shape From Shading. NIT Press (1989)
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)
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)
Blana, V., Vetter, T.: A Morphable Model for the Synthesis of 3d Faces. In: Siggraph 1999, Computer Graphics Proceedings, pp. 187–194 (1999)
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
Wang, H.C., Ahuja, N.: Facial Expression Decomposition. In: 9th IEEE International Conference on Computer Vision (ICCV 2003), vol. 2, pp. 958–965 (2003)
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)
Tucker, L.R.: Some Mathematical Notes of Three-mode Factor Analysis. Psychometrika 31(3), 279–322 (1996)
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)
Lathauwer, L.D., Moor, B.D., Vandewalle, J.: A Multilinear Singular Value Decomposition. SIAM Journal of Matrix Analysis and Application 21, 1253–1278 (2001)
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)
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)
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)
Kolda, T.G.: Orthogonal Tensor Decompositions. SIAM Journal on Matrix Analysis and Applications 3(1), 243–255 (2001)
Levin, J.: Three-Mode Factor Analysis, Ph.D Thesis, University of Illinois (1963)
Hitchcock, F.L.: The Expression of A Tensor or A Polyadic as A Sum of Products. J. Math. Phys. 7, 164–189 (1927)
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)
Hitchcock, F.L.: Multiple Invariants and Generalized Rank of a P-Way Matrix or Tensor. J. Math. Phys. 7, 39–79 (1927)
Cattell, R.B.: Parallel Proportional Profiles and Other Principles for Determining the Choice of Factors by Rotation. Psychometrika 9, 267–283 (1944)
Cattell, R.B.: The Three Basic Factor-Analytic Research Designs - Their Interrelations and Derivatives. Psych. Bull. 49, 499–520 (1952)
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)
Kapteyn, A., Neudecker, H., Wansbeek, T.: An Approach to n-Mode Component Analysis. Psychometrika 51 (1986)
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)
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)
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)
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)
Tucker, L.R.: The Extension of Factor Analysis to Three-Dimensional Matrices. In: Contributions to Mathematical Psychology, pp. 110–127 (1964)
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)
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)
Henrion, R.: Body Diagonalization of Core Matrices in Three-Way Principal Components Analysis: Theoretical Bounds and Simulation. Journal of Chemometrics 7, 477–494 (1993)
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)
Bro, R.: Multi-Way Analysis in the Food Industry: Models, Algorithms, and Applications, Ph.D Thesis, University of Amsterdam (1998)
Bro, R., Andersson, C.A., Kiers, H.A.L.: PARAFAC2: Modeling Chromatographic Data with Retention Time Shifts. J. Chemometrics 13, 295–309 (1999)
Lathauwer, L.D., Moor, B.D., Vandewalle, J.: From Matrix to Tensor: Multilinear Algebra ans Signal Processing. Mathematics in Signal Processing, 1–15 (1998)
Comon, P.: Tensor Decompositions: State of the Art and Applications. In: IMA Conference Mathematics in Signal Processing, pp. 18–20 (2000)
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)
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)
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)
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)
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)
Beckmann, C., Smith, S.: Tensorial Extensions of Independent Component Analysis for Multisubject FMRI Analysis. NeuroImage 25, 294–311 (2005)
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)
Kroonenberg, P.M.: Three-Mode Principal Component Anslysis: Theory and Applications. DOW Press (1983)
Henrion, R.: N-way Component Analysis Theory, Algorithms and Applications. Chemometrics and Intelligent Laboratory Systems 25, 1–23 (1983)
Coppi, R., Bolasco, S.: Multiway Data Analysis. North-Holland (1989)
Kroonenberg, P.M.: Applied Multiway Data Analysis. Wiley (2008)
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)
Andersson, C.A., Rao, R.: The N-Way Toolbox for MATLAB. Chemometrics and Intelligent Laboratory Systems 52, 1–4 (2000)
Landry, W.: Implementing A High Performance Tensor Libernary. Sci. Programming 11, 273–290 (2003)
Bader, B.W., Kolda, T.G.: Algorithm 862: MATLAB Tensor Classes for Fast Algorithm Prototyping. ACM Trans. Math. Software 32, 635–653 (2006)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights 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)