Comparison of Tensor Unfolding Variants for 2DPCA-Based Color Facial Portraits Recognition

  • Paweł Forczmański
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7594)


The paper presents a problem of recognition of color facial images in the aspect of dimensionality reduction performed by means of Principal Component Analysis employing different variants of input data organization. Here, input images are represented by tensors of 3rd order and the PCA is applied for matrices derived from such tensors. Its main advantage is associated with efficient representation of images leading to the accurate recognition. The paper describes practical aspects of the algorithm and its implementation for three variants of tensor unfolding. Furthermore the impact of the number of training/testing images, the reduction ratio and the color model on the recognition accuracy is investigated. The experiments performed on Essex facial image databases showed that face recognition using this type of feature space dimensionality reduction is particularly convenient and efficient, giving high recognition performance.


Face Recognition Training Image Recognition Accuracy Karhunen Loeve Transform Classical Principal Component Analysis 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Turk, M., Pentland, A.: Eigenfaces for Recognition. Journal of Cognitive Neurosicence 3(1), 71–86 (1991)CrossRefGoogle Scholar
  2. 2.
    Li Stan, Z., Jain, A.K.: Handbook of Face Recognition, vol. 395. Springer (2005)Google Scholar
  3. 3.
    Forczmański, P., Kukharev, G.: Comparative analysis of simple facial features extractors. J. of Real-Time Image Processing 1(4), 239–255 (2007)CrossRefGoogle Scholar
  4. 4.
    Yang, J., Zhang, D., Frangi, A.F., Yang, J.-Y.: Two-Dimensional PCA: A New Approach to Appearance-Based Face Representation and Recognition. IEEE Trans. Pattern Anal. Mach. Intell. 26(1), 131–137 (2004)CrossRefGoogle Scholar
  5. 5.
    Chen, S., Zhu, Y., Zhang, D., Yang, J.-Y.: Feature extraction approaches based on matrix pattern: MatPCA and MatFLDA. Pattern Recognition Letters 26, 1157–1167 (2005)CrossRefGoogle Scholar
  6. 6.
    Tsapatsoulis, N., Alexopoulos, V., Kollias, S.: A Vector Based Approximation of KLT and Its Application to Face Recognition. In: Proceedings of The IX European Signal Processing Conference EUSIPCO 1998, Island of Rhodes, Greece (1998)Google Scholar
  7. 7.
    Kukharev, G., Forczmański, P.: Data Dimensionality Reduction for Face Recognition. Machine Graphics and Vision 13(1/2), 99–122 (2004)Google Scholar
  8. 8.
    Yang, J., Liu, C.: Horizontal and Vertical 2DPCA Based Discriminant Analysis for Face Verification Using the FRGC Version 2 Database. In: Lee, S.-W., Li, S.Z. (eds.) ICB 2007. LNCS, vol. 4642, pp. 838–847. Springer, Heidelberg (2007)CrossRefGoogle Scholar
  9. 9.
    Thomas, M., Kumar, S., Kambhamettu, C.: Face Recognition Using a Color PCA Framework. In: Gasteratos, A., Vincze, M., Tsotsos, J.K. (eds.) ICVS 2008. LNCS, vol. 5008, pp. 373–382. Springer, Heidelberg (2008)CrossRefGoogle Scholar
  10. 10.
    Tucker, R.L.: Some mathematical notes on the three-mode factor analysis. Psychometrika 31, 279–331 (1966)MathSciNetCrossRefGoogle Scholar
  11. 11.
    De Lathauwer, L., De Moor, B., Vandewalle, J.: A multilinear Singular Value Decomposition. SIAM 21(4), 1253–1278 (2000)MathSciNetzbMATHGoogle Scholar
  12. 12.
    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)CrossRefGoogle Scholar
  13. 13.
    University of Essex, Department of Computer Science. Essex Faces - facial images collection, (accessed April 01, 2012)

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Paweł Forczmański
    • 1
  1. 1.Faculty of Computer Science and Information TechnologyWest Pomeranian University of Technology, SzczecinSzczecinPoland

Personalised recommendations