access icon free Improved complete neighbourhood preserving embedding for face recognition

© The Institution of Engineering and Technology
Received 11/09/2011, Accepted 18/01/2013, Revised 20/12/2012, Published

Complete neighbourhood preserving embedding (CNPE) is a recently proposed approach to overcome the drawbacks of neighbourhood preserving embedding (NPE) which is difficult to directly apply to face recognition because of computational complexity. However, there are still disadvantages for CNPE: (i) CNPE is time-consuming when N is large, here N is the sample size; (ii) the solutions of CNPE may suffer from the degenerate eigenvalue problem, that is, several eigenvectors with the same maximal eigenvalue, which make them not optimal in terms of the discriminant ability. In this study, the authors proposed a new approach, namely improved complete neighbourhood preserving (ICNPE), to address the drawbacks of CNPE. ICNPE is more efficient than CNPE and can overcome the degenerate eigenvalue problem of CNPE. Experiments on the Olivetti & Oracle Research Laboratory (ORL), Yale, PIE (pose, illumination and expression) and Alex Martinez and Robert Benavente (AR) face databases show the effectiveness of the proposed ICNPE.

Inspec keywords: eigenvalues and eigenfunctions; visual databases; computational complexity; face recognition

Other keywords: Yale face database; maximal eigenvalue; improved complete neighbourhood preserving embedding; degenerate eigenvalue problem; pose face database; ICNPE; eigenvectors; expression face database; face recognition; computational complexity; illumination face database; AR face databases; ORL face database

Subjects: Algebra; Computational complexity; Image recognition; Computer vision and image processing techniques; Algebra

References

    1. 1)
      • 19. Belkin, M., Niyogi, P.: ‘Laplacian eigenmaps for dimensionality reduction and data representation’, Neural Comput., 2003, 15, (6), pp. 1373–1396.
    2. 2)
      • 15. Lu, G.-F., Zou, J., Wang, Y.: ‘Incremental learning of complete linear discriminant analysis for face recognition’, Knowl.-Based Syst., 2012, 31, (7), pp. 19–27.
    3. 3)
      • 5. Hong, Z.Q., Yang, J.Y.: ‘Optimal discriminant plane for a small number of samples and design method of classifier on the plane’, Pattern Recognit., 1991, 24, (4), pp. 317–324.
    4. 4)
      • 10. Chen, L.F., Liao, H.Y.M., Ko, M.T., Yu, G.J.: ‘A new LDA-based face recognition system which can solve the small sample size problem’, Pattern Recognit., 2000, 33, (10), pp. 1713–1726.
    5. 5)
      • 13. Yang, J., Yang, J.Y.: ‘Why Can LDA Be Performed in PCA Transformed Space?’, Pattern Recognit., 2003, 36, (3), pp. 563–566.
    6. 6)
      • 29. Lai, Z., Wan, M., Jin, Z.: ‘Locality preserving embedding for face and handwriting digital recognition’, Neural Comput. Appl., 2011, 20, (4), pp. 565–573.
    7. 7)
      • 1. Chellappa, R., Wilson, C., Sirohey, S.: ‘Human and machine recognition of faces: a survey’, Proc. IEEE, 1995, 83, (5), pp. 705–740.
    8. 8)
      • 27. Lai, Z., Wong, W.K., Jin, Z., Yang, J., Xu, Y.: ‘Sparse approximation to the eigensubspace for discrimination’, IEEE Trans. Neural Netw. Learn. Syst., 2012, 23, (12), pp. 1948–1960.
    9. 9)
      • 28. Lai, Z., Jin, Z., Sun, M., Yang, J.: ‘Dynamic transition embedding for image feature extraction and recognition’, Neural Comput. Appl., 2012, 21, (8), pp. 1905–1915.
    10. 10)
      • 18. Roweis, S.T., Saul, L.K.: ‘Nonlinear dimension reduction by locally linear embedding’, Science, 2000, 290, (5500), pp. 2323–2326.
    11. 11)
      • 26. Fan, Z., Xu, Y., Zhang, D.: ‘Local linear discriminant analysis framework using sample neighbors’, IEEE Trans. Neural Netw., 2011, 22, (7), pp. 1119–1132.
    12. 12)
      • 11. Yu, H., Yang, J.: ‘A direct LDA algorithm for high-dimensional data with application to face recognition’, Pattern Recognit., 2000, 33, (1), pp. 1731–1726.
    13. 13)
      • 12. Liu, K., Cheng, Y.Q., Yang, J.Y., Liu, X.: ‘An efficient algorithm for Foley–Sammon optimal set of discriminant vectors by algebraic method’, Int. J. Pattern Recognit. Artif. Intell., 1992, 6, pp. 817–829.
    14. 14)
      • 25. Yang, W., Wang, J., Ren, M., Yang, J., Zhang, L., Liu, G.: ‘Feature extraction based on Laplacian bidirectional maximum margin criterion’, Pattern Recognit., 2009, 42, (11), pp. 2327–2334.
    15. 15)
      • 8. Cai, D., He, X., Han, J.: ‘SRDA: an efficient algorithm for large scale discriminant analysis’, IEEE Trans. Knowl. Data Eng., 2008, 20, (1), pp. 1–12.
    16. 16)
      • 14. Lu, G.-F., Zou, J., Wang, Y.: ‘Incremental complete LDA for face recognition’, Pattern Recognit., 2012, 45, (7), pp. 2510–2521.
    17. 17)
      • 24. Lai, Z., Wan, M., Jin, Z., Yang, J.: ‘Sparse two-dimensional local discriminant projections for feature extraction’, Neurocomputing, 2011, 74, pp. 629–637.
    18. 18)
      • 17. Tenenbaum, J.B., Silva, V.d., Langford, J.C.: ‘A global geometric framework for nonlinear dimensionality reduction’, Science, 2000, 290, pp. 2319–2323.
    19. 19)
      • 22. Wang, Y., Wu, Y.: ‘Complete neighborhood preserving embedding for face recognition’, Pattern Recognit., 2010, 43, (3), pp. 1008–1015.
    20. 20)
      • 23. Wan, M., Lai, Z., Jin, Z.: ‘Feature extraction using two-dimensional local graph embedding based on maximum margin criterion’, Appl. Math. Comput., 2011, 217, (23), pp. 9659–9668.
    21. 21)
      • 9. Cai, D.: ‘Spectral regression: a regression framework for efficient regularized subspace learning’. PhD thesis, Department of Computer Science, University of Illinois at Urbana-Champaign, 2009.
    22. 22)
      • 4. Belhumeour, P.N., Hespanha, J.P., Kriegman, D.J.: ‘Eigenfaces vs. Fisherfaces: recognition using class specific linear projection’, IEEE Trans. Pattern Anal. Mach. Intell., 1997, 19, (7), pp. 711–720.
    23. 23)
      • 16. Yang, W., Sun, C., Zhang, L.: ‘A multi-manifold discriminant analysis method for image feature extraction’, Pattern Recognit., 2011, 44, (8), pp. 1649–1657.
    24. 24)
      • 6. Friedman, J.H.: ‘Regularized discriminant analysis’, J. Am. Stat. Assoc., 1989, 84, (405), pp. 165–175.
    25. 25)
      • 30. Yan, S., Xu, D., Zhang, B., Zhang, H.-J., Yang, Q., Lin, S.: ‘Graph embedding and extensions: a general framework for dimensionality reduction’, IEEE Trans. Pattern Anal. Mach. Intell., 2007, 29, (1), pp. 40–51.
    26. 26)
      • 32. Lu, G.-F., Lin, Z., Jin, Z.: ‘Face recognition using discriminant locality preserving projections based on maximum margin criterion’, Pattern Recognit., 2010, 43, (10), pp. 3572–3579.
    27. 27)
      • 20. He, X., Yan, S., Hu, Y., Niyogi, P., Zhang, H.: ‘Face recognition using Laplacian faces’, IEEE Trans. Pattern Anal. Mach. Intell., 2005, 27, (3), pp. 328–340.
    28. 28)
      • 2. Zhao, W., Chellappa, R., Phillips, P., Rosenfeld, A.: ‘Face recognition: a literature survey’, ACM Comput. Surv., 2003, 35, (4), pp. 399–458.
    29. 29)
      • 7. Cai, D., He, X., Han, J.: ‘Spectral regression for efficient regularized subspace learning’. IEEE Int. Conf. Computer Vision (ICCV'07), Rio de Janeiro, Brazil, 2007.
    30. 30)
      • 21. He, X., Cai, D., Yan, S., Zhang, H.: ‘Neighborhood preserving embedding’. Proc. Int. Conf. on Computer Vision (ICCV), 2005, pp. 1208–1213.
    31. 31)
      • 3. Duda, R.O., Hart, P.E., Stork, D.G.: ‘Pattern classification’ ( John Wiley & Sons, New York, 2000, 2nd edn.).
    32. 32)
      • 31. Lu, G.-F., Zou, J.: ‘Feature extraction using a complete kernel extension of supervised graph embedding’, Neural Process. Lett., 2012, 34, (2), pp. 159–175.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-cvi.2012.0202
Loading

Related content

content/journals/10.1049/iet-cvi.2012.0202
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading