Your browser does not support JavaScript!
http://iet.metastore.ingenta.com
1887

access icon free Head pose estimation and face recognition using a non-linear tensor-based model

© The Institution of Engineering and Technology
Received 06/10/2012, Accepted 02/05/2013, Revised 06/04/2013, Published

Although the ability to estimate the face pose and recognise its identity are common human abilities, they are still a challenge in computer vision context. In this study, the authors aim to overcome these difficulties by learning a non-linear tensor-based model based on multi-linear decomposition. Proposed model maps the high-dimensional image space into low-dimensional pose manifold. For preserving the actual distance along the manifold shape, a graph-based distance measure is proposed. Also, to compensate for the limited number of training poses, mirrored images are added to training ones to improve the recognition accuracy. For performance evaluation of the proposed method, experiments are run on three famous face databases using three different manifold shapes and two different distance measures. Eight training data modes are chosen such that the influential parameters are studied comprehensively. The obtained results confirm the effectiveness of proposed model in achieving high accuracy in pose estimation and multi-view face recognition, even with different training poses for different identities.

Inspec keywords: pose estimation; face recognition; graph theory; tensors

Other keywords: mirrored image; graph based distance measure; training data modes; model map; nonlinear tensor based model; high-dimensional image space; low-dimensional pose manifold; training pose; multiview face recognition; head pose estimation

Subjects: Image recognition; Algebra; Image recognition; Combinatorial mathematics; Computer vision and image processing techniques; Combinatorial mathematics; Algebra

References

    1. 1)
      • 2. Tolba, A.S., El-Baz, A.H., El-Harby, A.A.: ‘Face recognition: a literature review’, Int. J. Signal Proc., 2006, 2, (2), pp. 88–103.
    2. 2)
      • 5. Wei, W., Zhang, Y., Tian, C.: ‘Head pose estimation method based on pose manifold and tensor decomposition’, J. Syst. Eng. Electron., 2010, 21, (5), pp. 907–913.
    3. 3)
      • 30. Poggio, T., Girosi, F.: ‘Networks for approximation and learning’, Proc. IEEE, 1990, 78, (9), pp. 1481–1497 (doi: 10.1109/5.58326).
    4. 4)
      • 32. Brown, L.M., Tian, Y.: ‘Comparative study of coarse head pose estimation’. Proc. Workshop on Motion and Video Computer, 2002, pp. 125–130.
    5. 5)
      • 31. Kolda Tamara, G.: ‘Orthogonal tensor decompositions’, SIAM J. Matrix Anal. Appl., 2001, 23, (1), pp. 243–255 (doi: 10.1137/S0895479800368354).
    6. 6)
      • 34. Tian, Y.L., Brown, L., Connell, C., et al: ‘Absolute head pose estimation from overhead wide-angle cameras’. IEEE Int. Workshop on Analysis and Modeling of Faces and Gestures, (AMFG'03), 2003, pp. 92–99.
    7. 7)
      • 7. Turk, M.A., Pentland, A.P.: ‘Face recognition using eigenfaces’. IEEE Comput. Society Conf. on Proc. Computer Vision and Pattern Recognition (CVPR'91), 1991, pp. 586–591.
    8. 8)
      • 3. Gao, X., Tian, C.: ‘Multi-view face recognition based on tensor subspace analysis and view manifold modeling’, Neurocomputing, 2009, 72, (16–18), pp. 3742–3750 (doi: 10.1016/j.neucom.2009.06.001).
    9. 9)
      • 10. Jian, Y., David, Z., Frangi Alejandro, F., Jing-yu, Y.: ‘Two-dimensional pca: a new approach to appearance-based face representation and recognition’, IEEE Trans. Pattern Anal. Mach. Intell., 2004, 26, (1), pp. 131–137 (doi: 10.1109/TPAMI.2004.1261097).
    10. 10)
      • 35. Mohseni, H., Kasaei, Sh.: ‘Multiview face recognition based on multilinear decomposition and pose manifold’, IET Image Process., 2013, DOI: 10.1049/iet-ipr.2013.0003.
    11. 11)
      • 41. Pathangay, V., Das, S., Greiner, T.: ‘Symmetry-based face pose estimation from a single uncalibrated view’. Proc. Eighth IEEE Int. Conf. on Automatic Face and Gesture Recognition, (FG ‘08), 2008, pp. 1–8.
    12. 12)
      • 37. Asthana, A., Marks, T.K., Jones, M.J., Tieu, K.H., Rohith, M.: ‘Fully automatic pose-invariant face recognition via 3d pose normalization’. IEEE Int. Conf. on Computer Vision (ICCV'11), 2011, pp. 937–944.
    13. 13)
      • 13. Lu, G.F., Lin, Z., Jin, Z.: ‘Face recognition using regularised generalised discriminant locality preserving projections’, IET Comput. Vis., 2011, 5, (2), pp. 107–116 (doi: 10.1049/iet-cvi.2009.0138).
    14. 14)
      • 4. Balasubramanian, V.N., Krishna, S., Panchanathan, S.: ‘Person-independent head pose estimation using biased manifold embedding’, EURASIP J. Adv. Signal Process., 2008, 2008, pp. 1–15 (doi: 10.1155/2008/283540).
    15. 15)
      • 33. Ba, S.O., Odobez, J.M.: ‘A probabilistic framework for joint head tracking and pose estimation’. Proc. 17th Int. Conf. on Pattern Recognition (ICPR'04), 2004, pp. 264–267.
    16. 16)
      • 36. Saquib Sarfraz, M., Hellwich, O.: ‘Probabilistic learning for fully automatic face recognition across pose’, Image and Vision Comput., 2009, 28, (5), pp. 744–753 (doi: 10.1016/j.imavis.2009.07.008).
    17. 17)
      • 17. Tenenbaum, J.B., Silva, V., Langford, J.C.: ‘A global geometric framework for nonlinear dimensionality reduction’, Science, 2000, 290, pp. 2319–2323 (doi: 10.1126/science.290.5500.2319).
    18. 18)
      • 20. Shuicheng, Y., Dong, X., Benyu, Z., Hong-Jiang, Z., Qiang, Y., Lin, S.: ‘Graph embedding and extensions: a general framework for dimensionality reduction’, IEEE Trans. Pattern Anal. Mach. Intell., 2007, 29, (1), pp. 40–51 (doi: 10.1109/TPAMI.2007.250598).
    19. 19)
      • 22. Ham, J., Lee, D.D., Mika, S., Schlkopf, B.: ‘A kernel view of the dimensionality reduction of manifolds’. Proc. 21th ACM Int. Conf. on Machine Learning, 2004.
    20. 20)
      • 14. Soundar, K.R., Murugesan, K.: ‘Preserving global and local information – a combined approach for recognising face images’, IET Comput. Vis., 2010, 4, (3), pp. 173–182 (doi: 10.1049/iet-cvi.2008.0065).
    21. 21)
      • 25. Ji, H., Su, F., Zhu, Y.: ‘Robust head pose estimation via semi-supervised manifold learning with l1-graph regularization’. Proc. Int. Joint Conf. on Biometrics (IJCB), 2011, pp. 1–6.
    22. 22)
      • 19. He, X., Yan, S., Hu, Y., Niyogi, P., Zhang, H.J.: ‘Face recognition using Laplacianfaces’, IEEE Trans. Pattern Anal. Mach. Intell., 2005, 27, (3), pp. 328–340 (doi: 10.1109/TPAMI.2005.55).
    23. 23)
      • 8. Lu, J., Plataniotis, K.N., Venetsanopoulos, A.N.: ‘Face recognition using lda-based algorithms’, Trans. Neural Netw., 2003, 14, (1), pp. 195–200 (doi: 10.1109/TNN.2002.806647).
    24. 24)
      • 38. Chunna, T., Guoliang, F., Xinbo, G.: ‘Multi-view face recognition by nonlinear tensor decomposition’. Proc. 19th Int. Conf. on Pattern Recognition (ICPR'08), 2008, pp. 1–4.
    25. 25)
      • 28. ‘Oriental face database’. Available at: http://www.aiar.xjtu.edu.cn/groups/face/English/HomePage.htm, 2008.
    26. 26)
      • 27. Black, J., Gargesha, M., Kahol, K., Kuchi, P., Panchanathan, S.: ‘A framework for performance evaluation of face recognition algorithms’. Proc. ITCOM, Internet Multimedia Systems II, 2002.
    27. 27)
      • 21. van der Maaten, L.J.P., Postma, E.O., van den Herik, H.J.: ‘Dimensionality reduction: a comparative review’, J. Mach. Learn. Res., 2009, 10, pp. 1–41.
    28. 28)
      • 9. Pentland, A., Moghaddam, B., Starner, T.: ‘View-based and modular eigenspaces for face recognition’. IEEE Computer Society Conf. on Proc. Computer Visible and Pattern Recognition (CVPR ‘94), 1994, pp. 84–91.
    29. 29)
      • 1. Murphy-Chutorian, E., Trivedi, M.M.: ‘Head pose estimation in computer vision: a survey’, IEEE Trans. Pattern Anal. Mach. Intell., 2009, 31, (4), pp. 607–626 (doi: 10.1109/TPAMI.2008.106).
    30. 30)
      • 6. Park, S.W., Savvides, M.: ‘An extension of multifactor analysis for face recognition based on submanifold learning’. IEEE Conf. on Proc. Computer Vision and Pattern Recognition (CVPR'10), 2010, pp. 2645–2652.
    31. 31)
      • 23. Ming-Hsuan, Y.: ‘Kernel eigenfaces vs. kernel fisherfaces: face recognition using kernel methods’. Proc. Fifth IEEE Int. Conf. on Automatic Face and Gesture Recognition, 2002, pp. 215–220.
    32. 32)
      • 40. Singh, R., Vatsa, M., Ross, A., Noore, A.: ‘A mosaicing scheme for pose-invariant face recognition’, IEEE Trans. Syst. Man Cybern. B, 2007, 37, (5), pp. 1212–1225 (doi: 10.1109/TSMCB.2007.903537).
    33. 33)
      • 15. Vasilescu, M.A., Terzopoulos, D.: ‘Multilinear analysis of image ensembles: Tensorfaces’. Proc. European Conf. on Computer Vision, 2002, pp. 447–460.
    34. 34)
      • 12. Jiangfeng, C., Bo, L., Baozong, Y.: ‘Face recognition using direct lpp algorithm’. Proc. Ninth Int. Conf. on Proc. Signal Processing (ICSP), 2008, pp. 1457–1460.
    35. 35)
      • 18. Roweis, S.T., Saul, L.K.: ‘Nonlinear dimensionality reduction by locally linear embedding’, Science, 2000, 290, pp. 2323–2326 (doi: 10.1126/science.290.5500.2323).
    36. 36)
      • 16. Yang, W., Zhang, L., Zhu, W.: ‘Head pose estimation based on tensor factorization’. Neural Information Processing, Lecture Notes in Computer Science, 4984, (Springer, 2008), pp. 831–840.
    37. 37)
      • 11. Wan, M., Yang, G., Lai, Z., Jin, Z.: ‘Feature extraction based on fuzzy local discriminant embedding with applications to face recognition’, IET Comput. Vis., 2011, 5, (5), pp. 301–308 (doi: 10.1049/iet-cvi.2011.0028).
    38. 38)
      • 39. Liu, X., Chen, T.: ‘Pose-robust face recognition using geometry assisted probabilistic modeling’. Proc. IEEE Computer Society Conf. on Computer Vision and Pattern Recognition, (CVPR ‘05), 2005, vol. 1, pp. 502–509.
    39. 39)
      • 24. Elgammal, A., Chan-Su, L.: ‘Separating style and content on a nonlinear manifold’. IEEE Computer Society Conf. Proc. Computer Vision and Pattern Recognition (CVPR'04), 2004, vol. 1, pp. 478–485.
    40. 40)
      • 29. Sim, T., Baker, S., Bsat, M.: ‘The cmu pose, illumination, and expression (pie) database’. Proc. Fifth IEEE Int. Conf. on Automatic Face and Gesture Recognition, 2002, pp. 46–51.
    41. 41)
      • 26. Prince, S.J.D., Warrell, J., Elder, J.H., Felisberti, F.M.: ‘Tied factor analysis for face recognition across large pose differences’, IEEE Trans. Pattern Anal. Mach. Intell., 2008, 30, (6), pp. 970–984 (doi: 10.1109/TPAMI.2008.48).
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-cvi.2012.0217
Loading

Related content

content/journals/10.1049/iet-cvi.2012.0217
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading
Print this page
This is a required field
Please enter a valid email address