access icon free On robust face recognition via sparse coding: the good, the bad and the ugly

In the field of face recognition, sparse representation (SR) has received considerable attention during the past few years, with a focus on holistic descriptors in closed-set identification applications. The underlying assumption in such SR-based methods is that each class in the gallery has sufficient samples and the query lies on the subspace spanned by the gallery of the same class. Unfortunately, such an assumption is easily violated in the face verification scenario, where the task is to determine if two faces (where one or both have not been seen before) belong to the same person. In this study, the authors propose an alternative approach to SR-based face verification, where SR encoding is performed on local image patches rather than the entire face. The obtained sparse signals are pooled via averaging to form multiple region descriptors, which then form an overall face descriptor. Owing to the deliberate loss of spatial relations within each region (caused by averaging), the resulting descriptor is robust to misalignment and various image deformations. Within the proposed framework, they evaluate several SR encoding techniques: l 1-minimisation, Sparse Autoencoder Neural Network (SANN) and an implicit probabilistic technique based on Gaussian mixture models. Thorough experiments on AR, FERET, exYaleB, BANCA and ChokePoint datasets show that the local SR approach obtains considerably better and more robust performance than several previous state-of-the-art holistic SR methods, on both the traditional closed-set identification task and the more applicable face verification task. The experiments also show that l 1-minimisation-based encoding has a considerably higher computational cost when compared with SANN-based and probabilistic encoding, but leads to higher recognition rates.

Inspec keywords: image coding; visual databases; face recognition; minimisation; neural nets; Gaussian processes

Other keywords: local image patches; holistic descriptors; FERET datasets; sparse signals; SANN; AR datasets; robust face recognition; image deformations; face verification scenario; exYaleB datasets; local SR approach; closed-set identification applications; l1-minimisation; multiple region descriptors; SR encoding; BANCA datasets; ChokePoint datasets; sparse autoencoder neural network; Gaussian mixture models; implicit probabilistic technique; spatial relations; sparse representation; sparse coding

Subjects: Other topics in statistics; Other topics in statistics; Computer vision and image processing techniques; Neural computing techniques; Optimisation techniques; Image recognition; Image and video coding; Spatial and pictorial databases; Optimisation techniques

References

    1. 1)
    2. 2)
    3. 3)
      • 8. Yang, M., Zhang, L.: ‘Gabor feature based sparse representation for face recognition with Gabor occlusion dictionary’. ECCV (6), (LNCS, 6316), 2010, pp. 448461.
    4. 4)
      • 15. Torralba, A., Shina, P.: ‘Detecting faces in improverished images’. Technical Report 028, MIT AI Lab, 2001.
    5. 5)
    6. 6)
    7. 7)
      • 24. Sanderson, C., Lovell, B.C.: ‘Multi-region probabilistic histograms for robust and scalable identity inference’. (LNCS, 5558), 2009, pp. 199208.
    8. 8)
    9. 9)
    10. 10)
    11. 11)
    12. 12)
    13. 13)
    14. 14)
      • 4. Ali, T., Veldhuis, R., Spreeuwers, L.: ‘Forensic face recognition: a survey’. Technical report TR-CTIT-10-40, Centre for Telematics and Information Technology, University of Twente, December 2010.
    15. 15)
    16. 16)
    17. 17)
    18. 18)
    19. 19)
    20. 20)
    21. 21)
    22. 22)
    23. 23)
    24. 24)
    25. 25)
    26. 26)
    27. 27)
    28. 28)
    29. 29)
    30. 30)
    31. 31)
      • 45. Martínez, A., Benavente, R.: ‘The AR face database’. CVC Technical Report 24, Computer Vision Center, Universitat Autónoma de Barcelona, June 1998.
    32. 32)
      • 42. Ahonen, T., Hadid, A., Pietikäinen, M.: ‘Face description with local binary patterns: application to face recognition’, IEEE Trans. Pattern Anal. Mach. Intell., 2006, 28, (12), pp. 20372041 (doi: 10.1109/TPAMI.2006.244).
    33. 33)
      • 51. Trefethen, L.N., Bau, D.: ‘Numerical linear algebra’ (Society for Industrial and Applied Mathematics, SIAM, 1997).
    34. 34)
      • 35. Good fellow, I.J., Le, Q.V., Saxe, A.M., Lee, H., Ng, A.Y.: ‘Measuring invariances in deep networks’, Adv. Neural Inf. Process. Syst., 2009, pp. 646654.
    35. 35)
      • 8. Yang, M., Zhang, L.: ‘Gabor feature based sparse representation for face recognition with Gabor occlusion dictionary’. ECCV (6), (LNCS, 6316), 2010, pp. 448461.
    36. 36)
      • 17. Wagner, A., Wright, J., Ganesh, A., Zhou, Z., Mobahi, H., Ma, Y.: ‘Towards a practical face recognition system: robust alignment and illumination by sparse representation’, IEEE Trans. Pattern Anal. Mach. Intell., 2012, 34, (2), pp. 372386 (doi: 10.1109/TPAMI.2011.112).
    37. 37)
      • 46. Bailly-Bailliére, E., Bengio, S., Bimbot, F., et al: ‘The BANCA database and evaluation protocol’, Audio- and Video-based Biometric Person Authentication (AVBPA), (LNCS, 2688), 2003, pp. 625638 (doi: 10.1007/3-540-44887-X_74).
    38. 38)
      • 29. Tropp, J.A.: ‘Greed is good: algorithmic results for sparse approximation’, IEEE Trans. Inf. Theory, 2004, 50, (10), pp. 22312242 (doi: 10.1109/TIT.2004.834793).
    39. 39)
      • 20. Aharon, M., Elad, M., Bruckstein, A.: ‘K-SVD: an algorithm for designing over complete dictionaries for sparse representation’, IEEE Trans. Signal Process., 2006, 54, (11), pp. 43114322 (doi: 10.1109/TSP.2006.881199).
    40. 40)
      • 40. Cui, Z., Shan, S., Chen, X., Zhang, L.: ‘Sparsely encoded local descriptor for face recognition’. IEEE Int. Conf. Automatic Face & Gesture Recognition and Workshops, 2011, pp. 149154.
    41. 41)
      • 50. Liu, C., Wechsler, H.: ‘Gabor feature based classification using the enhanced Fisher linear discriminant model for face recognition’, IEEE Trans. Image Process., 2002, 11, (4), pp. 467476 (doi: 10.1109/TIP.2002.999679).
    42. 42)
      • 33. Bishop, C.M.: ‘Neural networks for pattern recognition’ (Oxford University Press, 1995, 1st edn.).
    43. 43)
      • 48. Gao, W., Cao, B., Shan, S., et al: ‘The CAS-PEAL large-scale Chinese face database and baseline evaluations’, IEEE Trans. Syst. Man Cybern. A, Syst. Humans, 2008, 38, (1), pp. 149161 (doi: 10.1109/TSMCA.2007.909557).
    44. 44)
      • 24. Sanderson, C., Lovell, B.C.: ‘Multi-region probabilistic histograms for robust and scalable identity inference’. (LNCS, 5558), 2009, pp. 199208.
    45. 45)
      • 6. Wright, J., Yang, A.Y., Ganesh, A., Sastry, S.S., Ma, Y.: ‘Robust face recognition via sparse representation’, IEEE Trans. Pattern Anal. Mach. Intell., 2009, 31, (2), pp. 210227 (doi: 10.1109/TPAMI.2008.79).
    46. 46)
      • 30. Coates, A., Ng, A.Y.: ‘The importance of encoding versus training with sparse coding and vector quantization’. Proc. Int. Conf. Machine Learning, June 2011, pp. 921928.
    47. 47)
      • 1. Cardinaux, F., Sanderson, C., Bengio, S.: ‘User authentication via adapted statistical models of face images’, IEEE Trans. Signal Process., 2006, 54, (1), pp. 361373 (doi: 10.1109/TSP.2005.861075).
    48. 48)
      • 52. Huttenocher, D.P., Klanderman, G.A., Rucklidge, W.: ‘Comparing images using the Hausdorff distance’, IEEE Trans. Pattern Anal. Mach. Intell., 1993, 15, (9), pp. 850863 (doi: 10.1109/34.232073).
    49. 49)
      • 9. Yang, M., Zhang, L., Yang, J., Zhang, D.: ‘Robust sparse coding for face recognition’. IEEE Conf. Computer Vision and Pattern Recognition, 2011, pp. 625632.
    50. 50)
      • 10. Yang, M., Zhang, L., Feng, X., Zhang, D.: ‘Fisher discrimination dictionary learning for sparse representation’. IEEE Int. Conf. Computer Vision, 2011, pp. 543550.
    51. 51)
      • 34. Ranzato, M., Boureau, Y.-L., LeCun, Y.: ‘Sparse feature learning for deep belief networks’. NIPS, 2007.
    52. 52)
      • 4. Ali, T., Veldhuis, R., Spreeuwers, L.: ‘Forensic face recognition: a survey’. Technical report TR-CTIT-10-40, Centre for Telematics and Information Technology, University of Twente, December 2010.
    53. 53)
      • 47. Wong, Y., Chen, S., Mau, S., Sanderson, C., Lovell, B.C.: ‘Patch-based probabilistic image quality assessment for face selection and improved video-based face recognition’. Computer Vision and Pattern Recognition Workshops (CVPRW), 2011, pp. 7481.
    54. 54)
      • 45. Martínez, A., Benavente, R.: ‘The AR face database’. CVC Technical Report 24, Computer Vision Center, Universitat Autónoma de Barcelona, June 1998.
    55. 55)
      • 15. Torralba, A., Shina, P.: ‘Detecting faces in improverished images’. Technical Report 028, MIT AI Lab, 2001.
    56. 56)
      • 16. Rodriguez, Y., Cardinaux, F., Bengio, S., Mariéthoz, J.: ‘Measuring the performance of face localization systems’, Image Vis. Comput., 2006, 24, (8), pp. 882893 (doi: 10.1016/j.imavis.2006.02.012).
    57. 57)
      • 36. Reynolds, D.A.: ‘Gaussian mixture models’. Encyclopedia of Biometrics, 2009, pp. 659663.
    58. 58)
      • 38. Duda, R.O., Hart, P.E., Stork, D.G.: ‘Pattern classification’ (Wiley, 2001, 2nd edn.).
    59. 59)
      • 44. Phillips, P.J., Wechsler, H., Huang, J., Rauss, P.J.: ‘The FERET database and evaluation procedure for face-recognition algorithms’, Image Vis. Comput., 1998, 16, (5), pp. 295306 (doi: 10.1016/S0262-8856(97)00070-X).
    60. 60)
      • 11. Fisher, R.A.: ‘The use of multiple measurements in taxonomic problems’, Annals Eugen., 1936, 7, pp. 179188 (doi: 10.1111/j.1469-1809.1936.tb02137.x).
    61. 61)
      • 3. Doddington, G.R., Przybocki, M.A., Martin, A.F., Reynolds, D.A.: ‘The NIST speaker recognition evaluation – overview, methodology, systems, results, perspective’, Speech Commun., 2000, 31, (2-3), pp. 225254 (doi: 10.1016/S0167-6393(99)00080-1).
    62. 62)
      • 37. Bishop, C.M.: ‘Pattern recognition and machine learning’ (Springer, 2006).
    63. 63)
      • 39. Gonzalez, R., Woods, R.: ‘Digital image processing’ (Prentice-Hall, 2007, 3rd edn.).
    64. 64)
      • 26. Wong, Y., Harandi, M.T., Sanderson, C., Lovell, B.C.: ‘On robust biometric identity verification via sparse enbcoding of faces: holistic vs local approaches’. IEEE Int. Joint Conf. Neural Networks, 2012, pp. 17621769.
    65. 65)
      • 18. Heisele, B., Ho, P., Wu, J., Poggio, T.: ‘Face recognition: component-based versus global approaches’, Comput. Vis. Image Underst., 2003, 91, (1-2), pp. 621 (doi: 10.1016/S1077-3142(03)00073-0).
    66. 66)
      • 27. Tropp, J.A., Wright, S.J.: ‘Computational methods for sparse solution of linear inverse problems’, Proc. IEEE, 2010, 98, (6), pp. 948958 (doi: 10.1109/JPROC.2010.2044010).
    67. 67)
      • 32. Tropp, J.A., Gilbert, A.C., Strauss, M.J.: ‘Algorithms for simultaneous sparse approximation. Part I: greedy pursuit’, Signal Process., 2006, 86, (3), pp. 572588 (doi: 10.1016/j.sigpro.2005.05.030).
    68. 68)
      • 21. Ekenel, H.K., Stiefelhagen, R.: ‘Local appearance based face recognition using discrete cosine transform’. European Signal Processing Conf., 2005.
    69. 69)
      • 43. Bruckstein, A.M., Elad, M., Zibulevsky, M.: ‘On the uniqueness of nonnegative sparse solutions to underdetermined systems of equations’, IEEE Trans. Inf. Theory, 2008, 54, (11), pp. 48134820 (doi: 10.1109/TIT.2008.929920).
    70. 70)
      • 19. Sanderson, C., Bengio, S., Gao, Y.: ‘On transforming statistical models for non-frontal face verification’, Pattern Recognit., 2006, 39, (2), pp. 288302 (doi: 10.1016/j.patcog.2005.07.001).
    71. 71)
      • 53. Chen, S., Mau, S., Harandi, M.T., Sanderson, C., Bigdeli, A., Lovell, B.C.: ‘Face recognition from still images to video sequences: a local-feature-based framework’, EURASIP J. Image Video Process., 2011, 2011.
    72. 72)
      • 28. Chen, S.S., Donoho, D.L., Saunders, M.A.: ‘Atomic decomposition by basis pursuit’, SIAM Rev., 2001, 43, (1), pp. 129159 (doi: 10.1137/S003614450037906X).
    73. 73)
      • 2. Belhumeur, 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. 711720 (doi: 10.1109/34.598228).
    74. 74)
      • 25. Coates, A., Lee, H., Ng, A.Y.: ‘An analysis of single-layer networks in unsupervised feature learning’, J. Mach. Learn. Res., Proc. Track, 2011, 15, pp. 215223.
    75. 75)
      • 7. Yang, J., Zhang, L., Xu, Y., Yang, J.-Y.: ‘Beyond sparsity: the role of l1-optimizer in pattern classification’, Pattern Recognit., 2012, 45, (3), pp. 11041118 (doi: 10.1016/j.patcog.2011.08.022).
    76. 76)
      • 14. Turk, M., Pentland, A.: ‘Eigenfaces for recognition’, J. Cognitive Neurosci., 1991, 3, (1), pp. 7186 (doi: 10.1162/jocn.1991.3.1.71).
    77. 77)
      • 12. Shi, Q., Eriksson, A., van den Hengel, A., Shen, C.: ‘Is face recognition really a compressive sensing problem?IEEE Conf. Computer Vision and Pattern Recognition, 2011, pp. 553560.
    78. 78)
      • 13. Harandi, M.T., Ahmadabadi, M.N., Araabi, B.N.: ‘Optimal local basis: a reinforcement learning approach for face recognition’, Int. J. Comput. Vis., 2009, 81, (2), pp. 191204 (doi: 10.1007/s11263-008-0161-5).
    79. 79)
      • 49. Bengio, S., Mariéthoz, J.: ‘The expected performance curve: a new assessment measure for person authentication’. Proc. Odyssey 2004: The Speaker and Language Recognition Workshop, 2004, pp. 279284.
    80. 80)
      • 41. Lee, K.-C., Ho, J., Kriegman, D.J.: ‘Acquiring linear subspaces for face recognition under variable lighting’, IEEE Trans. Pattern Anal. Mach. Intell., 2005, 27, (5), pp. 684698 (doi: 10.1109/TPAMI.2005.92).
    81. 81)
      • 5. Tu, P.H., Doretto, G., Krahnstoever, N.O., et al: ‘An intelligent video framework for homeland protection’. Proc. SPIE Defence and Security Symp. – Unattended Ground, Sea, and Air Sensor Technologies and Applications IX, 2007, vol. 6562.
    82. 82)
      • 22. Csurka, G., Dance, C.R., Fan, L., Willamowski, J., Bray, C.: ‘Visual categorization with bags of key points’. In Workshop on Statistical Learning in Computer Vision, ECCV, 2004, pp. 122.
    83. 83)
      • 31. Rubinstein, R., Bruckstein, A.M., Elad, M.: ‘Dictionaries for sparse representation modeling’, Proc. IEEE, 2010, 98, (6), pp. 10451057 (doi: 10.1109/JPROC.2010.2040551).
    84. 84)
      • 23. Lazebnik, S., Schmid, C., Ponce, J.: ‘Beyond bags of features: spatial pyramid matching for recognizing natural scene categories’. IEEE Conf. Computer Vision and Pattern Recognition, 2006, pp. 21692178.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-bmt.2013.0033
Loading

Related content

content/journals/10.1049/iet-bmt.2013.0033
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading