access icon free Genetic algorithm-optimised structure of convolutional neural network for face recognition applications

© The Institution of Engineering and Technology
Received 26/01/2015, Accepted 08/02/2016, Revised 16/01/2016, Published 12/02/2016

Proposing a proper method for face recognition is still a challenging subject in biometric and computer vision applications. Although some reliable systems were introduced under relatively controlled conditions, their recognition rate is not satisfactory in the general settings. This is especially true when there are variations in pose, illumination, and facial expression. To alleviate these problems, a hybrid face recognition system is proposed which benefits from the superiority of both convolutional neural network (CNN) and support vector machine (SVM). To this end, first a genetic algorithm is employed to find the optimum structure of CNN. Then, the performance of the system is improved by replacing the last layer of CNN with an ensemble of SVMs. Finally, using concepts of error correction, decision is made. The potential of CNN as a trainable feature extractor provides a flexible recognition system that can recognise faces with variations in pose and illumination. Simulation results show that the system achieves good recognition rate and is robust against variations in terms of facial expressions, occlusion, noise, and illuminations.

Inspec keywords: neural nets; genetic algorithms; support vector machines; face recognition

Other keywords: flexible recognition system; facial expressions; CNN; convolutional neural network; face recognition; error correction; computer vision; occlusion; genetic algorithm-optimised structure; support vector machine; biometric

Subjects: Optimisation techniques; Computer vision and image processing techniques; Optimisation techniques; Neural computing techniques; Knowledge engineering techniques; Image recognition

References

    1. 1)
      • 44. Chang, C.-C., Lin, C.-J.: ‘LIBSVM: a library for support vector machines’, ACM Trans. Intell. Syst. Technol. (TIST), 2011, 2, (3), p. 27.
    2. 2)
      • 51. Singha, A., Bhowmik, M.K., Dhar, P., et al: ‘Analysis and performance evaluation of ica-based architectures for face recognition’, in Barneva, Reneta P., Bhattacharya, Bhargab B., Brimkov, Valentin E. (Eds.): ‘Combinatorial image analysis’ (Springer, 2015).
    3. 3)
      • 6. Heisele, B., Ho, P., Wu, J., et al: ‘Face recognition: component-based versus global approaches’, Comput. Vis. Image Underst., 2003, 91, (1), pp. 6–21.
    4. 4)
      • 24. Belhumeur, P.N., Hespanha, J.P., Kriegman, D.: ‘Eigenfaces vs. Fisherfaces: recognition using class specific linear projection’, IEEE Trans. Pattern Anal. Mach. Intell., 1997, 19, (7), pp. 711–720.
    5. 5)
      • 2. Hassaballah, M., Aly, S.: ‘Face recognition: challenges, achievements and future directions’, IET Comput. Vis., 2015, 9, (4), pp. 614–626.
    6. 6)
      • 31. Heisele, B., Serre, T., Pontil, M., et al: ‘Component-based face detection’. Computer Vision and Pattern Recognition, 2001. CVPR 2001. Proc. of the 2001 IEEE Computer Society Conf. on, 2001).
    7. 7)
      • 43. Duda, R.O., Hart, P.E., Stork, D.G.: ‘Pattern classification’ (John Wiley & Sons, 2012).
    8. 8)
      • 8. Penev, P.S., Atick, J.J.: ‘Local feature analysis: a general statistical theory for object representation’, Netw., Comput. Neural Syst., 1996, 7, (3), pp. 477–500.
    9. 9)
      • 38. Ramadan, R.M., Abdel-Kader, R.F.: ‘Face recognition using particle swarm optimization-based selected features’, Int. J. Signal Process. Image Process. Pattern Recognit., 2009, 2, (2), pp. 51–65.
    10. 10)
      • 26. Visani, M., Garcia, C., Jolion, J.-M.: ‘Normalized radial basis function networks and bilinear discriminant analysis for face recognition’. IEEE Conf. on Advanced Video and Signal Based Surveillance, 2005. AVSS 2005, 2005.
    11. 11)
      • 19. Ding, C., Tao, D.: ‘Robust face recognition via multimodal deep face representation’, IEEE Trans. Multimedia, 2015, 17, (11), pp. 2049–2058.
    12. 12)
      • 39. Sarawat Anam, M., Islam, S., Kashem, M., et al: ‘Face recognition using genetic algorithm and back propagation neural network’. Proc. of the Int. Multi Conf. of Engineers and Computer Scientists, 2009.
    13. 13)
      • 32. Mandal, S., Dhara, B.C.: ‘A hybrid face recognition method based on structural and holistic features’. Seventh Int. Conf. on Advances in Pattern Recognition, 2009. ICAPR'09, 2009.
    14. 14)
      • 1. Senior, A.W., Bolle, R.M.: ‘Face recognition and its application’, in Zhang, David D. (Ed.): ‘Biometric solutions’ (Springer, 2002).
    15. 15)
      • 13. Duffner, S., Garcia, C.: ‘Face recognition using non-linear image reconstruction’. IEEE Conf. Advanced Video and Signal Based Surveillance, 2007. AVSS 2007, 2007.
    16. 16)
      • 42. De Jong, K.A.: ‘Analysis of the behavior of a class of genetic adaptive systems’, 1975.
    17. 17)
      • 47. Dietterich, T.G., Bakiri, G.: ‘Solving multiclass learning problems via error-correcting output codes’, J. Artif. Intell. Res., 1995, 2, pp. 263–286.
    18. 18)
      • 27. Cevikalp, H., Neamtu, M., Wilkes, M., et al: ‘Discriminative common vectors for face recognition’, IEEE Trans. Pattern Anal. Mach. Intell., 2005, 27, (1), pp. 4–13.
    19. 19)
      • 16. Schroff, F., Kalenichenko, D., Philbin, J.: ‘Facenet: a unified embedding for face recognition and clustering’, arXiv preprint arXiv:1503.03832, 2015.
    20. 20)
      • 20. Ding, C., Choi, J., Tao, D., et al: ‘Multi-directional multi-level dual-cross patterns for robust face recognition’, arXiv preprint arXiv:1401.5311, 2014.
    21. 21)
      • 34. Ghasemzadeh, H., Khass, M.T., Arjmandi, M.K.: ‘Audio steganalysis based on reversed psychoacoustic model of human hearing’, Digital Signal Process., 2016, 51, pp. 133–141.
    22. 22)
      • 12. Abdullah, M.F.A., Sayeed, M.S., Muthu, K.S., et al: ‘Face recognition with symmetric local graph structure (SLGS)’, Expert Syst. Appl., 2014, 41, (14), pp. 6131–6137.
    23. 23)
      • 45. Hurwitz, J.S.: ‘Error-correcting codes and applications to large scale classification systems’ (Massachusetts Institute of Technology, 2009).
    24. 24)
      • 5. Takacs, B.: ‘Comparing face images using the modified Hausdorff distance’, Pattern Recognit., 1998, 31, (12), pp. 1873–1881.
    25. 25)
      • 48. Ferng, C.-S., Lin, H.-T.: ‘Multilabel classification using error-correcting codes of hard or soft bits’, IEEE Trans. Neural Netw. Learn. Syst., 2013, 24, (11), pp. 1888–1900.
    26. 26)
      • 30. Pentland, A., Moghaddam, B., Starner, T.: ‘View-based and modular eigenspaces for face recognition’. Computer Vision and Pattern Recognition, 1994. Proc. CVPR'94, 1994 IEEE Computer Society Conf. on, 1994.
    27. 27)
      • 50. Emambakhsh, M., Gao, J., Evans, A.: ‘Noise modelling for denoising and 3d face recognition algorithms performance evaluation’, IET Comput. Vis., 2015, 28, (9), pp. 1519–1524.
    28. 28)
      • 37. Ghasemzadeh, H.: ‘A metaheuristic approach for solving Jigsaw puzzles’. Iranian Conf. on Intelligent Systems (ICIS), 2014, 2014.
    29. 29)
      • 28. Cootes, T.F., Edwards, G.J., Taylor, C.J.: ‘Active appearance models’, IEEE Trans. Pattern Anal. Mach. Intell., 2001, 23, (6), pp. 681–685.
    30. 30)
      • 21. Ojala, T., Pietikäinen, M., Harwood, D.: ‘A comparative study of texture measures with classification based on featured distributions’, Pattern Recognit., 1996, 29, (1), pp. 51–59.
    31. 31)
      • 9. Samaria, F.S., Harter, A.C.: ‘Parameterisation of a stochastic model for human face identification’. Proc. of the Second IEEE Workshop on Applications of Computer Vision, 1994, 1994.
    32. 32)
      • 15. Taigman, Y., Yang, M., Ranzato, M.A., et al: ‘Web-scale training for face identification’, arXiv preprint arXiv:1406.5266, 2014.
    33. 33)
      • 54. Qu, X., Kim, S., Cui, R., et al: ‘Linear collaborative discriminant regression classification for face recognition’, J. Visual Commun. Image Represent., 2015, 31, pp. 312–319.
    34. 34)
      • 4. Brunelli, R., Poggio, T.: ‘Face recognition: features versus templates’, IEEE Trans. Pattern Anal. Mach. Intell., 1993, 15, (10), pp. 1042–1052.
    35. 35)
      • 40. Gen, M., Cheng, R.: ‘Genetic algorithms and engineering optimization’ (John Wiley & Sons, 2000).
    36. 36)
      • 46. Ghani, R.: ‘Using error-correcting codes for text classification’. ICML, 2000.
    37. 37)
      • 35. Ghasemzadeh, H., Khass, M.T., Arjmandi, M.K., et al: ‘Detection of vocal disorders based on phase space parameters and Lyapunov spectrum’, Biomed. Signal Process. Control, 2015, 22, pp. 135–145.
    38. 38)
      • 41. Blickle, T., Thiele, L.: ‘A comparison of selection schemes used in genetic algorithms’. TIK-Report, 1995.
    39. 39)
      • 3. Ding, C., Tao, D.: ‘A comprehensive survey on pose-invariant face recognition’, arXiv preprint arXiv:1502.04383, 2015.
    40. 40)
      • 7. Price, J.R., Gee, T.F.: ‘Face recognition using direct, weighted linear discriminant analysis and modular subspaces’, Pattern Recognit., 2005, 38, (2), pp. 209–219.
    41. 41)
      • 11. Abusham, E.A.: ‘Face verification using local graph structure (LGS)’. Int. Symp. on Biometrics and Security Technologies (ISBAST), 2014, 2014.
    42. 42)
      • 18. Zhang, Y., Zhao, D., Sun, J., et al: ‘Adaptive convolutional neural network and it's application in face recognition’, Neural Process. Lett., 2015, pp. 1–11.
    43. 43)
      • 52. Huang, R., Pavlovic, V., Metaxas, D.N.: ‘A hybrid face recognition method using Markov random fields’. Proc. of the 17th Int. Conf. on Pattern Recognition, 2004. ICPR 2004, 2004.
    44. 44)
      • 25. Bartlett, M.S., Movellan, J.R., Sejnowski, T.J.: ‘Face recognition by independent component analysis’, IEEE Trans. Neural Netw., 2002, 13, (6), pp. 1450–1464.
    45. 45)
      • 55. Chen, X., Fan, K., Liu, W., et al: ‘Discriminative structure discovery via dimensionality reduction for facial image manifold’, Neural Comput. Appl., 2015, 26, (2), pp. 373–381.
    46. 46)
      • 10. Perronnin, F., Dugelay, J.-L., Rose, K.: ‘A probabilistic model of face mapping with local transformations and its application to person recognition’, IEEE Trans. Pattern Anal. Mach. Intell., 2005, 27, (7), pp. 1157–1171.
    47. 47)
      • 23. Turk, M.A., Pentland, A.P.: ‘Face recognition using eigenfaces’. Computer Vision and Pattern Recognition, 1991. Proc. CVPR'91, IEEE Computer Society Conf. on, 1991.
    48. 48)
      • 29. Liu, Y.-H., Chen, Y.-T.: ‘Face recognition using total margin-based adaptive fuzzy support vector machines’, IEEE Trans. Neural Netw., 2007, 18, (1), pp. 178–192.
    49. 49)
      • 33. Liu, Z., Liu, C.: ‘Fusion of color, local spatial and global frequency information for face recognition’, Pattern Recognit., 2010, 43, (8), pp. 2882–2890.
    50. 50)
      • 14. Taigman, Y., Yang, M., Ranzato, M.A., et al: ‘Deepface: closing the gap to human-level performance in face verification’. IEEE Conf. Computer Vision and Pattern Recognition (CVPR), 2014, 2014.
    51. 51)
      • 36. LeCun, Y., Bottou, L., Bengio, Y., et al: ‘Gradient-based learning applied to document recognition’, Proc. IEEE, 1998, 86, (11), pp. 2278–2324.
    52. 52)
      • 22. Wiskott, L., Fellous, J.-M., Kuiger, N., et al: ‘Face recognition by elastic bunch graph matching’, IEEE Trans. Pattern Anal. Mach. Intell., 1997, 19, (7), pp. 775–779.
    53. 53)
      • 53. Liu, Z., Pu, J., Xu, M., et al: ‘Face recognition via weighted two phase test sample sparse representation’, Neural Process. Lett., 2015, 41, (1), pp. 43–53.
    54. 54)
      • 49. Berger, A.: ‘Error-correcting output coding for text classification’. IJCAI-99: Workshop on Machine Learning for Information Filtering, 1999.
    55. 55)
      • 17. Zhou, E., Cao, Z., Yin, Q.: ‘Naive-deep face recognition: touching the limit of LFW benchmark or not?’, arXiv preprint arXiv:1501.04690, 2015.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-cvi.2015.0037
Loading

Related content

content/journals/10.1049/iet-cvi.2015.0037
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading