Facial hyperspectral image analysis has become a popular topic since it provides additional spectral information on subjects unlike the 2D face imagery which only has spatial information, hence it has an opportunity to improve face recognition accuracy. Three new methods for feature extraction for facial hyperspectral image classification are proposed. The methods employ a three-dimensional discrete wavelet transform (3D-DWT) to extract features from facial hyperspectral images. One of the advantages of 3D-DWT for feature extraction in hyperspectral images is that the horizontal, vertical and spectral information are processed in parallel. The most important characteristic of 3D-DWT is decomposing hyperspectral images into a set of spatio-spectral frequency subbands. The study proposes three methods using 3D-DWT for feature extraction: 3D-subband energy, 3D-subband overlapping cube and 3D-global energy. The k-NN and collaborative representation-based classifier (CRC) are used to process extracted feature vector datasets, where classification accuracies are evaluated by four test scenarios. The results under different test scenarios revealed that accuracy of proposed 3D-DWT methods is superior to alternative methods using spatio-spectral classification.

References

1. 1)
  - 20. Weeks, M.C.: ‘Architectures for the 3-D discrete wavelet transform’. PhD thesis, The University of Southwestern Louisiana, 1998.
2. 2)
  - 24. Guo, X., Huang, X., Zhang, L.: ‘Three-dimensional wavelet texture feature extraction and classification for multi/hyperspectral imagery’, IEEE Geosci. Remote Sens. Lett., 2014, 11, (12), pp. 2183–2187.
3. 3)
  - 2. Pan, Z., Healy, G., Prasad, M., et al: ‘Face recognition in hyperspectral images’, IEEE Trans. Pattern Anal. Mach. Intell., 2003, 25, (12), pp. 1552–1560.
4. 4)
  - 8. PolyU-HSFD. Available at http://www.comp.polyu.edu.hk/~biometrics/hyper_face.htm, accessed 13 November 2015.
5. 5)
  - 23. Lustig, M., Donoho, D., Pauly, J.M.: ‘Sparse MRI: the application of compressed sensing for rapid MR imaging’, Magn. Reson. Med., 2007, 58, (6), pp. 1182–1195.
6. 6)
  - 4. Igarashi, T., Nishino, K., Nayar, S.K.: ‘The appearance of human skin: a survey’, Found. Trends Comput. Graph. Vis., 2007, 3, (1), pp. 1–95.
7. 7)
  - 18. Khan, Z., Shafait, F., Mian, A.: ‘Joint group sparse PCA for compressed hyperspectral imaging’, IEEE Image Process., 2015, 24, (12), pp. 4934–4942.
8. 8)
  - 11. Liang, J., Zhou, J., Gao, Y.: ‘3D local derivative pattern for hyperspectral face recognition’. 11th IEEE Int. Conf. Workshops on Automatic Face and Gesture Recognition (FG), 2015.
9. 9)
  - 6. Pan, Z., Healey, G., Tromberg, B.: ‘Comparison of spectral-only and spectral/spatial face recognition for personal identity verification’, EURASIP J. Adv Signal Process., 2009, 2009, (1), pp. 1–6.
10. 10)
  - 13. Cho, W., Jang, J., Koschan, A., et al: ‘Hyperspectral face recognition using improved inter-channel alignment based on qualitative prediction models’, Opt. Express, 2016, 24, (24), pp. 27637–27662.
11. 11)
  - 10. Uzair, M., Mahmood, A., Mian, A.: ‘Hyperspectral face recognition with spatiospectral information fusion and PLS regression’, IEEE Trans. Image Process., 2015, 24, (3), pp. 1127–1137.
12. 12)
  - 22. Yoo, H.Y., Lee, K., Kwon, B.: ‘Application of the 3D discrete wavelet transformation scheme to remotely sensed image classification’, Korean J. Remote Sens., 2007, 23, (5), pp. 355–363.
13. 13)
  - 17. CMU-HSFD. Available at http://www.consortium.ri.cmu.edu/hsagree/index.cgi, accessed 16 May 2016.
14. 14)
  - 26. Wandishin, M.S., Mullen, S.J.: ‘Multiclass ROC analysis’, Weather Forecast., 2009, 24, (2), pp. 530–547.
15. 15)
  - 14. Sharma, V., Diba, A., Tuytelaars, T., et al: ‘Hyperspectral CNN for image classification & band selection, with application to face recognition’. Technical Report: KUL/ESAT/PSI/1604, 2016.
16. 16)
  - 9. Uzair, M., Mahmood, A., Mian, A.: ‘Hyperspectral face recognition using 3D-DCT and partial least squares’. IEEE BMVC, 2013.
17. 17)
  - 5. Di, W., Zhang, L., Zhang, D., et al: ‘Studied on hyperspectral face recognition in visible spectrum with feature band selection’, IEEE Trans. Syst. Man Cybern A, 2010, 40, (6), pp. 1354–1361.
18. 18)
  - 19. Weeks, M., Bayoumi, M.A.: ‘Three-dimensional discrete wavelet transform architectures’, IEEE Trans. Signal Process., 2002, 50, (8), pp. 2050–2063.
19. 19)
  - 12. Chen, G., Sun, W., Xie, W.: ‘Hyperspectral face recognition with log-polar Fourier features and collaborative representation based voting classifiers’, IET Biomet., 2017, 6, (1), pp. 36–42.
20. 20)
  - 25. Ghasemzadeh, A., Demirel, H.: ‘Hyperspectral face recognition using 3D discrete wavelet transform’. IPTA, 2016.
21. 21)
  - 7. Vartak, P., Bharadi, V.: ‘Hyperspectral face recognition by texture feature extraction using hybrid wavelets type I & II and Kekre wavelet transform’. Int. Conf. Computing Control and Automation, 2015.
22. 22)
  - 1. Shen, L., Zheng, S.: ‘Hyperspectral face recognition using 3D Gabor wavelets’. Int. Conf. Pattern Recognition, 2012, pp. 1127–1137.
23. 23)
  - 3. Zhao, W., Chellappa, R., Phillips, P., et al: ‘Face recognition: a literature survey’, ACM Comput. Surv., 2003, 35, (4), pp. 399–458.
24. 24)
  - 16. Wang, H., Bau, T.C., Healey, G.: ‘Expression-invariant face recognition in hyperspectral images’, Opt. Eng., 2014, 53, (10), pp. 103102–103102.
25. 25)
  - 15. Sharma, V., Van Gool, L.: ‘Image-level classification in hyperspectral images using feature descriptors, with application to face recognition’, arXiv preprint arXiv: 1605.03428, 2016.
26. 26)
  - 27. Chen, G., Li, Ch., Sun, W.: ‘Hyperspectral face recognition via feature extraction and CRC-based classifier’, IET Image Process., 2017, 11, (4), pp. 266–272.
27. 27)
  - 21. Hsiang, S.T., Woods, J.W.: ‘Embedded video coding using invertible motion compensated 3-D subband/wavelet filter bank’, Signal Process. Image Commun., 2001, 16, (8), pp. 705–724.

3D discrete wavelet transform-based feature extraction for hyperspectral face recognition

References

Related content