© The Institution of Engineering and Technology
A novel method called modality-independent Kernel discriminant analysis joint sparse auto-encoder, for solving heterogeneous face recognition problem is proposed. A projection matrix to map multimodal data into a common feature space for representing cross-modal image data is first learnt. Then extend the model via sparse auto-encoder in an unsupervised manner with the combination of a regularisation term and a Kullback–Leiber divergence term. Different from classical approaches, this model does not require the data correspondences when collecting external cross-modal data. Thus, it is practical for real-world cross-modal classification problem. Experiments conducted on two heterogeneous face datasets demonstrate the effectiveness of the proposed approach.
References
-
-
1)
-
14. Tenenbaum, J.B., Freeman, W.T.: ‘Separating style and content with bilinear models’, Neural Comput., 2000, 1283, pp. 1247–1283 (doi: 10.1162/089976600300015349).
-
2)
-
7. Lei, Z., Li, S.Z.: ‘Coupled spectral regression for matching heterogeneous faces’. CVPR, Miami, Florida, USA, June 2009, pp. 1123–1128.
-
3)
-
15. Wang, X., Tang, X.: ‘Face photo-sketch synthesis and recognition’, PAMI, 2009, 31, (11), pp. 1955–1967 (doi: 10.1109/TPAMI.2008.222).
-
4)
-
13. Felix, J.X., Dipan, K.P., Marios, S.: ‘NIR-VIS heterogeneous face recognition via cross-spectral joint dictionary learning and reconstruction’. CVPR, Boston, Massachusetts, USA, June 2015, pp. 141–150.
-
5)
-
8. Sharma, A., Jacobs, D.W.: ‘Bypassing synthesis: PLS for face recognition with pose, low-resolution and sketch’. CVPR, Colorado Springs, CO, USA, June 2011, pp. 593–600.
-
6)
-
3. Choi, S.: ‘Combined features for face recognition under illumination variation’, Electron. Lett., 2016, 52, (1), pp. 31–33 (doi: 10.1049/el.2015.2936).
-
7)
-
6. Yi, D., Liu, R., Chu, R., Lei, Z., Li, S.Z.: ‘Face matching between near infrared and visible light images’. Advances in Biometrics, International Conference, Seoul, Korea, August 2007, pp. 523–530.
-
8)
-
2. Ylioninas, J., Kannala, J., Hadid, A., Pietikainen, M.: ‘Unsupervised learning of overcomplete face descriptors’. CVPRW, Boston, Massachusetts, USA, June 2015, pp. 75–83.
-
9)
-
5. Lin, D., Tang, X.: ‘Inter-modality face recognition’. ECCV, Graz, Austria, May 2006, pp. 13–26.
-
10)
-
14. Luo, W., Yang, Y., Xu, W., Fu, T.: ‘Locality-constrained sparse auto-encoder for image classification’, Signal Process. Lett., 2015, 22, (8), pp. 1070–1073 (doi: 10.1109/LSP.2014.2384196).
-
11)
-
12. Mika, R., Weston, G., Schölkopf, J., Müller, B.: ‘Fisher discriminant analysis with kernels’, in Neural Networks for Signal Processing IX, Hu, Y.-H., Larsen, J., Wilson, E., Douglas, S., Eds. Piscataway, NJ, USA, August 1999, pp. 41–48.
-
12)
-
28. Belhumeur, P., Hespanha, J., Kriegman, D.: ‘Eigenfaces vs. Fisherfaces: recognition using class specific linear projection’, IEEE Trans. Pattern Anal. Mach. Intell., 1997, 19, pp. 711–720 (doi: 10.1109/34.598228).
-
13)
-
1. Qiu, Q., Chellappa, R.: ‘Compositional dictionaries for domain adaptive face recognition’, Trans. Image Process., 2015, 24, (12), pp. 5152–5165 (doi: 10.1109/TIP.2015.2479456).
-
14)
-
4. Chen, D., Cao, X.D., Wen, F., Sun, J.: ‘Blessing of dimensionality: high-dimensional feature and its efficient compression for face verification’. CVPR, Portland, USA, June 2013, pp. 3025–3032.
-
15)
-
9. Yi, D., Liu, R., Chu, R., Lei, Z., Li, S.Z.: ‘Face matching between near infrared and visible light images’, Adv. Biometrics, Seoul, Korea, August 2007, pp. 523–530.
http://iet.metastore.ingenta.com/content/journals/10.1049/el.2016.2661
Related content
content/journals/10.1049/el.2016.2661
pub_keyword,iet_inspecKeyword,pub_concept
6
6