Unsupervised feature learning via prior information-based similarity metric learning for face verification
- Author(s): HongZhong Tang 1, 2, 3 ; Xiao Li 1, 3 ; Xiang Wang 1, 3 ; Lizhen Mao 1, 3 ; Ling Zhu 1, 3
-
-
View affiliations
-
Affiliations:
1:
College of Information Engineering , Xiangtan University , Xiangtan 411105 , People's Republic of China ;
2: College of Electrical and Information Engineering , Hunan University , Changsha 410082 , People's Republic of China ;
3: Key Laboratory of Intelligent Computing & Information Processing of Ministry of Education , Xiangtan University , Xiangtan 411105 , People's Republic of China
-
Affiliations:
1:
College of Information Engineering , Xiangtan University , Xiangtan 411105 , People's Republic of China ;
- Source:
Volume 12, Issue 8,
October
2018,
p.
966 – 974
DOI: 10.1049/iet-spr.2017.0017 , Print ISSN 1751-9675, Online ISSN 1751-9683
Here, an efficient framework is developed to address the problem of unconstrained face verification. In particular, an unsupervised feature learning method for face image representation and a novel similarity metric model are discussed. First, the authors propose an unsupervised feature learning method with sparse auto-encoder (SAE) based on local descriptor (SAELD). A set of filter operators are learned based on SAE model from local patches, and face descriptors are extracted by applying the set of filter operators to convolve images. This can address the face discriminative representation issue of unconstrained face verification. Then pairwise SAELD descriptors are projected into the weighted subspace. Furthermore, a prior information-based similarity metric learning model is presented, in which the metric matrix is learned by enforcing a regularisation term based on the prior similar and discriminative information. This idea can improve the robustness to intra-personal variations and discrimination to inter-personal variations. Experimental results show that the proposed method has competitive performance compared with several state-of-the-art methods on challenging labelled faces in the wild data set.
Inspec keywords: image representation; unsupervised learning; face recognition; matrix algebra
Other keywords: sparse auto-encoder based on local descriptor; face image representation; prior information-based similarity metric learning; face discriminative representation; face verification; metric matrix; unsupervised feature learning method; SAELD
Subjects: Image recognition; Knowledge engineering techniques; Algebra; Computer vision and image processing techniques; Algebra
References
-
-
1)
-
9. Nguyen, H.V., Bai, L.: ‘Cosine similarity metric learning for face verification’. Proc. Int. Conf. Computer Vision ACCV, 2011, pp. 709–720.
-
-
2)
-
34. Wright, J., Yang, A. Y., Ganesh, A., et al: ‘Robust face recognition via sparse representation’, IEEE Trans. Pattern Anal. Mach. Intell., 2009, 31, (2), pp. 210–227.
-
-
3)
-
21. Ahonen, T., Hadid, A., Pietikainen, M.: ‘Face recognition with local binary patterns’. Proc. Int. Conf. Computer Vision, 2004, pp. 469–481.
-
-
4)
-
20. Blanton, A., Allen, K.C., Miller, T., et al: ‘A comparison of human and automated face verification accuracy on unconstrained image sets’. Proc. Int. Conf. Computer Vision and Pattern Recognition Workshops, 2016, pp. 161–168.
-
-
5)
-
2. Hua, G., Viola, P., Drucker, S.M.: ‘Face recognition using discriminatively trained orthogonal rank one tensor projections’. Proc. Int. Conf. Computer Vision and Pattern Recognition, 2007, pp. 1–8.
-
-
6)
-
47. Cox, D., Pinto, N.: ‘Beyond simple features: a large-scale feature search approach to unconstrained face recognition’. Proc. Int. Conf. Automatic Face and Gesture Recognition and Workshops, 2011, pp. 8–15.
-
-
7)
-
8. Mignon, A., Jurie, F.: ‘PCCA: a new approach for distance learning from sparse pairwise constraints’. Proc. Int. Conf. Computer Vision and Pattern Recognition, 2012, pp. 2666–2672.
-
-
8)
-
13. Hu, J., Lu, J., Tan, Y.-P.: ‘Discriminative deep metric learning for face verification in the wild’. Proc. Int. Conf. Computer Vision and Pattern, 2014, pp. 1875–1882.
-
-
9)
-
24. Tan, X., Triggs, B.: ‘Enhanced local texture feature sets for face recognition under difficult lighting conditions’, Proc. Int. Conf. Image Process., 2010, 19, (6), pp. 1635–1650.
-
-
10)
-
3. Zhao, W., Chellappa, R., Phillips, P.J., et al: ‘Face recognition: a literature survey’. ACM Computing Surveys, 2003, pp. 399–458.
-
-
11)
-
11. Cui, Z., Li, W., Xu, D., et al: ‘Fusing robust face region descriptors via multiple metric learning for face recognition in the wild’. Proc. Int. Conf. Computer Vision and Pattern Recognition, 2013, pp. 3554–3561.
-
-
12)
-
23. Wolf, L.,, Hassner, T.,, Taigman, Y.: ‘Descriptor based methods in the wild’. Workshop on Faces in Real Life Images Detection Alignment and Recognition, 2008.
-
-
13)
-
37. Cui, Z., Shan, S., Wang, R., et al: ‘Sparsely encoded local descriptor for face verification’. Neurocomputing, 2015, 147, pp. 403–411.
-
-
14)
-
40. Zhu, X., Lei, Z., Yan, J., et al: ‘High-fidelity pose and expression normalization for face recognition in the wild’. Proc. Int. Conf. Computer Vision and Pattern Recognition, 2015, pp. 787–796.
-
-
15)
-
19. Sankaranarayanan, S., Alavi, A., Chellappa, R.: ‘Triplet similarity embedding for face verification’, 2016.
-
-
16)
-
16. Chen, J.C., Patel, V.M., Chellappa, R.: ‘Unconstrained face verification using deep CNN features’. Proc. Int. Conf. Applications of Computer Vision, 2016, pp. 1–9.
-
-
17)
-
45. 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. 711–720.
-
-
18)
-
44. Ojala, T., Pietikainen, M., Maenpaa, T.: ‘Multiresolution gray-scale and rotation invariant texture classification with local binary patterns’, IEEE Trans. Pattern Anal. Mach. Intell., 2000, 24, (7), pp. 971–987.
-
-
19)
-
29. Guillaumin, M., Verbeek, J., Schmid, C.: ‘Is that you? Metric learning approaches for face identification’. Proc. Int. Conf. Computer Vision, 2009, pp. 498–505.
-
-
20)
-
39. Hassner, T., Harel, S., Paz, E.: ‘Effective face frontalization in unconstrained images’. Proc. Int. Conf. Computer Vision and Pattern Recognition, 2015, pp. 4295–4304.
-
-
21)
-
31. Huang, G.B., Ramesh, M., Berg, T., et al: ‘Labeled faces in the wild: a database for studying face recognition in unconstrained environments’. 2007, 07-49.
-
-
22)
-
17. Chen, J.C., Zheng, J., Patel, V.M., et al: ‘Fisher vector encoded deep convolutional features for unconstrained face verification’. Proc. Int. Conf. Image Processing, 2016, pp. 2981–2985.
-
-
23)
-
36. Kan, M., Shan, S., Chang, H.: ‘Stacked progressive auto-encoders for face recognition across poses’. Proc. Int. Conf. Computer Vision and Pattern Recognition, 2014, pp. 1883–1890.
-
-
24)
-
32. Meng, X., Shan, S., Chen, X., et al: ‘Local visual primitives for face modelling and recognition’, Proc. Int. Conf. Pattern Recognit., 2006, 2, pp. 536–539.
-
-
25)
-
10. Köstinger, M., Hirzer, M., Wohlhart, P., et al: ‘Large scale metric learning from equivalence constraints’. Proc. Int. Conf. Computer Vision and Pattern Recognition, 2012, pp. 2288–2295.
-
-
26)
-
38. Lu, J., Liong, V. E., Zhou, X., et al: ‘Learning compact binary face descriptor for face recognition’, IEEE Trans. Pattern Anal. Mach. Intell., 2015, 37, (10), pp. 2041–2056.
-
-
27)
-
15. Lu, J., Wang, G., Deng, W., et al: ‘Reconstruction-based metric learning for unconstrained face verification’, IEEE Trans. Inf. Forensics Sec., 2015, 10, (1), pp. 79–89.
-
-
28)
-
1. Hua, G., Akbarzadeh, A.: ‘A robust elastic and partial matching metric for face recognition’. Proc. Int. Conf. Computer Vision, 2009, pp. 2082–2089.
-
-
29)
-
7. Guo, H., Wang, R.: ‘Face verification using sparse representations’. Proc. Int. Conf. Computer Vision and Pattern Recognition, 2012, pp. 37–44.
-
-
30)
-
33. Ahonen, T., Pietikainen, M.: ‘Image description using joint distribution of filter bank responses’, Pattern Recognit. Lett., 2009, 30, (4), pp. 368–376.
-
-
31)
-
43. Everingham, M., Sivic, J., Zisserman, A.: ‘“Hello! my name is... buffy” – automatic naming of characters in tv video’, BMVC, 2006, 57, (8), pp. 899–908.
-
-
32)
-
12. Cao, Q., Ying, Y., Li, P.: ‘Similarity metric learning for face recognition’. Proc. Int. Conf. Computer Vision, 2013, pp. 2408–2415.
-
-
33)
-
46. Wolf, L., Hassner, T., Taigman, Y.: ‘Similarity scores based on background samples’. Asian Conf. on Computer Vision, 2009, pp. 88–97.
-
-
34)
-
22. Zhang, L., Chu, R., Xiang, S., et al: ‘Face detection based on multi-block LBP representation’. Proc. Int. Conf. Advances in Biometrics, 2007, pp. 11–18.
-
-
35)
-
4. Zini, L., Noceti, N., Fusco, G., et al: ‘Structured multi-class feature selection with an application to face recognition’, Pattern Recognit. Lett., 2015, 55, pp. 35–41.
-
-
36)
-
18. Crosswhite, N., Byrne, J., Stauffer, C., et al: ‘Template adaptation for face verification and identification’. Proc. Int. Conf. Automatic Face Gesture Recognition, 2017, pp. 1–8.
-
-
37)
-
25. Lowe, D.G.: ‘Distinctive image features from scale-invariant keypoints’, Int. J. Comput. Vis., 2004, 60, (2), pp. 91–110.
-
-
38)
-
5. Cao, Z., Yin, Q., Tang, X., et al: ‘Face recognition with learning-based descriptor’. Proc. Int. Conf. Computer Vision and Pattern Recognition, 2010, pp. 2707–2714.
-
-
39)
-
27. Davis, J.V., Kulis, B., Jain, P., et al: ‘Information-theoretic metric learning’. Proc. Int. Conf. in: Machine Learning, ACM, 2007, pp. 209–216.
-
-
40)
-
14. Hu, J., Lu, J., Tan, Y.-P.: ‘Deep transfer metric learning’. Proc. Int. Conf. Computer Vision and Pattern Recognition, 2015, pp. 37–44.
-
-
41)
-
41. Hinton, G. E., Zemel, R. S.: ‘Autoencoders, minimum description length, and Helmholtz free energy’. Advances in Neural Information Processing Systems, 1994, pp. 3–3.
-
-
42)
-
26. Xing, E.P., Ng, A.Y., Jordan, M.I.: ‘Distance metric learning with application to clustering with side-information’. Adv. Neural Inf. Process. Syst., 2003, 35, (15), pp. 505–512.
-
-
43)
-
30. Ying, Y., Li, P.: ‘Distance metric learning with eigenvalue optimization’, J. Mach. Learn. Res., 2012, 13, (1), pp. 1–26.
-
-
44)
-
35. Huang, G.B., Honglak, L., Learned-Miller, E.: ‘Learning hierarchical representations for face verification with convolutional deep belief networks’. Proc. Int. Conf. Computer Vision and Pattern Recognition (CVPR), 2012, pp. 2518–2525.
-
-
45)
-
42. Taigman, Y., Wolf, L., Hassner, T.: ‘Multiple one-shots for utilizing class label information’. Proc. Int. Conf. British Mach. Vision, 2009, pp. 1–12.
-
-
46)
-
6. Lee, K.M.: ‘Component-based face detection and verification’, Pattern Recognit. Lett., 2008, 29, (3), pp. 200–214.
-
-
47)
-
28. Weinberger, K.Q., Saul, L.K.: ‘Distance metric learning for large margin nearest neighbor classification’, J. Mach. Learn. Res., 2009, 2, (10), pp. 207–244.
-
-
1)