Abstract
Deep feature is widely applied in many fields such as image retrieval, image classification, face verification, etc. All the post-processing methods using deep feature make some assumptions about feature distribution. However, in most situations, features do not follow the hypothesised distribution approximately. In this paper, we focus on face-verification applications which also suffer from these problems. We propose an up-sample method called IUSM to alleviate the problems caused by biased samples. Additionally, by analyzing the Joint Bayesian model theoretically and practically, we propose a feature fusion method called LFF which utilizes the distribution properties of Joint Bayesian. Based on IUSM, the face verification accuracy of biased data is improved by 6 % while generalization ability of convolution network is not crippled. On the widely used Labeled Face in the Wild(LFW) dataset, LFF method can slightly improve the accuracy 0.15 % while the baseline accuracy is more than 97.51 %. We also argue that LFF can improve each deep face verification algorithm which uses Joint Bayesian model due to LFF’s linear combination of features.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Ahonen, T., Hadid, A., Pietikainen, M.: Face description with local binary patterns: application to face recognition. IEEE Trans. Pattern Anal. Mach. Intell. 28(12), 2037–2041 (2006)
Berry, J., Fasel, I., Fadiga, L., Archangeli, D.: Training deep nets with imbalanced and unlabeled data. In: INTERSPEECH (2012)
Cao, X., Wipf, D., Wen, F., Duan, G., Sun, J.: A practical transfer learning algorithm for face verification. In: 2013 IEEE International Conference on Computer Vision (ICCV), pp. 3208–3215. IEEE (2013)
Chen, D., Cao, X., Wang, L., Wen, F., Sun, J.: Bayesian face revisited: a joint formulation. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012, Part III. LNCS, vol. 7574, pp. 566–579. Springer, Heidelberg (2012)
Ciresan, D., Meier, U., Schmidhuber, J.: Multi-column deep neural networks for image classification. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3642–3649. IEEE (2012)
Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005, vol. 1, pp. 886–893. IEEE (2005)
Guan, S., Chen, M., Ha, H.Y., Chen, S.C., Shyu, M.L., Zhang, C.: Deep learning with MCA-based instance selection and bootstrapping for imbalanced data classification. In: First IEEE International Conference on Collaboration and Internet Computing (CIC) (2015)
Guo, X., Yin, Y., Dong, C., Yang, G., Zhou, G.: On the class imbalance problem. In: 2008 Fourth International Conference on Natural Computation, ICNC 2008, vol. 4, pp. 192–201. IEEE (2008)
Huang, G.B., Ramesh, M., Berg, T., Learned-Miller, E.: Labeled faces in the wild: a database for studying face recognition in unconstrained environments. Technical report 07–49, University of Massachusetts, Amherst (2007)
Ke, Y., Sukthankar, R.: PCA-SIFT: A more distinctive representation for local image descriptors. In: Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2004, vol. 2, pp. II-506–II-513. IEEE (2004)
Krizhevsky, A., Sutskever, I., Hinton, G.E.: Image net classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 1097–1105 (2012)
Mathai, A.M., Provost, S.B.: Quadratic forms in random variables: theory and applications. J. Am. Stat. Assoc. (1992)
Miller, D., Kemelmacher-Shlizerman, I., Seitz, S.M.: Megaface: a million faces for recognition at scale (2015). arXiv:1505.02108
Monard, M.C., Batista, G.E.: Learmng with skewed class distrihutions. In: Advances in Logic, Artificial Intelligence, and Robotics: LAPTEC 2002, vol. 85, p. 173 (2002)
Schroff, F., Kalenichenko, D., Philbin, J.: Facenet: a unified embedding for face recognition and clustering (2015). arXiv:1503.03832
Sun, Y., Chen, Y., Wang, X., Tang, X.: Deep learning face representation by joint identification-verification. In: Advances in Neural Information Processing Systems, pp. 1988–1996 (2014)
Sun, Y., Liang, D., Wang, X., Tang, X.: Deepid3: face recognition with very deep neural networks (2015). arXiv:1502.00873
Sun, Y., Wang, X., Tang, X.: Deep learning face representation from predicting 10,000 classes. In: 2014 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1891–1898. IEEE (2014)
Yi, D., Lei, Z., Liao, S., Li, S.Z.: Learning face representation from scratch (2014). arXiv:1411.7923
Yu, H., Yang, J.: A direct lda algorithm for high-dimensional data with application to face recognition. Pattern Recogn. 34(10), 2067–2070 (2001)
Zhou, E., Cao, Z., Yin, Q.: Naive-deep face recognition: touching the limit of LFW benchmark or not? (2015). arXiv:1501.04690
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer International Publishing Switzerland
About this paper
Cite this paper
Qu, Z., Li, X., Dou, Y., Yang, K. (2016). Face Verification Algorithm with Exploiting Feature Distribution. In: Booth, R., Zhang, ML. (eds) PRICAI 2016: Trends in Artificial Intelligence. PRICAI 2016. Lecture Notes in Computer Science(), vol 9810. Springer, Cham. https://doi.org/10.1007/978-3-319-42911-3_33
Download citation
DOI: https://doi.org/10.1007/978-3-319-42911-3_33
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-42910-6
Online ISBN: 978-3-319-42911-3
eBook Packages: Computer ScienceComputer Science (R0)