Article

Cosine similarity metric learning for face verification

Authors:

Hieu V. Nguyen and

Li BaiAuthors Info & Claims

ACCV'10: Proceedings of the 10th Asian conference on Computer vision - Volume Part II

November 2010

Pages 709 - 720

Published: 08 November 2010 Publication History

Abstract

Face verification is the task of deciding by analyzing face images, whether a person is who he/she claims to be. This is very challenging due to image variations in lighting, pose, facial expression, and age. The task boils down to computing the distance between two face vectors. As such, appropriate distance metrics are essential for face verification accuracy. In this paper we propose a new method, named the Cosine Similarity Metric Learning (CSML) for learning a distance metric for facial verification. The use of cosine similarity in our method leads to an effective learning algorithm which can improve the generalization ability of any given metric. Our method is tested on the state-of-the-art dataset, the Labeled Faces in the Wild (LFW), and has achieved the highest accuracy in the literature.

References

[1]

Phillips, P., Wechsler, H., Huang, J., Rauss, P.: The FERET database and evaluation procedure for face-recognition algorithms. Image and Vision Computing 16, 295-306 (1998)

[2]

Shan, S., Zhang, W., Su, Y., Chen, X., Gao, W., Frjdl, I., Cas, B.: Ensemble of Piecewise FDA Based on Spatial Histograms of Local (Gabor) Binary Patterns for Face Recognition. In: Proceedings of the 18th International Conference on Pattern Recognition, pp. 606-609 (2006)

Digital Library

[3]

Hieu, N., Bai, L., Shen, L.: Local gabor binary pattern whitened pca: A novel approach for face recognition from single image per person. In: Proceedings of the 3rd IAPR/IEEE International Conference on Biometrics (2009)

Digital Library

[4]

Shen, L., Bai, L.: MutualBoost learning for selecting Gabor features for face recognition. Pattern Recognition Letters 27, 1758-1767 (2006)

Digital Library

[5]

Shen, L., Bai, L., Fairhurst, M.: Gabor wavelets and general discriminant analysis for face identification and verification. Image and Vision Computing 27, 1758-1767 (2006)

Digital Library

[6]

Nguyen, H.V., Bai, L.: Compact binary patterns (cbp) with multiple patch classifiers for fast and accurate face recognition. In: CompIMAGE, pp. 187-198 (2010)

Digital Library

[7]

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)

[8]

Guillaumin, M., Verbeek, J., Schmid, C.: Is that you? metric learning approaches for face identification. In: International Conference on Computer Vision, pp. 498- 505 (2009)

[9]

Taigman, Y., Wolf, L., Hassner, T.: Multiple one-shots for utilizing class label information. In: The British Machine Vision Conference, BMVC (2009)

[10]

Goldberger, J., Roweis, S., Hinton, G., Salakhutdinov, R.: Neighborhood component analysis. In: NIPS

[11]

Xing, E.P., Ng, A.Y., Jordan, M.I., Russell, S.: Distance metric learning, with application to clustering with side-information. In: Advances in Neural Information Processing Systems 15, vol. 15, pp. 505-512 (2003)

[12]

Weinberger, K., Blitzer, J., Saul, L.: Distance metric learning for large margin nearest neighbor classification. In: Advances in Neural Information Processing Systems 18, pp. 1473-1480 (2006)

Digital Library

[13]

Davis, J.V., Kulis, B., Jain, P., Sra, S., Dhillon, I.S.: Information-theoretic metric learning. In: ICML 2007: Proceedings of the 24th International Conference on Machine Learning, pp. 209-216. ACM, New York (2007)

Digital Library

[14]

Wolf, L., Hassner, T., Taigman, Y.: Similarity scores based on background samples. In: Zha, H., Taniguchi, R.-i., Maybank, S. (eds.) ACCV 2009. LNCS, vol. 5995, pp. 88-97. Springer, Heidelberg (2010)

Digital Library

[15]

Ahonen, T., Hadid, A., Pietikainen, M.: Face Recognition with Local Binary Patterns. In: Guessarian, I. (ed.) LITP 1990. LNCS, vol. 469, pp. 469-481. Springer, Heidelberg (1990)

[16]

Daugman, J.: Complete Discrete 2D Gabor Transforms by Neural Networks for Image Analysis and Compression. IEEE Trans. Acoust.Speech Signal Process. 36 (1988)

[17]

Shan, S., Gao, W., Chang, Y., Cao, B., Yang, P.: Review the strength of Gabor features for face recognition from the angle of its robustness to mis-alignment. In: Proceedings of the 17th International Conference on Pattern Recognition, ICPR 2004, vol. 1 (2004)

Digital Library

[18]

Tan, X., Triggs, B.: Fusing Gabor and LBP Feature Sets for Kernel-Based Face Recognition. In: Zhou, S.K., Zhao, W., Tang, X., Gong, S. (eds.) AMFG 2007. LNCS, vol. 4778, pp. 235-249. Springer, Heidelberg (2007)

Digital Library

[19]

Zhang, W., Shan, S., Gao, W., Chen, X., Zhang, H.: Local Gabor Binary Pattern Histogram Sequence (LGBPHS): A Novel Non-Statistical Model for Face Representation and Recognition. In: Proc. ICCV, pp. 786-791 (2005) 720 H.V. Nguyen and L. Bai

Digital Library

[20]

Wolf, L., Hassner, T., Taigman, Y.: Descriptor based methods in the wild. In: Real-Life Images Workshop at the European Conference on Computer Vision, ECCV (2008)

[21]

Deng, W., Hu, J., Guo, J.: Gabor-Eigen-Whiten-Cosine: A Robust Scheme for Face Recognition. In: Zhao, W., Gong, S., Tang, X. (eds.) AMFG 2005. LNCS, vol. 3723, pp. 336-349. Springer, Heidelberg (2005)

Digital Library

[22]

http://vis-www.cs.umass.edu/lfw/results.html: (LFW benchmark results)

Cited By

Wang XLi QYu DLi QXu G(2024)Counterfactual Explanation for Fairness in RecommendationACM Transactions on Information Systems10.1145/364367042:4(1-30)Online publication date: 29-Jan-2024
https://dl.acm.org/doi/10.1145/3643670
Li RYe XZhou HZha H(2021)Learning to match via inverse optimal transportThe Journal of Machine Learning Research10.5555/3322706.336202120:1(2954-2990)Online publication date: 9-Mar-2021
https://dl.acm.org/doi/10.5555/3322706.3362021
Hu ZZhang YPan S(2021)Footstep-Induced Floor Vibration DatasetProceedings of the 19th ACM Conference on Embedded Networked Sensor Systems10.1145/3485730.3494117(546-551)Online publication date: 15-Nov-2021
https://dl.acm.org/doi/10.1145/3485730.3494117
Show More Cited By

Recommendations

Similarity metric learning for face verification using sigmoid decision function

In this paper, we consider the face verification problem, which is to determine whether two face images belong to the same subject or not. Although many research efforts have been focused on this problem, it still remains a challenging problem due to ...
Read More
Multiview discriminative marginal metric learning for makeup face verification
Abstract
Makeup face verification in the wild is an important research problem for its popularization in real-world. However, little effort has been made to tackle it in computer vision. In this research, we first build a new database, i.e., ...
Read More
Video-based kinship verification using distance metric learning

We investigate the problem of kinship verification from facial videos.We present a new video face dataset for the video-based kinship verification study.We develop a benchmark to evaluate state-of-the-art metric learning methods in video-based kinship ...
Read More

Comments

Information & Contributors

Information

Published In

cover image Guide Proceedings

ACCV'10: Proceedings of the 10th Asian conference on Computer vision - Volume Part II

November 2010

726 pages

ISBN:9783642193088

Editors:
Ron Kimmel
Department of Computer Science, Technion, Israel Institute of Technology, Haifa, Israel
,
Reinhard Klette
The University of Auckland, Auckland, New Zealand
,
Akihiro Sugimoto
National Institute of Informatics, Chiyoda, Tokyo, Japan

Sponsors

NEXTWINDOW: NextWindow - Touch-Screen Technology
ADEPT: Adept Electronic Solutions
AFCV: The Asian Federation of Computer Vision Societies
NICTA: National Information and Communications Technology Australia
4DVIEWS: 4D View Solutions

Publisher

Springer-Verlag

Berlin, Heidelberg

Publication History

Published: 08 November 2010

Qualifiers

Article

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

52
Total Citations
View Citations
0
Total Downloads

Downloads (Last 12 months)0
Downloads (Last 6 weeks)0

Other Metrics

View Author Metrics

Citations

Cited By

Wang XLi QYu DLi QXu G(2024)Counterfactual Explanation for Fairness in RecommendationACM Transactions on Information Systems10.1145/364367042:4(1-30)Online publication date: 29-Jan-2024
https://dl.acm.org/doi/10.1145/3643670
Li RYe XZhou HZha H(2021)Learning to match via inverse optimal transportThe Journal of Machine Learning Research10.5555/3322706.336202120:1(2954-2990)Online publication date: 9-Mar-2021
https://dl.acm.org/doi/10.5555/3322706.3362021
Hu ZZhang YPan S(2021)Footstep-Induced Floor Vibration DatasetProceedings of the 19th ACM Conference on Embedded Networked Sensor Systems10.1145/3485730.3494117(546-551)Online publication date: 15-Nov-2021
https://dl.acm.org/doi/10.1145/3485730.3494117
Li YZhang CHan SZhang LYin BLiu YXu MShen HZhuang YSmith JYang YCesar PMetze FPrabhakaran B(2021)Boosting Mobile CNN Inference through Semantic MemoryProceedings of the 29th ACM International Conference on Multimedia10.1145/3474085.3475399(2362-2371)Online publication date: 17-Oct-2021
https://dl.acm.org/doi/10.1145/3474085.3475399
Xia YXia YLi WSong RCao KStilla UShen HZhuang YSmith JYang YCesar PMetze FPrabhakaran B(2021)ASFM-Net: Asymmetrical Siamese Feature Matching Network for Point CompletionProceedings of the 29th ACM International Conference on Multimedia10.1145/3474085.3475348(1938-1947)Online publication date: 17-Oct-2021
https://dl.acm.org/doi/10.1145/3474085.3475348
Songwa PSaeed ABhardwaj SKruisselbrink TOzcelebi T(2021)LumNetProceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies10.1145/34635005:2(1-20)Online publication date: 24-Jun-2021
https://dl.acm.org/doi/10.1145/3463500
Shen XLu KMehta SZhang JLiu WFan JZha Z(2021)MKEL: Multiple Kernel Ensemble Learning via Unified Ensemble Loss for Image ClassificationACM Transactions on Intelligent Systems and Technology10.1145/345721712:4(1-21)Online publication date: 8-Jun-2021
https://dl.acm.org/doi/10.1145/3457217
Keswani VCelis LZhu FChin Ooi BMiao CWang HSkrypnyk IHsu WChawla S(2021)Auditing for Diversity Using Representative ExamplesProceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining10.1145/3447548.3467433(860-870)Online publication date: 14-Aug-2021
https://dl.acm.org/doi/10.1145/3447548.3467433
Robinson JQin CShao MTurk MChellappa RFu Y(2021)The 5th Recognizing Families in the Wild Data Challenge: Predicting Kinship from Faces2021 16th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2021)10.1109/FG52635.2021.9666990(01-07)Online publication date: 15-Dec-2021
https://dl.acm.org/doi/10.1109/FG52635.2021.9666990
Chen YWu LZaki MLarochelle HRanzato MHadsell RBalcan MLin H(2020)Iterative deep graph learning for graph neural networksProceedings of the 34th International Conference on Neural Information Processing Systems10.5555/3495724.3497344(19314-19326)Online publication date: 6-Dec-2020
https://dl.acm.org/doi/10.5555/3495724.3497344
Show More Cited By

View Options

View options

Media

Figures

Other

Tables

View Table of Contents