Abstract
Clustering of face images is a well-known clustering problem with several applications as for example the automated face tagging in photo albums. The performance of face clustering algorithms largely depends on the face representations that are used. Therefore, the exploitation of the internal face representation (embedding) obtained by feeding the face image to a deep face network has led to increased clustering performance. In this work, we perform face clustering by combining multiple representations of each image obtained from several deep face networks. The multiple deep representations are not exploited in a straightforward manner (simple vector concatenation). Instead a weight is assigned to each representation to reflect its importance on the clustering result and a weighted clustering algorithm is employed to automatically adjust the weights and, consequently, the contribution of each representation on the clustering solution. It should also be noted that in the proposed approach, the number of clusters (number of faces) is not given as input, but it is automatically estimated using the silhouette criterion. The conducted experiments have shown that the weighted combination of deep face representations leads to improved clustering performance compared to using single representations.
Similar content being viewed by others
References
Arthur D, Vassilvitskii S (2007) K-means++: the advantages of careful seeding. In: ACM-SIAM symposium on discrete algorithms, vol 8, pp 1027–1035
Cao Q, Shen L, Xie W, Parkhi OM, Zisserman A (2018) Vggface2: a dataset for recognising faces across pose and age. In: IEEE conference on automatic face and gesture recognition (F&G), pp 67–74
Cao X, Zhang C, Zhou C, Fu H, Foroosh H (2015) Constrained multi-view video face clustering. IEEE Trans Image Process 24(11):4381–4393
Deng J, Guo J, Xue N, Zafeiriou S (2019) Arcface: additive angular margin loss for deep face recognition. In: CVPR, pp 4690–4699
Deng J, Guo J, Zhou Y, Yu J, Kotsia I, Zafeiriou S (2020) Retinaface: single-stage dense face localisation in the wild. In: CVPR, pp 5203–5212
Fitzgibbon A, Zisserman A (2002) On affine invariant clustering and automatic cast listing in movies. In: ECCV, pp 304–320
Guo S, Xu J, Chen D, Zhang C, Wang X, Zhao R (2020) Density-aware feature embedding for face clustering. In: CVPR, pp 6697–6705
Hu J, Shen L, Sun G (2018) Squeeze-and-excitation networks. In: CVPR, pp 7132–7141
Hu Y, Mian AS, Owens R (2011) Sparse approximated nearest points for image set classification. In: CVPR, pp 121–128
Huang GB, Mattar M, Berg T, Learned-Miller E (2014) Labeled faces in the wild: updates and new reporting procedures. Technical Report UM-CS-2014-003, University of Massachusetts, Amherst
Huang GB, Mattar M, Berg T, Learned-Miller E (2007) Labeled faces in the wild: a database for studying face recognition in unconstrained environments. Technical report 07-49, University of Massachusetts, Amherst
Huang JZ, Ng MK, Hongqiang Rong, Zichen Li (2005) Automated variable weighting in \(k\)-means type clustering. IEEE Trans Pattern Anal Mach Intell 27(5):657–668
Kirby M, Sirovich L (1990) Application of the Karhunen-Loeve procedure for the characterization of human faces. IEEE Trans Pattern Anal Mach Intell 12(1):103–108
Klontz JC, Jain AK (2013) A case study of automated face recognition: the boston marathon bombings suspects. Computer 46(11):91–94
Kulshreshtha P, Guha T (2018) An online algorithm for constrained face clustering in videos. In: IEEE international conference on image processing (ICIP), pp 2670–2674
Lin W, Chen J, Chellappa R (2017) A proximity-aware hierarchical clustering of faces. In: 12th IEEE international conference on automatic face and gesture recognition (FG 2017), pp 294–301
Ng H, Winkler S (2014) A data-driven approach to cleaning large face datasets. In: IEEE international conference on image processing (ICIP), pp 343–347
Otto C, Wang D, Jain AK (2018) Clustering millions of faces by identity. IEEE Trans Pattern Anal Mach Intell 40(2):289–303
Parkhi O, Vedaldi A, Zisserman A (2015) Deep face recognition. In: British machine vision conference (BMVC), pp 41.1–41.12
Wang R, Shan S, Chen X, Gao W (2008) Manifold-manifold distance with application to face recognition based on image set. In: CVPR, pp 1–8
Schroff F, Kalenichenko D, Philbin J (2015) Facenet: a unified embedding for face recognition and clustering. In: CVPR, pp 815–823
Sharma V, Sarfraz MS, Stiefelhagen R (2017) A simple and effective technique for face clustering in tv series. In: CVPR workshop on brave new motion representations
Shi Y, Otto C, Jain AK (2018) Face clustering: representation and pairwise constraints. IEEE Trans Inf Forens Secur 13:1626–1640
Sirovich L, Kirby M (1987) Low-dimensional procedure for the characterization of human faces. J Opt Soc Am, A, Opt Image Sci 4:519–24
Taigman Y, Yang M, Ranzato M, Wolf L (2014) Deepface: closing the gap to human-level performance in face verification. In: CVPR, pp 1701–1708
Turk M, Pentland A (1991) Eigenfaces for recognition. J Cognit Neurosci 3(1):71–86
Wang Z, Zheng L, Li Y, Wang S (2019) Linkage based face clustering via graph convolution network. In: CVPR, pp 1117–1125
Wolf L, Hassner T, Maoz I (2011) Face recognition in unconstrained videos with matched background similarity. In: CVPR, pp 529–534
Wu B, Hu BG, Ji Q (2017) A coupled hidden Markov random field model for simultaneous face clustering and tracking in videos. Pattern Recogn 64:361–373
Zhang K, Zhang Z, Li Z, Qiao Y (2016) Joint face detection and alignment using multitask cascaded convolutional networks. IEEE Signal Process Lett 23:1499–5031
Zhang Z, Luo P, Loy CC, Tang X (2016) Joint face representation adaptation and clustering in videos. In: ECCV, pp 236–251
Zheng T, Deng W, Hu J (2017) Cross-age LFW: a database for studying cross-age face recognition in unconstrained environments. CoRR. arXiv:1708.08197
Zhu C, Wen F, Sun J (2011) A rank-order distance based clustering algorithm for face tagging. In: CVPR, pp 481–488
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no conflict of interest.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Skiadopoulou, D., Likas, A. Face clustering using a weighted combination of deep representations. Neural Comput & Applic 34, 995–1006 (2022). https://doi.org/10.1007/s00521-021-06581-8
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-021-06581-8