Abstract Aiming at the variations of face pairs caused by different age gaps, an ensemble face pairs distance metric learning method(EFPML) is proposed for cross-age face verification. Firstly, the whole dataset is divided into several subsets with different age gaps. Then, a distance metric is learned for each subset. Finally, all face pairs are re-represented for many times via learnt distance metrics, the new representations are more distinguishable and the limited cross-age face data are expanded. To evaluate the proposed method, a series of experiments are conducted on two real-world cross age datasets, FG-NET and CACD. The results show that EFPML consistently outperforms the state-of-the-art methods and it has ability to reduce the effect of aging and improve verification performance.
Fund:Supported by National Natural Science Foundation of China(No.61632004,61370129,61375062), Program for Changjiang Scholars and Innovative Research Team in University(No.IRT201206)
About author:: (WU Jiaqi, born in 1992, master student. Her research interests include machine lear-ning and image processing.) (JING Liping(Corresponding author), born in 1978, Ph.D., professor. Her research interests include machine learning, high-dimensional data mining and its application in social multimedia and intelligent recommendation.)
[1] ADINI Y, MOSES Y, ULLMAN S. Face Recognition: The Problem of Compensating for Changes in Illumination Direction. IEEE Tran-sactions on Pattern Analysis and Machine Intelligence, 1997, 19(7): 721-732. [2] INOUE K, KUROKI Y. Illumination-Robust Face Recognition via Sparse Representation // Proc of the IEEE Conference on Visual Communications and Image Processing. Washington, USA: IEEE, 2011: 1-4. [3] BLANZ V, VETTER T. Face Recognition Based on Fitting a 3D Morphable Model. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2003, 25(9): 1063-1074. [4] DING C X, XU C, TAO D C. Multi-task Pose-Invariant Face Re-cognition. IEEE Transactions on Image Processing, 2015, 24(3): 980-993. [5] ZHU X Y, LEI Z, YAN J J, et al. High-Fidelity Pose and Expre-ssion Normalization for Face Recognition in the Wild // Proc of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2015: 787-796. [6] RAMANATHAN N, CHELLAPPA R. Modeling Age Progression in Young Faces // Proc of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2006, I: 387-394. [7] DU L, LING H B. Cross-Age Face Verification by Coordinating with Cross-Face Age Verification // Proc of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2015: 2329-2338. [8] RAMANATHAN N, CHELLAPPA R. Face Verification across Age Progression. IEEE Transactions on Image Processing, 2006, 15(11): 3349-3361. [9] LANITIS A. A Survey of the Effects of Aging on Biometric Identity Verification. International Journal of Biometrics, 2009, 2(1): 34-52. [10] JAIN A K, TONG Y, PARK U. Age-Invariant Face Recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2010, 32(5): 947-954. [11] LANITIS A, TAYLOR C J, COOTES T F. Toward Automatic Si-mulation of Aging Effects on Face Images. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2002, 24(4): 442-455. [12] SHU X B, TANG J H, LAI H J, et al. Personalized Age Progre-ssion with Aging Dictionary // Proc of the IEEE International Conference on Computer Vision. Washington, USA: IEEE, 2015: 3970-3978. [13] LING H B, SOATTO S, RAMANATHAN N, et al. Face Verification across Age Progression Using Discriminative Methods. IEEE Transactions on Information Forensics and Security, 2010, 5(1): 82-91. [14] BERETA M, KARCZMAREK P, PEDRYCZ W, et al. Local Descriptors in Application to the Aging Problem in Face Recognition. Pattern Recognition, 2013, 46(10): 2634-2646. [15] ALI A S O, SAGAYAN V, SAEED A M, et al. Age-Invariant Face Recognition System Using Combined Shape and Texture Features. IET Biometrics, 2015, 4(2): 98-115. [16] LU J W, ZHOU X Z, TAN Y P, et al. Neighborhood Repulsed Metric Learning for Kinship Verification. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2014, 36(2): 331-345.
[17] HINTON G E, SALAKHUTDINOV R R. Reducing the Dimensionality of Data with Neural Networks. Science, 2006, 313(5786): 504-507. [18] WANG W, CUI Z, YAN Y, et al. Recurrent Face Aging // Proc of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2016: 2378-2386. [19] LIN L, WANG G R, ZUO W M, et al. Cross-Domain Visual Matching via Generalized Similarity Measure and Feature Learning. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(6): 1089-1102. [20] WEN Y D, LI Z F, QIAO Y. Latent Factor Guided Convolutional Neural Networks for Age-Invariant Face Recognition // Proc of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2016: 4893-4901. [21] ZHOU Z H. Ensemble Methods: Foundations and Algorithms. Boca Raton, USA: CRC Press, 2012. [22] CHEN B C, CHEN C S, HSU W H. Cross-Age Reference Coding for Age-Invariant Face Recognition and Retrieval // Proc of the European Conference on Computer Vision. Berlin, Germany: Springer, 2014: 768-783. [23] AHONEN T, HADID A, PIETIKAINEN M. Face Description with Local Binary Patterns: Application to Face Recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2006, 28(12): 2037-2041. [24] LOWE D G. Distinctive Image Features from Scale-Invariant Keypoints. International Journal of Computer Vision, 2004, 60(2): 91-110.
2017, Vol. 30 
