Abstract:To solve the problem of kinship verification of facial image, an algorithm for neighborhood repulsed metric learning based on local feature fusion is proposed. Firstly, texture and skin color features are extracted from the key areas of the face images. Then, the feature fusion method is proposed. Finally, the metric learning method is introduced to learn a transformational matrix capable of making the distance between the samples with kinship smaller and the distance between the samples of non-kin larger. The prior knowledge of the similarity degree of existing data samples is utilized to learn the best similarity measure to describe the similarity of kinship samples better. The experimental results on KinFaceW-I and KinFaceW-II databases demonstrate the efficiency of the proposed algorithm.
胡正平,郭增洁,王蒙,孙 哲. 基于局部特征融合的邻域排斥度量学习亲属关系认证算法*[J]. 模式识别与人工智能, 2017, 30(6): 530-537.
HU Zhengping, GUO Zengjie, WANG Meng, SUN Zhe. Neighborhood Repulsed Metric Learning for Kinship Verification Based on Local Feature Fusion. , 2017, 30(6): 530-537.
[1] FANG R G, TANG K D, SNAVELY N, et al. Towards Computational Models of Kinship Verification // Proc of the 17th IEEE International Conference on Image Processing. Washington, USA: IEEE, 2010: 1577-1580. [2] YAN H B, LU J W, ZHOU X Z. Prototype-Based Discriminative Feature Learning for Kinship Verification. IEEE Transactions on Cybernetics, 2015, 45(11): 2535-2545. [3] LIU Q F, PUTHENPUTHUSSERY A, LIU C J. Inheritable Fisher Vector Feature for Kinship Verification // Proc of the 7th IEEE International Conference on Biometrics Theory, Applications and Systems. Washington, USA: IEEE, 2015. DOI: 10.1109/BTAS.2015.7358768. [4] ALIREZAZADEH P, FATHI A, ABDALI-MOHAMMADI F. A Genetic Algorithm Based Feature Selection for Kinship Verification. IEEE Signal Processing Letters, 2015, 22(12): 2459-2463. [5] XIA S Y, SHAO M, FU Y. Kinship Verification through Transfer Learning // Proc of the 22nd International Joint Conference on Artificial Intelligence. Palo Alto, USA: AAAI Press, 2011, III: 2539-2544. [6] XIA S Y, SHAO M, LUO J B, et al. Understanding Kin Relationships in a Photo. IEEE Transactions on Multimedia, 2012, 14(4): 1046-1056. [7] ZHOU X Z, SHANG Y Y, YAN H B, et al. Ensemble Similarity Learning for Kinship Verification from Facial Images in the Wild. Information Fusion, 2016, 32(B): 40-48. [8] ZHOU X Z, YAN H B, SHANG Y Y. Kinship Verification from Facial Images by Scalable Similarity Fusion. Neurocomputing, 2016, 197: 136-142. [9] XU M, SHANG Y Y. Kinship Verification Using Facial Images by Robust Similarity Learning[J/OL]. [2016-11-21]. http://dx.doi.org/10.1155/2016/4072323. [10] WANG M Y, LI Z C, SHU X B, et al. Deep Kinship Verification // Proc of the 17th IEEE International Workshop on Multimedia Signal Processing. Washington, USA: IEEE, 2015. DOI: 10.1109/MMSP.2015.7340820. [11] LU J W, HU J L, ZHOU X Z, et al. Kinship Verification in the Wild: The First Kinship Verification Competition // Proc of the IEEE International Joint Conference on Biometrics. Washington, USA: IEEE, 2014. DOI: 10.1109/BTAS.2014.6996230. [12] YAN H B, LU J L, DENG W H, et al. Discriminative Multimetric Learning for Kinship Verification. IEEE Transactions on Information Forensics and Security, 2014, 9(7): 1169-1178. [13] LU J W, HU J L, LIONG V E, et al. The FG 2015 Kinship Verification in the Wild Evaluation // Proc of the 11th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition. Washington, USA: IEEE, 2015. DOI: 10.1109/FG.2015.7163159. [14] ZHOU X Z, HU J L, LU J W, et al. Kinship Verification from Facial Images under Uncontrolled Conditions // Proc of the 19th ACM International Conference on Multimedia. New York, USA: ACM, 2011: 953-956. [15] GUO G D, WANG X L. Kinship Measurement on Salient Facial Features. IEEE Transactions on Instrumentation and Measurement, 2012, 61(8): 2322-2325. [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.