用于亲属关系鉴别的成对约束组合度量学习

doi:10.6040/j.issn.1672-3961.0.2021.282

摘要/Abstract

摘要： 针对现有的度量学习方法存在训练参数多,容易导致过拟合和鲁棒性差的问题,提出一种成对约束组合度量学习方法(pairwise constrained compositional metric learning, PCCML),利用数据集中生成的局部判别度量,学习各组份度量的最优权重组合。在大边距框架下,PCCML通过约束正样本对马氏距离小于较小的阈值,负样本对马氏距离大于较大的阈值,有效提高了鉴别精度。在KinFaceW-I和KinFaceW-II基准数据集上的试验结果表明了所提出的PCCML方法对鉴别亲属关系问题的有效性。

关键词: 亲属关系鉴别, 人脸识别, 成对约束, 度量学习, 相似度学习

中图分类号:

TP391

刘笑,陈家炜,胡峻林. 用于亲属关系鉴别的成对约束组合度量学习[J]. 山东大学学报 (工学版), 2022, 52(2): 50-56.

LIU Xiao, CHEN Jiawei, HU Junlin. Pairwise constrained compositional metric learning for kinship verification[J]. Journal of Shandong University(Engineering Science), 2022, 52(2): 50-56.

参考文献

[1] DUONG C N, TRUONG T D, LUU K, et al. Vec2Face: unveil human faces from their blackbox features in face recognition[C] // Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle, USA: IEEE, 2020: 6132-6141.
[2] CHANG J, LAN Z, CHENG C, et al. Data uncertainty learning in face recognition[C] //Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.Seattle, USA: IEEE, 2020: 5710-5719.
[3] DENG J, GUO J, XUE N, et al. Arcface: additive angular margin loss for deep face recognition[C] //Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Long Beach, USA: IEEE, 2019: 4690-4699.
[4] LOPES A T, AGUIAR E, SOUZA A F, et al. Facial expression recognition with convolutional neural networks: coping with few data and the training sample order[J]. Pattern Recognition, 2017, 61: 610-628.
[5] LI S, DENG W. Deep facial expression recognition: a survey[J]. IEEE Transactions on Affective Computing, 2020, 1(1): 1-25.
[6] CHEN S, ZHANG C, DONG M, et al. Using ranking-cnn for age estimation[C] //Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Honolulu, USA: IEEE, 2017: 5183-5192.
[7] LEVI G, HASSNER T. Age and gender classification using convolutional neural networks[C] //Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops. Boston, USA: IEEE, 2015: 34-42.
[8] BOUTELLAA E, HADID A, BENGHERABI M, et al. On the use of Kinect depth data for identity, gender and ethnicity classification from facial images[J]. Pattern Recognition Letters, 2015, 68(11): 270-277.
[9] FANG R, TANG K D, SNAVELY N, et al. Towards computational models of kinship verification[C] //Proceedings of the 2010 IEEE International Conference on Image Processing. Hong Kong, China: IEEE, 2010: 1577-1580.
[10] XIA S, SHAO M, FU Y. Kinship verification through transfer learning[C] // Proceedings of the Twenty-Second International Joint Conference on Artificial Intelligence. Barcelona, Spain: AAAI, 2011: 2539-2544.
[11] LU J, ZHOU X, TAN Y P, et al. Neighborhood repulsed metric learning for kinship verification[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013, 36(2): 331-345.
[12] FENG Z, JIN R, JAIN A. Large-scale image annotation by efficient and robust kernel metric learning[C] //Proceedings of the IEEE International Conference on Computer Vision. Sydney, Australia: IEEE, 2013: 1609-1616.
[13] LU J, WANG G, DENG W, et al. Multi-manifold deep metric learning for image set classification[C] //Proceedings of the IEEE conference on computer vision and pattern recognition. Boston, USA: IEEE, 2015: 1137-1145.
[14] LU J, WANG G, DENG W, et al. Reconstruction-based metric learning for unconstrained face verification[J]. IEEE Transactions on Information Forensics and Security, 2014, 10(1): 79-89.
[15] SHI Y, BELLET A, SHA F. Sparse compositional metric learning[C] // Proceedings of the AAAI Conference on Artificial Intelligence. Québec City, Canada: AAAI, 2014.
[16] DING Z, SUH S, HAN J, et al. Discriminative low-rank metric learning for face recognition[C] // Proceedings of the 2015 11th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition. Ljubljana, Slovenia: IEEE, 2015: 1-6.
[17] LIN X, DUAN Y, DONG Q, et al. Deep variational metric learning[C] //Proceedings of the European Conference on Computer Vision. Munich, Germany: Springer, 2018: 689-704.
[18] WANG C, HU Y, GAO X, et al. KPML: a novel probabilistic perspective kernel mahalanobis distance metric learning model for semi-supervised clustering[C] //Proceedings of the International Conference on Database and Expert Systems Applications. Bratislava, Slovakia: Springer, 2020: 259-274.
[19] LU J, HU J, TAN Y P. Discriminative deep metric learning for face and kinship verification[J]. IEEE Transactions on Image Processing, 2017, 26(9): 4269-4282.
[20] HU J, LU J, TAN Y P, et al. Local large-margin multi-metric learning for face and kinship verification[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2017, 28(8): 1875-1891.
[21] MAHPOD S, KELLER Y. Kinship verification using multiview hybrid distance learning[J]. Computer Vision and Image Understanding, 2018, 167(2): 28-36.
[22] OZKAN S, OZKAN A. Kinshipgan: synthesizing of kinship faces from family photos by regularizing a deep face network[C] //Proceedings of the 2018 25th IEEE International Conference on Image Processing. Athens, Greece: IEEE, 2018: 2142-2146.
[23] WANG S, YAN H. Discriminative sampling via deep reinforcement learning for kinship verification[J]. Pattern Recognition Letters, 2020, 138(6): 38-43.
[24] YAN H, SONG C. Multi-scale deep relational reasoning for facial kinship verification[J]. Pattern Recognition, 2021, 110(2): 274-283.
[25] XIAO L. Dual averaging methods for regularized stochastic learning and online optimization[J]. Journal of Machine Learning Research, 2010, 11(1): 2543-2596.
[26] DALAL N, TRIGGS B. Histograms of oriented gradients for human detection[C] //Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. San Diego, USA: IEEE, 2005, 886-893.
[27] AHONEN T, HADID A, PIETIKAINEN M. Face description with local binary patterns: application to face recognition[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2006, 28(12): 2037-2041.
[28] PATEL B, MAHESHWATI R P, RAMAN B. Evalu-ation of periocular features for kinship verification in the wild[J]. Computer Vision and Image Understanding, 2017, 160(5): 24-35.
[29] HU J, LU J, LIU L, et al. Multi-view geometric mean metric learning for kinship verification[C] //Proceedings of the 2019 IEEE International Conference on Image Processing. Taipei, China: IEEE, 2019: 1178-1182.
[30] KAN M, SHAN S, XU D, et al. Side-information based linear discriminant analysis for face recognition[C] //Proceedings of the British Machine Vision Conference. Dundee, UK: IEEE, 2011: 1-12.

相关文章 14

[1]	解子奇,王立宏,李嫚. 块对角子空间聚类中成对约束的主动式学习[J]. 山东大学学报 (工学版), 2021, 51(2): 65-73.
[2]	范君,业巧林,业宁. 基于改进的有监督无参局部保持投影算法的人脸识别[J]. 山东大学学报 (工学版), 2019, 49(1): 10-16.
[3]	牟廉明. 自适应特征选择加权k子凸包分类[J]. 山东大学学报 (工学版), 2018, 48(5): 32-37.
[4]	张振月,李斐,江铭炎. 基于低秩表示投影的无监督人脸特征提取[J]. 山东大学学报(工学版), 2018, 48(1): 15-20.
[5]	周凯,元昌安,覃晓,郑彦,冯文铎. 基于核贝叶斯压缩感知的人脸识别[J]. 山东大学学报(工学版), 2016, 46(3): 74-78.
[6]	任捷怡, 吴小俊. 一种改进的协方差鉴别学习方法[J]. 山东大学学报(工学版), 2015, 45(1): 9-12.
[7]	谢志华. 一种新的血流建模方法及其在红外人脸识别中的应用[J]. 山东大学学报(工学版), 2013, 43(5): 1-5.
[8]	郭慧玲,王士同*,闫晓波. 基于广义旋转不变性核函数的人脸识别[J]. 山东大学学报(工学版), 2012, 42(5): 71-79.
[9]	丁彦,李永忠*. 基于PCA和半监督聚类的入侵检测算法研究[J]. 山东大学学报(工学版), 2012, 42(5): 41-46.
[10]	曹红根1,袁宝华1,朱辉生2. 结合对比度信息与LBP的分块人脸识别[J]. 山东大学学报(工学版), 2012, 42(4): 29-34.
[11]	翟俊海1,翟梦尧1,张素芳2,王熙照1. 基于小波子空间集成的人脸识别[J]. 山东大学学报(工学版), 2012, 42(2): 1-6.
[12]	张友新,王立宏. 两阶段近邻传播半监督聚类算法[J]. 山东大学学报(工学版), 2012, 42(2): 18-22.
[13]	王熙照,白丽杰*,花强,刘玉超. null[J]. 山东大学学报(工学版), 2011, 41(4): 1-6.
[14]	张道强. 知识保持的嵌入方法[J]. 山东大学学报(工学版), 2010, 40(2): 1-10.

多维度评价

Viewed

Full text

Abstract

Cited

Shared

Discussed