第2期 方涛，等：神经网络多层特征信息融合的人脸识别方法 ·285· ion and Pattern Recognition.Columbus,USA,2014: ive margin softmax for face verification[J].IEEE signal 1891-1898 processing letters,2018,25(7):926-930 [10]ZEILER M D,FERGUS R.Visualizing and understand- [18]任克强，胡慧.角度空间三元组损失微调的人脸识 ing convolutional networks[C]//Proceedings of the 13th 别).液晶与显示，2019,341)少：110-117. European Conference on Computer Vision.Cham,Ger- REN Keqiang,HU Hui.Face recognition of triple loss many,2014:818-833. fine-tuning in angular space[J].Chinese journal of liquid [11]HOFFER E,AILON N.Deep metric learning using triplet crystals and displays,2019,34(1):110-117. network[C]//Proceedings of the 3rd International Work- [19]GUNTHER M.CRUZ S.RUDD E M.et al.Toward shop no Similarity-Based Pattern Recognition.Copenha- open-set face recognition[C]//Proceedings of the 2017 gen,Denmark,2015:84-92. IEEE Conference on Computer Vision and Pattern Recog- [12]TADMOR O,ROSENWEIN T,SHALEV-SHWARTZ S, nition Workshops.Honolulu,USA.2017:71-80 et al.Learning a metric embedding for face recognition [20]HUANG G B,MATTAR M,BERG T.et al.Labeled using the multibatch method[C]//Proceedings of the 30th faces in the wild:a database forstudying face recognition International Conference on Neural Information Pro- in unconstrained environments [C]//Workshop on Faces cessing Systems.Red Hook,United States,2016: 1396-1397. in'Real-Life'Images:Detection,Alignment,and Recogni- [13]吕璐，蔡晓东，曾燕，等.一种基于融合深度卷积神经网 tion.Marseille,Francem,2008. 络与度量学习的人脸识别方法[】.现代电子技术， 作者简介： 2018.41(9):58-61,67 方涛，硕士研究生，主要研究方向 LYU Lu,CAI Xiaodong,ZENG Yan,et al.A face recog- 为人工智能与模式识别。 nition method based on fusion of deep CNN and metric learning[J].Modern electronics technique,2018,41(9): 58-61,67 [14]WEN Yandong,ZHANG Kaipeng,LI Zhifeng,et al.A discriminative feature learning approach for deep face re- cognition[Cl//Proceedings of the 14th European Confer- 陈志国，副教授，主要研究方向为 ence on Computer Vision.Amsterdam,the Netherlands. 人工智能、计算机智能控制。参与 2016:499-515. 973军工子项目1项.承担企业研究 项目50多项，获得中国轻工业联合会 [15]LIU Weiyang,WEN Yandong,YU Zandong,et al. 科技进步奖二等奖1项、中国轻工业 SphereFace:deep hypersphere embedding for face recog- 联合会科技进步奖三等奖1项、无锡 nition[Cl//Proceedings of the 2017 IEEE Conference on 市科技进步奖三等奖1项，IEEE会 Computer Vision and Pattern Recognition.Honolulu, 员。发表学术论文20余篇。 USA.2017:212-220. [16]WANG Hao,WANG Yitong,ZHOU Zheng,et al.Cos- 傅毅，副教授，主要研究方向为智 能优化算法，生物信息。主持国家自 Face:Large margin cosine loss for deep face recognition[Cl/ 然科学基金青年基金项目1项、江苏 Proceedings of the 2018 IEEE/CVF Conference on Com- 省自然科学基金项目1项，参与国家 puter Vision and Pattern Recognition.Salt Lake City, 自然科学基金青年基金项目1项，江 USA,2018:5265-5274. 苏省环境监测科研基金项目1项。发 [17]WANG Feng,CHENG Jian,LIU Weiyang,et al.Addit- 表学术论文30多篇。ion and Pattern Recognition. Columbus, USA, 2014: 1891−1898. ZEILER M D, FERGUS R. Visualizing and understand￾ing convolutional networks[C]//Proceedings of the 13th European Conference on Computer Vision. Cham, Ger￾many, 2014: 818−833. [10] HOFFER E, AILON N. Deep metric learning using triplet network[C]//Proceedings of the 3rd International Work￾shop no Similarity-Based Pattern Recognition. Copenha￾gen, Denmark, 2015: 84−92. [11] TADMOR O, ROSENWEIN T, SHALEV-SHWARTZ S, et al. Learning a metric embedding for face recognition using the multibatch method[C]//Proceedings of the 30th International Conference on Neural Information Pro￾cessing Systems. Red Hook, United States, 2016: 1396−1397. [12] 吕璐, 蔡晓东, 曾燕, 等. 一种基于融合深度卷积神经网 络与度量学习的人脸识别方法 [J]. 现代电子技术, 2018, 41(9): 58–61, 67. LYU Lu, CAI Xiaodong, ZENG Yan, et al. A face recog￾nition method based on fusion of deep CNN and metric learning[J]. Modern electronics technique, 2018, 41(9): 58–61, 67. [13] WEN Yandong, ZHANG Kaipeng, LI Zhifeng, et al. A discriminative feature learning approach for deep face re￾cognition[C]//Proceedings of the 14th European Confer￾ence on Computer Vision. Amsterdam, the Netherlands, 2016: 499−515. [14] LIU Weiyang, WEN Yandong, YU Zandong, et al. SphereFace: deep hypersphere embedding for face recog￾nition[C]//Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, USA, 2017: 212−220. [15] WANG Hao, WANG Yitong, ZHOU Zheng, et al. Cos￾Face: Large margin cosine loss for deep face recognition[C]// Proceedings of the 2018 IEEE/CVF Conference on Com￾puter Vision and Pattern Recognition. Salt Lake City, USA, 2018: 5265−5274. [16] [17] WANG Feng, CHENG Jian, LIU Weiyang, et al. Addit￾ive margin softmax for face verification[J]. IEEE signal processing letters, 2018, 25(7): 926–930. 任克强, 胡慧. 角度空间三元组损失微调的人脸识 别 [J]. 液晶与显示, 2019, 34(1): 110–117. REN Keqiang, HU Hui. Face recognition of triple loss fine-tuning in angular space[J]. Chinese journal of liquid crystals and displays, 2019, 34(1): 110–117. [18] GUNTHER M, CRUZ S, RUDD E M, et al. Toward open-set face recognition[C]//Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recog￾nition Workshops. Honolulu, USA, 2017: 71−80. [19] HUANG G B, MATTAR M, BERG T, et al. Labeled faces in the wild: a database forstudying face recognition in unconstrained environments [C] // Workshop on Faces in 'Real-Life' Images: Detection, Alignment, and Recogni￾tion. Marseille, Francem, 2008. [20] 作者简介： 方涛，硕士研究生，主要研究方向 为人工智能与模式识别。 陈志国，副教授，主要研究方向为 人工智能、计算机智能控制。参与 973 军工子项目 1 项，承担企业研究 项目 50 多项，获得中国轻工业联合会 科技进步奖二等奖 1 项、中国轻工业 联合会科技进步奖三等奖 1 项、无锡 市科技进步奖三等奖 1 项，IEEE 会 员。发表学术论文 20 余篇。 傅毅，副教授，主要研究方向为智 能优化算法，生物信息。主持国家自 然科学基金青年基金项目 1 项、江苏 省自然科学基金项目 1 项，参与国家 自然科学基金青年基金项目 1 项，江 苏省环境监测科研基金项目 1 项。发 表学术论文 30 多篇。 第 2 期 方涛，等：神经网络多层特征信息融合的人脸识别方法 ·285·