角度空间三元组损失微调的人脸识别

任克强; 胡慧

doi:doi:10.3788/yjyxs20193401.0110

液晶与显示, 2019, 34 (1): 110, 网络出版: 2019-03-06

角度空间三元组损失微调的人脸识别

Face recognition of triple loss fine-tuning in angular space

论文大纲

任克强 ^*胡慧

作者单位

江西理工大学信息工程学院, 江西赣州 341000

人脸识别卷积神经网络角度Softmax损失三元组损失特征相加 face recognition convolutional neural network angular Softmax loss triple loss feature addition

摘要

针对角度Softmax损失强约束存在的问题, 提出一种用角度空间三元组损失对角度Softmax损失预训练模型进行微调的算法。算法首先对原来的卷积神经网络结构进行改进, 将1×1卷积核与池化层加在不同残差块间, 以进行选择更有效的特征。然后用角度空间下的三元组损失对预训练模型进行微调, 以降低困难样本的强约束条件。最后在测试时, 分别提取原始人脸图像特征和水平翻转的人脸图像特征, 对两个特征相加作为最终的人脸特征表达, 以丰富人脸特征信息, 提高识别率。实验结果表明, 在LFW和YTF人脸数据集分别取得了99.25%和94.52%的识别率, 在大规模人脸身份识别中, 本文提出的方法在仅用单模型和比较小的训练集就能有效地提高人脸识别率。

Abstract

Aiming at the problem that angular Softmax loss exists in strong constraint, an algorithm to fine-turn the angular Softmax loss pre-training model by using triple loss in angle space was proposed in this paper. Firstly, the original structure of convolution neural network was improved and the convolution kernels of 1×1 and pooling layers were added between different residual blocks to select more effective features. Secondly, the pre-training model was fine-tuned by triple loss in angular space to reduce the strong constraint condition of difficult samples. Finally, in the test, the features of original and the horizontal flipped face images were extracted respectively, and the two features were added as the final facial feature expression, so as to enrich the face feature information and improve the recognition rate. The experimental results show that the recognition rates of the LFW and YTF face data sets are 99.25% and 94.52%, respectively. The method proposed in this paper can effectively improve the face recognition rate in large-scale face identification by using only a single model and a relatively small training set.

参考文献

[1] 卢洋,王世刚,赵文婷,等.基于人脸姿态估计的虚拟眼镜试戴技术［J］.中国光学,2015,8(4): 582-588.

LUY, WANG S G, ZHAO W T, et al. Technology of virtual eyeglasses try-on system based on face pose estimation ［J］. Chinese Optics, 2015, 8(4): 582-588. (in Chinese)

[2] 郑明秋,杨帆.改进非负矩阵分解的神经网络人脸识别［J］.液晶与显示,2017,32(3): 213-218.

ZHENG M Q, YANG F. Face recognition based on mproved NME and neurd network ［J］. Chinese Journal of Liquid Crystals and Displays, 2017, 32(3): 213-218. (in Chinese)

[3] 严严,陈日伟,王菡子.基于深度学习的人脸分析研究进展［J］.厦门大学学报(自然科学版),2017,56(1): 13-24.

YAN Y, CHEN R W, WANG H Z. Resent advcmces on deep-leaming based face analysis ［J］. Journal of Xiamen University (Natural Science ), 2017, 56(1): 13-24. (in Chinese)

[4] TAIGMAN Y, YANG M, RANZATO M, et al. Deepface: closing the gap to human-level performance in face verification ［C］ //IEEE Conference on Computer Vision and Pattern Recognition. Columbus, USA: IEEE, 2014: 1701-1708.

[5] SUN Y, WANG X, TANG X. Deep learning face representation from predicting 10,000 classes ［C］//IEEE Conference on Computer Vision and Pattern Recognition. Columbus, USA: IEEE Computer Society, 2014: 1891-1898.

[6] 李倩玉,蒋建国,齐美彬.基于改进深层网络的人脸识别算法［J］.电子学报,2017,45(3): 619-625.

LI Q Y, JIANG J G, QI M B. Face recognition algorithm based on improved deep network ［J］. Acta Electronica Sinica, 2017, 45(3): 619-625. (in Chinese)

[7] CHOPRA S, HADSELL R, LECUN Y. Learning a similarity metric discriminatively, with application to face verification ［C］// IEEE Conference on Computer Vision and Pattern Recognition. New York, USA: IEEE, 2005: 539-546.

[8] SCHROFF F, KALENICHENKO D, PHILBIN J. Facenet: a unified embedding for face recognition and clustering ［C］//IEEE Conference on Computer Vision and Pattern Recognition. Boston, USA: IEEE , 2015: 815-823.

[9] WEN Y, ZHANG K, LI Z, et al. A discriminative feature learning approach for deep face recognition ［C］//European Conference on Computer Vision. Amsterdam: Springer International Publishing, 2016: 499-515.

[10] SUN Y, WANG X, TANG X, et al. Deep learning face representation by joint identification-verification ［C］// Conference and Workshop on Neural Information Processing Systems. Montreal, Canada: MIT Press, 2014: 1988-1996.

[11] LIU W, WEN Y, YU Z, et al. Sphereface: deep hypersphere embedding for face recognition［C］//IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, USA: IEEE, 2017: 6738-6746.

[12] 沈凌云,郎百和,朱明.一种基于人工神经网络的人脸识别方法［J］.液晶与显示,2011,26(6): 836-840.

SHEN L Y, LANG B H, ZHU M. Face recognition method based on artificial neural network ［J］. Chinese Journal of Liquid Crystals and Displays, 2011, 26(6): 836-840. (in Chinese)

[13] PARKHI O M, VEDALDI A, ZISSERMAN A. Deep face recognition ［C］// British Machine Vision Conference. Swansea, UK: British Machine Association, 2015: 41-42.

[14] SUN Y, WANG X, TANG X. Deeply learned face representations are sparse, selective, and robust ［C］//IEEE Conference on Computer Vision and Pattern Recognition. Boston, USA: IEEE: 2015: 2892-2900.

[15] WU X, HE R, SUN Z, et al. A light CNN for deep face representation with noisy labels ［J］. IEEE Transactions on Information Forensics and Security, 2018,13(11): 2884-2896.

[16] WANG F, XIANG X, CHENG J, et al. Normface: L2 hypersphere embedding for face verification ［C］//Proceedings of the 2017 ACM on Multimedia Conference. Mountain View, USA: ACM New York, 2017: 1041-1049.

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. REN Ke-qiang, HU Hui. Face recognition of triple loss fine-tuning in angular space[J]. Chinese Journal of Liquid Crystals and Displays, 2019, 34(1): 110.

角度空间三元组损失微调的人脸识别

关于本站 Cookie 的使用提示

全站搜索

角度空间三元组损失微调的人脸识别

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索