[1]谷凤伟,陆军,夏桂华.facenet皮尔森判别网络的人脸识别方法[J].智能系统学报,2022,17(1):107-115.[doi:10.11992/tis.202104008]
GU Fengwei,LU Jun,XIA Guihua.Face recognition method based on facenet Pearson discrimination network[J].CAAI Transactions on Intelligent Systems,2022,17(1):107-115.[doi:10.11992/tis.202104008]
点击复制
GU Fengwei,LU Jun,XIA Guihua.Face recognition method based on facenet Pearson discrimination network[J].CAAI Transactions on Intelligent Systems,2022,17(1):107-115.[doi:10.11992/tis.202104008]
facenet皮尔森判别网络的人脸识别方法
《智能系统学报》[ISSN 1673-4785/CN 23-1538/TP] 卷:
17
期数:
2022年第1期
页码:
107-115
栏目:
学术论文—智能系统
出版日期:
2022-01-05
- Title:
- Face recognition method based on facenet Pearson discrimination network
- Keywords:
- unrestricted scene; face recognition; facenet; multi-task cascaded convolutional neural network; face detection; Pearson correlation coefficient; euclidean distance; face dataset
- 分类号:
- TP391.41
- 摘要:
- 非限制场景下存在光照、遮挡和姿态变化等问题，这严重影响了人脸识别模型的性能和准确度。针对该问题，本文对facenet进行改进，提出了一种基于facenet皮尔森判别网络的人脸识别方法facenetPDN。首先，构建facenetPDN深度卷积神经网络，在facenet前端融合多任务级联卷积神经网络进行人脸检测提取目标人脸。然后，通过深度神经网络提取人脸深度特征信息，采用皮尔森相关系数判别模块替换facenet中的欧氏距离判别模块实现人脸深度特征判别。最后，使用CASIA-WebFace和CASIA-FaceV5人脸数据集训练网络。为了证明本文方法的有效性，训练后的模型在LFW和celeA人脸数据集进行测试和评估，并进行对比分析。实验结果表明，改进后的facenetPDN方法的准确度比原来整体提高了1.34%，在融合训练集下提高了0.78%，该算法鲁棒性和泛化能力优良，可实现多人种的人脸识别，对非限制场景下人脸目标具有良好的识别效果。
- Abstract:
- In unrestricted scenes, there are problems such as illumination, occlusion, and pose changes, which seriously affect the performance and accuracy of the face recognition model. This paper improves facenet to solve this problem, and proposes a facenetPDN method based on facenet Pearson discriminant network. Firstly, the deep convolutional neural network in facenetPDN is constructed, and the multi-task cascaded convolutional neural network is fused on the front-end of facenet to detect and extract the target face. Then, the facial depth feature information is extracted through the deep convolutional neural network, and the Pearson correlation coefficient discrimination module is used to replace the Euclidean distance discrimination module in the facenet algorithm to realize the facial depth feature discrimination. Finally, CASIA-WebFace and CASIA-FaceV5 face datasets are used to train the network. The trained model is tested and evaluated on the LFW and celeA face datasets to prove effectiveness of the method in this paper, and a comparative analysis is performed. The experimental results show that the accuracy of the improved facenetPDN method is 1.34% higher than that of the original method as a whole, and the accuracy of the model after training in the fusion training dataset is improved by 0.78%. The algorithm has excellent robustness and generalization ability, which can realize multi-ethnic face recognition, and has a good recognition effect on face targets in unrestricted scenes.
- 参考文献/References:
-
[1] GALBALLY J, MARCEL S, FIERREZ J. Image quality assessment for fake biometric detection: application to iris, fingerprint, and face recognition[J]. IEEE transactions on image processing, 2014, 23(2): 710–724.
[2] HOANG V D, DANG V D, NGUYEN T T, et al. A solution based on combination of RFID tags and facial recognition for monitoring systems[C]//2018 5th NAFOSTED Conference on Information and Computer Science (NICS). Ho Chi Minh City, Vietnam: IEEE, 2018: 384–387.
[3] CAI Weidong, MA Bo, ZHANG Liu, et al. A pointer meter recognition method based on virtual sample generation technology[J]. Measurement, 2020, 163: 107962.
[4] NIGAM S, SINGH R, MISRA A K. Efficient facial expression recognition using histogram of oriented gradients in wavelet domain[J]. Multimedia tools and applications, 2018, 77(21): 28725–28747.
[5] VYANZA V E, SETIANINGSIH C, IRAWAN B. Design of smart door system for live face recognition based on image processing using principal component analysis and template matching correlation methods[C]//2017 IEEE Asia Pacific Conference on Wireless and Mobile (APWiMob). Bandung, Indonesia: IEEE, 2017: 23–29.
[6] ZHU Yue, GAO Wanrong, GUO Zhenyan, et al. Liver tissue classification of en face images by fractal dimension-based support vector machine[J]. Journal of biophotonics, 2020, 13(4): e201960154.
[7] OUYANG Aijia, LIU Yanmin, PEI Shengyu, et al. A hybrid improved kernel LDA and PNN algorithm for efficient face recognition[J]. Neurocomputing, 2020, 393: 214–222.
[8] 张毅, 廖巧珍, 罗元. 融合二阶HOG与CS-LBP的头部姿态估计[J]. 智能系统学报, 2015, 10(5): 741–746.
ZHANG Yi, LIAO Qiaozhen, LUO Yuan. Head pose estimation fusing the second order HOG and CS-LBP[J]. CAAI Transactions on Intelligent Systems, 2015, 10(5): 741-746.
[9] 杨恢先, 刘建, 张孟娟, 等. 双差值局部方向模式的人脸识别[J]. 智能系统学报, 2018, 13(5): 751–759.
YANG Huixian, LIU Jian, ZHANG Mengjuan, et al. Face recognition with double difference local directional pattern[J]. CAAI transactions on intelligent systems, 2018, 13(5): 751–759.
[10] 刘峤, 秦志光, 陈伟, 等. 基于零范数特征选择的支持向量机模型[J]. 自动化学报, 2011, 37(2): 252–256.
LIU Qiao, QIN Zhiguang, CHEN Wei, et al. Zero-norm penalized feature selection support vector machine[J]. Acta automatica sinica, 2011, 37(2): 252–256.
[11] 朱换荣, 郑智超, 孙怀江. 面向局部线性回归分类器的判别分析方法[J]. 智能系统学报, 2019, 14(5): 959–965.
ZHU Huanrong, ZHENG Zhichao, SUN Huaijiang. Locality-regularized linear regression classification-based discriminant analysis[J]. CAAI transactions on intelligent systems, 2019, 14(5): 959–965.
[12] LECUN Y, BENGIO Y, HINTON G. Deep learning[J]. Nature, 2015, 521(7553): 436–444.
[13] TAIGMAN Y, YANG Ming, RANZATO M A, et al. DeepFace: closing the gap to human-level performance in face verification[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Columbus, USA: IEEE, 2014: 1701–1708.
[14] SUN Yi, WANG Xiaogang, TANG Xiaoou. Deep learning face representation from predicting 10,000 classes[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Columbus, USA: IEEE, 2014: 1891–1898.
[15] BanBANSAL A, NANDURI A, CASTILLO C D, et al. UMDFaces: an annotated face dataset for training deep networks[C]//2017 IEEE international joint conference on biometrics . Denver, USA: IEEE, 2017: 464–473.
[16] WANG Hao, WANG Yitong, ZHOU Zheng, et al. CosFace: large margin cosine loss for deep face recognition[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City, USA, 2018: 5265–5274.
[17] SCHERHAG U, RATHGEB C, MERKLE J, et al. Deep face representations for differential morphing attack detection[J]. IEEE transactions on information forensics and security, 2020, 15: 3625–3639.
[18] PRASAD P S, PATHAK R, GUNJAN V K, et al. Deep learning based representation for face recognition[M].ICCCE 2019. Singapore: Springer, 2020: 419–424.
[19] ZHANG Kaipeng, ZHANG Zhanpeng, LI Zhifeng, et al. Joint face detection and alignment using multitask cascaded convolutional networks[J]. IEEE signal processing letters, 2016, 23(10): 1499–1503.
[20] SCHROFF F, KALENICHENKO D, PHILBIN J. FaceNet: a unified embedding for face recognition and clustering[C]//2015 IEEE Conference on Computer Vision and Pattern Recognition. Boston, USA: IEEE, 2015: 815–823.
[21] THOMAS A, HARIKRISHNAN P M, PALANISAMY P, et al. Moving vehicle candidate recognition and classification using inception-ResNet-v2[C]//2020 IEEE 44th Annual Computers, Software, and Applications Conference (COMPSAC). Madrid, Spain: IEEE, 2020: 467–472.
[22] ZHAO Yuanfang, ZHEN Zonglei, LIU Xiqin, et al. The neural network for face recognition: insights from an fMRI study on developmental prosopagnosia[J]. NeuroImage, 2018, 169: 151–161.
[23] GAO Wen, GAO Bo, SHAN Shiguang, et al. The CAS-PEAL large-scale Chinese face database and baseline evaluations[J]. IEEE transactions on systems, man, and cybernetics-part A: systems and humans, 2008, 38(1): 149–161.
[24] LIU Ziwei, LUO Ping, WANG Xiaogang, et al. Deep learning face attributes in the wild[C]//Proceedings of the IEEE International Conference on Computer Vision. Santiago, Chile: IEEE, 2015: 3730–3738.
[25] LI Xiaobin, WANG Weiqiang. Learning discriminative features via weights-biased softmax loss[J]. Pattern recognition, 2020, 107: 107405.
[26] FARZANEH A H, QI Xiaojun. Discriminant distribution-agnostic loss for facial expression recognition in the wild[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops. Seattle, USA: IEEE, 2020: 1631–1639.
[27] ALBIERO V, BOWYER K W, VANGARA K, et al. Does face recognition accuracy get better with age? deep face matchers say no[C]//Proceedings of the IEEE Winter Conference on Applications of Computer Vision. Snowmass, USA: IEEE, 2020: 250–258.
[28] TAIGMAN Y, YANG M, RANZATO M, et al. DeepFace: closing the gap to human-level performance in face verification[C]// Conference on Computer Vision and Pattern Recognition. IEEE Computer Society, 2014.
[29] CAO Xudong, WIPF D, WEN Fang, et al. A practical transfer learning algorithm for face verification[C]//2013 IEEE International Conference on Computer Vision. Sydney, Australia: IEEE, 2013: 3208–3215.
[30] CHEN Dong, CAO Xudong, WEN Fang, et al. Blessing of dimensionality: high-dimensional feature and its efficient compression for face verification[C]//2013 IEEE Conference on Computer Vision and Pattern Recognition. Portland, USA: IEEE, 2013: 3025–3032.
[31] PARKHI O M, VEDALDI A, ZISSERMAN A. Deep face recognition[C]//Proceedings of the British Machine Vision Conference. Swansea, UK: BMVA Press, 2015: 41.1–41.12.
[32] YI Dong, LEI Zhen, LIAO Shengcai, et al. Learning face representation from scratch[J]. arXiv preprint arXiv: 1411.7923, 2014.
- 相似文献/References:
-
[1]金一,阮秋琦.一种局部加权的二维主成分分析算法及其在人脸识别中的应用[J].智能系统学报,2007,2(3):25.
JIN Yi,RUAN Qiu-qi.A partially weighted twodimensional PCA for face recognition[J].CAAI Transactions on Intelligent Systems,2007,2():25.
[2]任小龙,苏光大,相 燕.使用第2代身份证的人脸识别身份认证系统[J].智能系统学报,2009,4(3):213.
REN Xiao-long,SU Guang-da,XIANG Yan.Face authentication system using the Chinese second generation identity card[J].CAAI Transactions on Intelligent Systems,2009,4():213.
[3]苏光大.多技术合力的人脸识别系统设计[J].智能系统学报,2009,4(6):471.[doi:doi:10.3969/j.issn.1673-4785.2009.06.001]
SU Guang-da.Face recognition system designed to integrate multiple techniques[J].CAAI Transactions on Intelligent Systems,2009,4():471.[doi:doi:10.3969/j.issn.1673-4785.2009.06.001]
[4]王科俊,邹国锋,张洁.SPCA参数对单样本人脸识别效果影响分析[J].智能系统学报,2011,6(6):531.
WANG Kejun,ZOU Guofeng,ZHANG Jie.Analysis of the influence of SPCA parameters on the recognition of a single sample face[J].CAAI Transactions on Intelligent Systems,2011,6():531.
[5]杜吉祥,翟传敏,叶永青.使用稀疏约束非负矩阵分解算法的跨年龄人脸识别[J].智能系统学报,2012,7(3):271.
DU Jixiang,ZHAI Chuanmin,YE Yongqing.An agespan face recognition method based on an NMF algorithm with sparseness constraints[J].CAAI Transactions on Intelligent Systems,2012,7():271.
[6]阮晓虎,李卫军,覃鸿,等.一种基于特征匹配的人脸配准判断方法[J].智能系统学报,2015,10(1):12.[doi:10.3969/j.issn.1673-4785.201312064]
RUAN Xiaohu,LI Weijun,QIN Hong,et al.An assessment method for face alignment based on feature matching[J].CAAI Transactions on Intelligent Systems,2015,10():12.[doi:10.3969/j.issn.1673-4785.201312064]
[7]孙劲光,孟凡宇.一种特征加权融合人脸识别方法[J].智能系统学报,2015,10(6):912.[doi:10.11992/tis.201509025]
SUN Jinguang,MENG Fanyu.Face recognition by weighted fusion of facial features[J].CAAI Transactions on Intelligent Systems,2015,10():912.[doi:10.11992/tis.201509025]
[8]马晓,张番栋,封举富.基于深度学习特征的稀疏表示的人脸识别方法[J].智能系统学报,2016,11(3):279.[doi:10.11992/tis.201603026]
MA Xiao,ZHANG Fandong,FENG Jufu.Sparse representation via deep learning features based face recognition method[J].CAAI Transactions on Intelligent Systems,2016,11():279.[doi:10.11992/tis.201603026]
[9]刘训利,龚勋,王国胤.一种基于非残差估计线性表示模型的人脸识别[J].智能系统学报,2014,9(3):285.[doi:10.3969/j.issn.1673-4785.201309065]
LIU Xunli,GONG Xun,WANG Guoyin.Face recognition based on the linear representation model without residual estimation[J].CAAI Transactions on Intelligent Systems,2014,9():285.[doi:10.3969/j.issn.1673-4785.201309065]
[10]夏洋洋,龚勋,洪西进.人脸识别背后的数据清理问题研究[J].智能系统学报,2017,12(5):616.[doi:10.11992/tis.201706025]
XIA Yangyang,GONG Xun,HONG Xijin.Research on the data cleansing problem for face recognition technology[J].CAAI Transactions on Intelligent Systems,2017,12():616.[doi:10.11992/tis.201706025]
备注/Memo
收稿日期:2021-04-06。
基金项目:黑龙江省自然科学基金项目（F201123）.
作者简介:谷凤伟，博士研究生，主要研究方向为人脸识别、机器视觉、图像处理、目标跟踪;陆军，教授，博士生导师，主要研究方向为计算机视觉、智能控制技术、图像处理、高性能船舶控制和机械臂控制。科技部科技型中小企业创新基金项目评审专家，国家自然科学基金同行评议专家。获省部级以上奖励多项。发表学术论文70余篇;夏桂华，教授、博士生导师，主要研究船舶运动建模与仿真、智能船舶技术、船舶驾控模拟系统、图像处理和智能机器人控制。享受国务院特殊津贴专家，获省部级以上奖励多项。发表学术论文70余篇。
通讯作者:陆军. E-mail: lujun0260@sina.com
更新日期/Last Update:
1900-01-01