基于改进深层网络的人脸识别算法

doi:10.3969/j.issn.0372-2112.2017.03.017

电子学报 ›› 2017, Vol. 45 ›› Issue (3): 619-625.DOI: 10.3969/j.issn.0372-2112.2017.03.017

基于改进深层网络的人脸识别算法

李倩玉, 蒋建国, 齐美彬

合肥工业大学计算机与信息学院, 安徽合肥 230009

收稿日期:2015-06-24 修回日期:2016-01-14 出版日期:2017-03-25
- 作者简介:
- 李倩玉 女,1991年生于安徽合肥,合肥工业大学研究生,研究方向为数字图像处理与分析、人脸检测与识别.E-mail:qianyuli@mail.hfut.edu.cn;蒋建国 男,1955年生于安徽黄山,教授、博士生导师,合肥工业大学计算机与信息学院.研究方向为视频信息分析与处理、多媒体智能监控系统、分布式智能系统、DSP技术应用等.E-mail:jgjiang@hfut.edu.cn;齐美彬 男,1969年生于安徽池州,教授、硕士生导师,合肥工业大学计算机与信息学院.研究方向为运动目标检测与跟踪、视频编码等.E-mail:qimeibin@163.com
- 基金资助:
- 国家自然科学基金 (No.61371155）; 安徽科技攻关项目 (No.1301b042023）

Face Recognition Algorithm Based on Improved Deep Networks

LI Qian-yu, JIANG Jian-guo, QI Mei-bin

School of Computer & Information, Hefei University of Technology, Hefei, Anhui 230009, China

Received:2015-06-24 Revised:2016-01-14 Online:2017-03-25 Published:2017-03-25
- Supported by:
- National Natural Science Foundation of China (No.61371155); Science and Technology Research and Development Program of Anhui Province (No.1301b042023)

摘要/Abstract

摘要：

目前的人脸识别算法在其特征提取过程中采用手工设计（hand-crafted）特征或利用深度学习自动提取特征.本文提出一种基于改进深层网络自动提取特征的人脸识别算法，可以更准确地提取出目标的鉴别性特征.算法首先对图像进行ZCA（Zero-mean Component Analysis）白化等预处理，减小特征相关性，降低网络训练复杂度.然后，基于卷积、池化、多层稀疏自动编码器构建深层网络特征提取器.所使用的卷积核是通过单独的无监督学习获得的.此改进的深层网络通过预训练和微调，得到一个自动的深层特征提取器.最后，利用Softmax回归模型对提取的特征进行分类.本文算法在多个常用人脸库上进行了实验，表明了其在性能上比传统方法和普通深度学习方法都有所提高.

关键词: 人脸识别, 改进的深层网络, 卷积, 池化, 多层稀疏自动编码器

Abstract:

Current face recognition algorithms use hand-crafted features or extract features by deep learning.This paper presents a face recognition algorithm based on improved deep networks that can automatically extract the discriminative features of the target more accurately.Firstly,this algorithm uses ZCA(Zero-mean Component Analysis)whitening to preprocess the input images in order to reduce the correlation between features and the complexity of the training networks.Then,it organically combines convolution,pooling and stacked sparse autoencoder to get a deep network feature extractor.The convolution kernels are achieved through a separate unsupervised learning model.The improved deep networks get an automatic deep feature extractor through preliminary training and fine-tuning.Finally,the softmax regression model is used to classify the extracted features.This algorithm is tested on several commonly used face databases.It is indicated that the performance is better than the traditional methods and common deep learning methods.

Key words: face recognition, improved deep networks, convolution, pooling, stacked sparse autoencoder

中图分类号:

TP391

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 Qian-yu, JIANG Jian-guo, QI Mei-bin . Face Recognition Algorithm Based on Improved Deep Networks[J]. Acta Electronica Sinica, 2017, 45(3): 619-625.

参考文献

[1] Deng W,Hu J,Lu J,et al.Transform-Invariant PCA:A unified approach to fully automatic face alignment,representationand recognition[J].IEEE Trans onPattern Analysis and Machine Intelligence,2014,36(6):1275-1284.
[2] 周家锐,纪震,等.基于Gabor小波与Memetic算法的人脸识别方法[J].电子学报,2012,40(4):642-646. Zhou Jia-rui,Ji Zhen,et al.Face recognitionusingGabor wavelets and Memetic algorithm[J].Acta Electronica Sinica,2012,40(4):642-646.(in Chinese)
[3] 杨飞,苏剑波.人脸显性特征的融合构造方法及识别[J].电子学报,2012,40(3):466-471. Yang Fei,Su Jian-bo.Face recognition based on explicit facial features by fusion construction method[J].Acta Electronica Sinica,2012,40(3):466-471.(in Chinese)
[4] Braverman M.Poly-logarithmic independence fools bounded-depthbooleancircuits[J].Communications of the ACM,2011,54(4):108-115.
[5] Zhang H,Zhou F,Zhang W,et al.Real-time action recognition based on a modified Deep Belief Network model[A].International Conference on Information and Automation[C].Hailar,HulunBuir,Inner Mongolia,China:IEEE,2014.225-228.
[6] Ouyang W,Wang X,Zeng X,et al.Deepid-net:Deformable deep convolutional neural networks for object detection[A].Conference on Computer Vision and Pattern Recognition[C].Boston,MA,USA:IEEE,2015.2403-2412.
[7] BENGIO Y.Learning deep architectures for AI[J].Foundations and Trends in Machine Learning,2009,2(1):1-12.
[8] Bengio Y,Le Cun Y.Scaling learning algorithms towards AI[J].Large-Scale Kernel Machines,2007,34(5):321-359.
[9] Sun Y,Wang X,Tang X.Deep convolutional network cascade for facial point detection[A].Conference on Computer Vision and Pattern Recognition[C].Portland,OR,USA:IEEE,2013.3476-3483.
[10] Hinton G E,Osindero S,Teh Y W.A fast learning algorithm for deep belief nets[J].Neural Computation,2006,18(7):1527-1554.
[11] Taigman Y,Yang M,Ranzato M A,et al.Deepface:Closing the gap to human-level performance in face verification[A].Conference on Computer Vision and Pattern Recognition[C].Columbus,OH,USA:IEEE,2014.1701-1708.
[12] Deng J,Zhang Z,Marchi E,et al.Sparse autoencoder-based feature transfer learning for speech emotion recognition[A].Humaine Association Conference on Affective Computing andIntelligent Interaction[C].Geneva,Switzerland:IEEE,2013.511-516.
[13] Phan H T,Duong A T,Le N D H,et al.Hierarchical sparse autoencoder using linear regression-based features in clustering for handwritten digit recognition[A].International Symposium on Image and Signal Processing and Analysis[C].Melbourne,Australia:IEEE,2013.183-188.
[14] Zhang C,Zhang Z.Improving multiview face detection with multi-task deep convolutional neural networks[A].IEEE Winter Conference on Applications of Computer Vision[C].Steamboat Springs,CO,USA:IEEE,2014.1036-1041.
[15] Dahl G E,Yu D,Deng L,et al.Context-dependent pre-trained deep neural networks for large-vocabulary speech recognition[J].IEEE Transactions on Audio,Speech,and Language Processing,2012,20(1):30-42.
[16] Hinton G E,Salakhutdinov R R.Replicated softmax:an undirected topic model[A].Advances in Neural Information Processing Systems[C].Vancouver,BC,Canada:NIPS,2009.1607-1614.
[17] Heisele B,Ho P,Poggio T.Face recognition with support vector machines:Global versus component-based approach[A].International Conference on Computer Vision[C].Vancouver,Canada:IEEE,2001.688-694.

基于改进深层网络的人脸识别算法

Face Recognition Algorithm Based on Improved Deep Networks

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	郑云飞, 王晓兵, 张雄伟, 曹铁勇, 孙蒙. 基于金字塔知识的自蒸馏HRNet目标分割方法[J]. 电子学报, 2023, 51(3): 746-756.
[2]	黄赟, 张帆, 郭威, 陈立, 羊光. 一种基于数据标准差的卷积神经网络量化方法[J]. 电子学报, 2023, 51(3): 639-647.
[3]	吕杭, 蒋明峰, 李杨, 张鞠成, 王志康. 基于混合时频域特征的卷积神经网络心律失常分类方法的研究[J]. 电子学报, 2023, 51(3): 701-711.
[4]	吴翼腾, 刘伟, 于溆乔. 基于参数差异假设的图卷积网络对抗性攻击[J]. 电子学报, 2023, 51(2): 330-341.
[5]	许新征, 李杉. 基于特征膨胀卷积模块的轻量化技术研究[J]. 电子学报, 2023, 51(2): 355-364.
[6]	杨利平, 侯振威, 辜小花, 郝峻永. 弱标签声音事件检测的空间-通道特征表征与自注意池化[J]. 电子学报, 2023, 51(2): 297-306.
[7]	张聿远, 闫文君, 张立民. 基于多模态特征融合网络的空时分组码识别算法[J]. 电子学报, 2023, 51(2): 489-498.
[8]	张永梅, 孙捷. 基于动静态特征双输入神经网络的咳嗽声诊断COVID-19算法[J]. 电子学报, 2023, 51(1): 202-212.
[9]	丁琪, 田萱, 孙国栋. 基于注意力增强的热点感知新闻推荐模型[J]. 电子学报, 2023, 51(1): 93-104.
[10]	郭晓轩, 冯其波, 冀振燕, 郑发家, 杨燕燕. 多线激光光条图像缺陷分割模型研究[J]. 电子学报, 2023, 51(1): 172-179.
[11]	袁海英, 成君鹏, 曾智勇, 武延瑞. Mobile_BLNet：基于Big-Little Net的轻量级卷积神经网络优化设计[J]. 电子学报, 2023, 51(1): 180-191.
[12]	吴靖, 叶晓晶, 黄峰, 陈丽琼, 王志锋, 刘文犀. 基于深度学习的单帧图像超分辨率重建综述[J]. 电子学报, 2022, 50(9): 2265-2294.
[13]	毛国君, 王者浩, 黄山, 王翔. 基于剪边策略的图残差卷积深层网络模型[J]. 电子学报, 2022, 50(9): 2205-2214.
[14]	袁海英, 曾智勇, 成君鹏. 面向灵活并行度的稀疏卷积神经网络加速器[J]. 电子学报, 2022, 50(8): 1811-1818.
[15]	孔玮, 刘云, 李辉, 崔雪红, 杨浩冉. 基于全局自适应有向图的行人轨迹预测[J]. 电子学报, 2022, 50(8): 1905-1916.