计算机科学 ›› 2018, Vol. 45 ›› Issue (10): 267-271.doi: 10.11896/j.issn.1002-137X.2018.10.049
张志禹, 刘思媛
ZHANG Zhi-yu, LIU Si-yuan
摘要: 相比于传统的降维算法,深度学习中的栈式自编码器(Stacked Autoencoder,SAE)能够有效地学习特征并实现高效降维,然而对输入特征极其敏感。第二代离散曲波变换(Discrete Curvelet Transform,DCT)能够提取出人脸的各向信息(包含边缘和概貌特征),确保SAE的输入特征充分,从而弥补了其不足。因此,提出了一种基于Curv-SAE特征融合的人脸识别降维算法,即对人脸图像进行DCT得到特征脸并将其作为SAE的输入特征进行训练,特征融合后将其输入到分类器中进行识别。在ORL和FERET人脸数据库上的实验表明,与小波变换相比,曲波的特征信息更丰富;与传统的降维算法相比,SAE的特征表达更充分且识别精度更高。
中图分类号:
[1]CHENG J L,WECHSLER H.A Gabor Feature Classifier for Face Recognition[C]∥IEEE International Conference on Computer Vision.2001:270-275. [2]CHIENJ T,WU C C.Discriminant Wavelet-faves and Nearest Feature classifiers for Face Recognition[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2002(24):1644-1649. [3]HU Z H,SONG Y L.Image reduction and reconstruction based on autoencoder network [J].Journal of Electronic and Information Technology,2009,31(5):1189-1193.(in Chinese) 胡昭华,宋耀良.基于Autoencoder网络的数据降维和重构[J].电子与信息学报,2009,31(5):1189-1193. [4]MEE D A,RAT A C.Enhanced Face Recognition Through Varia- tion of Principle Component Analysis(PCA)[C]∥International Conference on Industrial and Information.2007:347-351. [5]BEL P N,HES J P,KRR D J,et al.Fisherfaces:Recognition Using Class Specific Linear Projection[J].IEEE Trans.on PAMI,1997,19(7):711-720. [6]MART T,LEO M,D’ORAZIO.Facial Feature Estraction by Kernel Independent Component Analysis[C]∥IEEE Conference on Advanced Video and Signal Based Surveillance.2005:210-275. [7]HU Z H,SONG Y L.Image reduction and reconstruction based on a continuous self-coding network[J].Data Collection and Processing,2010,25(3):318-324.(in Chinese) 胡昭华,宋耀良.基于一种连续自编码网络的图像降维和重构[J].数据采集与处理,2010,25(3):318-324. [8]TEN J B,SILVA V D,LANGFO J C.A Global Geometric Framework for Nonlinear Dimensionality Reduction[J].Science,2000,290(5500):2319-2323. [9]ROUEIS S T,SAUL L K.Nonlinear Dimensionality Reduction by Locally Linear Embedding[J].Science,2000,290(5500):2323-2326. [10]LIANG W,DAVID S.Learning and Matching of Dynamic Shape Manifolds for Human Action Recognition[J].IEEE Transactions on Image Processing,2007,16(6):1646-1661. [11]HINTON G E,OSIN S.A Fast Learning Algorithm for Deep Belief Nets[J].Neural Computation,2006,18(7):1527-1554. [12]HINTON G E,SALAK R R.Reducing the Dimensionality of Data with Neural Networks[J].Science,2006,313(9):504-507. [13]CANDES E J,DONOHO D L.Curvelet-A Surprisingly Effective Nonadaptive Representation for Objects with Edges[M]∥Curve and Suface Fitting:SaintMalo.TN:Vanderbilt Univ Press,1999. [14]CANDES E J,DEMANET L,DONOHO D L.Fast Discrete Curvelet Transforms[R].Applied and Computational Mathematics.California:California Institute of Technology,2005. [15]VINCENT P,LARO H,BENGIO Y,et al.Extracting and Composing Robust Features with Denoising Autoencoders[C]∥Proceedings of the 25th International Conference on Mchine Lear-ning.2008:1096-1103. [16]ZHU X T,ZHANG Y Z,WANG F D.Research on data dimension reduction method based on sparse self-coding network[J].Journal of Shenyang University of Technology,2016,35(5):39-44.(in Chinese) 朱啸天,张艳珠,王凡迪.一种基于稀疏自编码网络的数据降维方法研究[J].沈阳理工大学学报,2016,35(5):39-44. [17]CHEN D Y.Research on dimension reduction algorithm of ma- nifold learning and its application in face recognition[D].Jiangsu:Jiangnan University,2014.(in Chinese) 陈达遥.流形学习降维算法研究及其在人脸识别中的应用[D].江苏:江南大学,2014. [18]WANG H Y.Research on manifold learning feature extraction method and face recognition in subspace[D].Harbin:Harbin Polytechnic University,2017.(in Chinese) 王海燕.子空间的流形学习特征提取方法及人脸识别研究[D].哈尔滨:哈尔滨理工大学,2017. [19]GUO J X,CHEN W.Feature recognition based on HOG multi-feature fusion and random forest[J].Computer Science,2013,40(10):279-284.(in Chinese) 郭金鑫,陈玮.基于HOG多特征融合与随机森林的人脸识别[J].计算机科学,2013,40(10):279-284. [20]FADHLAN K Z,AMIR A S,YASIR M M.Robust Face Recognition Against Expressions and Partial Occlusions[J].International Journal of Automation and Computing,2016,13(4):319-337. |
[1] | 徐涌鑫, 赵俊峰, 王亚沙, 谢冰, 杨恺. 时序知识图谱表示学习 Temporal Knowledge Graph Representation Learning 计算机科学, 2022, 49(9): 162-171. https://doi.org/10.11896/jsjkx.220500204 |
[2] | 饶志双, 贾真, 张凡, 李天瑞. 基于Key-Value关联记忆网络的知识图谱问答方法 Key-Value Relational Memory Networks for Question Answering over Knowledge Graph 计算机科学, 2022, 49(9): 202-207. https://doi.org/10.11896/jsjkx.220300277 |
[3] | 汤凌韬, 王迪, 张鲁飞, 刘盛云. 基于安全多方计算和差分隐私的联邦学习方案 Federated Learning Scheme Based on Secure Multi-party Computation and Differential Privacy 计算机科学, 2022, 49(9): 297-305. https://doi.org/10.11896/jsjkx.210800108 |
[4] | 王剑, 彭雨琦, 赵宇斐, 杨健. 基于深度学习的社交网络舆情信息抽取方法综述 Survey of Social Network Public Opinion Information Extraction Based on Deep Learning 计算机科学, 2022, 49(8): 279-293. https://doi.org/10.11896/jsjkx.220300099 |
[5] | 郝志荣, 陈龙, 黄嘉成. 面向文本分类的类别区分式通用对抗攻击方法 Class Discriminative Universal Adversarial Attack for Text Classification 计算机科学, 2022, 49(8): 323-329. https://doi.org/10.11896/jsjkx.220200077 |
[6] | 姜梦函, 李邵梅, 郑洪浩, 张建朋. 基于改进位置编码的谣言检测模型 Rumor Detection Model Based on Improved Position Embedding 计算机科学, 2022, 49(8): 330-335. https://doi.org/10.11896/jsjkx.210600046 |
[7] | 孙奇, 吉根林, 张杰. 基于非局部注意力生成对抗网络的视频异常事件检测方法 Non-local Attention Based Generative Adversarial Network for Video Abnormal Event Detection 计算机科学, 2022, 49(8): 172-177. https://doi.org/10.11896/jsjkx.210600061 |
[8] | 侯钰涛, 阿布都克力木·阿布力孜, 哈里旦木·阿布都克里木. 中文预训练模型研究进展 Advances in Chinese Pre-training Models 计算机科学, 2022, 49(7): 148-163. https://doi.org/10.11896/jsjkx.211200018 |
[9] | 周慧, 施皓晨, 屠要峰, 黄圣君. 基于主动采样的深度鲁棒神经网络学习 Robust Deep Neural Network Learning Based on Active Sampling 计算机科学, 2022, 49(7): 164-169. https://doi.org/10.11896/jsjkx.210600044 |
[10] | 苏丹宁, 曹桂涛, 王燕楠, 王宏, 任赫. 小样本雷达辐射源识别的深度学习方法综述 Survey of Deep Learning for Radar Emitter Identification Based on Small Sample 计算机科学, 2022, 49(7): 226-235. https://doi.org/10.11896/jsjkx.210600138 |
[11] | 胡艳羽, 赵龙, 董祥军. 一种用于癌症分类的两阶段深度特征选择提取算法 Two-stage Deep Feature Selection Extraction Algorithm for Cancer Classification 计算机科学, 2022, 49(7): 73-78. https://doi.org/10.11896/jsjkx.210500092 |
[12] | 程成, 降爱莲. 基于多路径特征提取的实时语义分割方法 Real-time Semantic Segmentation Method Based on Multi-path Feature Extraction 计算机科学, 2022, 49(7): 120-126. https://doi.org/10.11896/jsjkx.210500157 |
[13] | 王君锋, 刘凡, 杨赛, 吕坦悦, 陈峙宇, 许峰. 基于多源迁移学习的大坝裂缝检测 Dam Crack Detection Based on Multi-source Transfer Learning 计算机科学, 2022, 49(6A): 319-324. https://doi.org/10.11896/jsjkx.210500124 |
[14] | 楚玉春, 龚航, 王学芳, 刘培顺. 基于YOLOv4的目标检测知识蒸馏算法研究 Study on Knowledge Distillation of Target Detection Algorithm Based on YOLOv4 计算机科学, 2022, 49(6A): 337-344. https://doi.org/10.11896/jsjkx.210600204 |
[15] | 周志豪, 陈磊, 伍翔, 丘东亮, 梁广升, 曾凡巧. 基于SMOTE-SDSAE-SVM的车载CAN总线入侵检测算法 SMOTE-SDSAE-SVM Based Vehicle CAN Bus Intrusion Detection Algorithm 计算机科学, 2022, 49(6A): 562-570. https://doi.org/10.11896/jsjkx.210700106 |
|