一种改进的局部嵌入网络人脸图像分类方法

doi:10.19665/j.issn1001-2400.2020.04.003

西安电子科技大学学报 ›› 2020, Vol. 47 ›› Issue (4): 18-23.doi: 10.19665/j.issn1001-2400.2020.04.003

一种改进的局部嵌入网络人脸图像分类方法

刘道华^1,²(),王莎莎¹,杨志鹏¹,崔玉爽¹

1.信阳师范学院计算机与信息技术学院,河南信阳 464000
2.信阳师范学院河南省教育大数据分析与应用重点实验室,河南信阳 464000

收稿日期:2020-01-29 出版日期:2020-08-20 发布日期:2020-08-14
作者简介:刘道华(1974—),男,教授,博士,E-mail:ldhzzx@163.com.
基金资助:
国家自然科学基金资助(61572417);河南省高等学校重点科研资助(19A520035)

Improved face image classification method based on the local embedding network

LIU Daohua^1,²(),WANG Shasha¹,YANG Zhipeng¹,CUI Yushuang¹

1. School of Computer and Information Technology, Xinyang Normal University, Xinyang 464000, China
2. Henan Key Lab. of Analysis and Applications of Education Big Data, Xinyang Normal University, Xinyang 464000, China

Received:2020-01-29 Online:2020-08-20 Published:2020-08-14

摘要/Abstract

摘要：

为提高局部线性嵌入网络在人脸表情识别上的精度以及人脸分类的准确性,提出了一种改进的局部线性嵌入网络人脸图像分类方法。该方法在局部线性嵌入算法的基础上,利用类内-类间判别矩阵作为网络的输入,同时利用重构人脸图像集对局部线性嵌入算法进行改进,并将改进的基于聚类的局部线性嵌入算法嵌入到卷积核的构造过程中,从而增加了不同类别人脸的区分度。通过在Extended Yale B数据集和Olivetti Research Laboratory数据集上进行对比实验,分析了在处理人脸表情和人脸识别任务中不同方法的效果。结果表明,所提出的改进局部线性嵌入网络人脸图像分类方法比文献中其他方法在识别率上提高了11%~26%。

关键词: 特征表达, 局部线性嵌入网络, 区分度, 图像分类

Abstract:

In order to improve the accuracy of facial expression recognition and face classification in a local linear embedding network, an improved face image classification method based on the local linear embedding network is proposed. Based on the local linear embedding algorithm, the intra-class to inter-class discrimination matrix is used as the input of the network. At the same time, the reconstruction of the face image set is used to improve the local linear embedding algorithm, and the improvement of the local linear embedding algorithm based on clustering is embedded into the construction process of the convolution kernel, thus increasing the discrimination degree of different types of faces. By the Extended Yale B data set and Olivetti Research Laboratory data set on the contrast experiment, the experiment is analyzed in the treatment of facial expressions and the effects of various methods in the face recognition task, the results show that, compared with the other methods, the recognition rate of the proposed improved locally linear embedding network face image classification method is raised by 11%~26%.

Key words: feature expression, locally linear embedded network, discriminative power, image classification

中图分类号:

TP391

刘道华,王莎莎,杨志鹏,崔玉爽. 一种改进的局部嵌入网络人脸图像分类方法[J]. 西安电子科技大学学报, 2020, 47(4): 18-23.

LIU Daohua,WANG Shasha,YANG Zhipeng,CUI Yushuang. Improved face image classification method based on the local embedding network[J]. Journal of Xidian University, 2020, 47(4): 18-23.

图/表 5

图1

图2

图3

图4

表1

参考文献 10

[1]	LU S, LU Z, ZHANG Y D. Pathological Brain Detection Based on AlexNet and Transfer Learning[J]. Journal of Computational Science, 2019,40(30):41-47.
[2]	LI C, MA L. A New Framework for Feature Descriptor Based on SIFT[J]. Pattern Recognition Letters, 2009,30(5):544-557. doi: 10.1016/j.patrec.2008.12.004
[3]	韩冰, 贾中华, 高新波. 改进的主成分分析网络极光图像分类方法[J]. 西安电子科技大学学报, 2017,44(1):83-88.
	HAN Bing, JIA Zhonghua, GAO Xinbo. Improved PCANEeT for Aurora Images Classification[J]. Journal of Xidian University, 2017,44(1):83-88.
[4]	李昌湘, 白创. 嵌入式人脸识别系统设计与实现[J]. 智能计算机与应用, 2018,8(3):115-117.
	LI Changxiang, BAI Chuang. Design and Implementation of Embedded Face Recognition System[J]. Intelligent Computer and Applications, 2018,8(3):115-117.
[5]	PRADO-JARAMILLO N, ESTARRON-ESPINOSA M, ESCALONA-BUENDIA H, et al. Volatile Compounds Generation During Different Stages of the Tequila Production Process[J]. LWT - Food Science and Technology, 2015,61(2):471-483. doi: 10.1016/j.lwt.2014.11.042
[6]	吴青, 祁宗仙, 臧博研, 等. 自适应局部稀疏线性嵌入降维算法[J]. 西安邮电大学学报, 2019,24(2):67-71.
	WU Qing, QI Zongxian, ZANG Boyan, et al. A Dimension-reduction Method Based on Locally and Sparsely Adaptive Linear Embedding[J]. Journal of Xi’an University of Posts and Telecommunications, 2019,24(2):67-71.
[7]	欧阳宁, 王先傲, 蔡晓东, 等. 结合小波与递归神经网络的低分辨率人脸识别[J]. 西安电子科技大学学报, 2019,46(6):95-101.
	OUYANG Ning, WANG Xianao, CAI Xiaodong, et al. Low Resolution Face Recognition Method Based on Wavelet and Recursive Neural Networks[J]. Journal of Xidian University, 2019,46(6):95-101.
[8]	TONG S G, HUANG Y Y, TONG Z M. A Robust Face Recognition Method Combining LBP with Multi-mirror Symmetry for Images with Various Face Interferences[J]. International Journal of Automation and Computing, 2019,16(5):671-682. doi: 10.1007/s11633-018-1153-8
[9]	SHI J, WU J, LI Y, et al. Histopathological Image Classification with Color Pattern Random Binary Hashing-Based PCANet and Matrix-Form Classifier[J]. IEEE Journal of Biomedical and Health Informatics, 2017,21(5):1327-1337. pmid: 27576270
[10]	LEE K C, HO J, KRIEGMAN D J. Acquiring Linear Subspaces for Face Recognition under Variable Lighting[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005,27(5):684-698. doi: 10.1109/TPAMI.2005.92 pmid: 15875791

提取方法	遮挡比例
提取方法	0%	20%	40%	60%	80%
LBP	75.74	66.64	55.62	44.33	19.16
LLENet	84.14	82.32	76.48	72.49	43.74
PCANet	95.72	92.16	83.96	86.47	51.74
P-LBP	94.13	91.84	83.13	70.96	41.74
CLLE	97.72	97.54	96.65	90.47	62.87

一种改进的局部嵌入网络人脸图像分类方法

Improved face image classification method based on the local embedding network

RichHTML

PDF (PC)

赞

可视化

摘要/Abstract

引用本文

使用本文

图/表 5

参考文献 10

相关文章 8

Metrics

本文评价

推荐阅读 10

[1]	程德,郝毅,周靖宇,王楠楠,高新波. 利用混合双通路神经网络的跨模态行人重识别[J]. 西安电子科技大学学报, 2021, 48(5): 190-200.
[2]	宋建锋,韦玥,苗启广,权义宁,陈毓生. 压缩激励机制驱动的尿液细胞图像分类算法[J]. 西安电子科技大学学报, 2020, 47(2): 39-45.
[3]	孙宸, 成立业. 空间感知矩阵学习的极化SAR图像分类[J]. 西安电子科技大学学报, 2018, 45(6): 92-98.
[4]	李雪, 艾丽蓉, 周晓京, 张凯. 幼儿视力检查的自动评测方法[J]. 西安电子科技大学学报, 2018, 45(6): 150-155.
[5]	陈博;王爽;焦李成;刘芳;毛莎莎. 贝叶斯集成框架下的极化SAR图像分类 [J]. J4, 2015, 42(2): 45-51.
[6]	韩冰;仇文亮. 一种特征显著性编码的极光图像分类方法[J]. J4, 2013, 40(6): 180-186.
[7]	杨曦;李洁;韩冰;高新波. 一种分层小波模型下的极光图像分类算法[J]. J4, 2013, 40(2): 18-24.
[8]	孔月萍;曾平;张跃鹏. 一种半调图像分类识别算法[J]. J4, 2011, 38(5): 52-58+183.