基于改进的有监督无参局部保持投影算法的人脸识别

doi:10.6040/j.issn.1672-3961.0.2017.419

山东大学学报 (工学版) ›› 2019, Vol. 49 ›› Issue (1): 10-16.doi: 10.6040/j.issn.1672-3961.0.2017.419

基于改进的有监督无参局部保持投影算法的人脸识别

范君^1,²(),业巧林¹,业宁^1,*()

1. 南京林业大学信息科学技术学院, 江苏南京 210037
2. 江苏工程职业技术学院建筑工程学院, 江苏南通 226007

收稿日期:2017-08-24 出版日期:2019-02-20 发布日期:2019-03-01
通讯作者: 业宁 E-mail:13773679049@139.com;njfuyn@163.com
作者简介:范君(1975—)，男，江苏南通人，副教授，硕士，主要研究方向为模式识别，机器学习. E-mail:13773679049@139.com
基金资助:
江苏省高等职业院校国内高级访问学者计划(2016GRFX013);江苏省青蓝工程培养对象(2016-15);江苏省住建厅建设系统科技计划(2017ZD138);江苏省高校哲学社会科学研究(2018SJA1247);校科研计划(GYKY/2017/5, GYKY/2017/12)

Face recognition based on improved prameter-free supervised localitypreserving projections

Jun FAN^1,²(),Qiaolin YE¹,Ning YE^1,*()

1. College of Information Science and Technology, Nanjing Forestry University, Nanjing 210037, Jiangsu, China
2. School of Civil Engineering, Jiangsu College of Engineering and Technology, Nantong 226007, Jiangsu, China

Received:2017-08-24 Online:2019-02-20 Published:2019-03-01
Contact: Ning YE E-mail:13773679049@139.com;njfuyn@163.com
Supported by:
江苏省高等职业院校国内高级访问学者计划(2016GRFX013);江苏省青蓝工程培养对象(2016-15);江苏省住建厅建设系统科技计划(2017ZD138);江苏省高校哲学社会科学研究(2018SJA1247);校科研计划(GYKY/2017/5, GYKY/2017/12)

摘要/Abstract

摘要：

针对局部保持投影算法的无监督性质和参数选择复杂性问题,提出一种改进的有监督无参数局部保持投影算法(supervised dice parameter-free locality preserving projection, SdPLPP)。SdPLPP算法使用广义Dice系数构建近邻矩阵,有效避免局部保持投影(locality preserving projection algorithm, LPP)算法参数选择调整的问题,采用监督模式对数据进行特征提取。SdPLPP在Iris数据集进行了图像可视化试验,直观分析试验分类后的样本距离值与算法性能的关系,并在ORL, Yale, FERET 3种人脸库上进行试验,通过对人脸数据的特征提取,采用最近邻分类法统计识别率,验证SdPLPP算法的有效性。试验结果表明:在人脸识别率方面, SdPLPP算法优于PCA, ULDA, LPP, SPLPP和EP-SLPP的算法,并优于已提出的其他有监督无参数局部保持投影算法。

关键词: 特征提取, 局部保持投影, 无参数近邻矩阵, 广义Dice系数, 人脸识别

Abstract:

To solve the problem of unsupervised and complexity of parameter selection of the locality preserving projection algorithm, an improved supervised dice parameter-free locality preserving projection algorithm (SdPLPP)was proposed. SdPLPP constructed affinity matrix by using generalized Dice coefficient and extract features of data under the supervised mode, which could avoid the problems of parameters selection and adjustment of locality preserving projection (LPP) algorithm. The proposed algorithm performed experiment of image visualization based on the Iris dataset, analyzed the relationship between the value of the distance of sample data and the performance of the algorithm. To verifying the effectiveness and performance of algorithm, SdPLPP carried out the feature extraction experiments based on three kinds of human face databases, such as ORL, Yale and FERET, and used nearest neighbor classifier to get correct recognition rate. The experimental results showed that the SdPLPP algorithm was superior to PCA, ULDA, LPP, SPLPP and EP-SLPP algorithm in face recognition, and it was better than other algorithms of supervised parameter-free locality preserving projections.

Key words: feature extraction, locality preserving projections (LPP), parameter-free affninty matrix, generalized Dice coefficient, face recognition

中图分类号:

TP391.4

范君,业巧林,业宁. 基于改进的有监督无参局部保持投影算法的人脸识别[J]. 山东大学学报 (工学版), 2019, 49(1): 10-16.

Jun FAN,Qiaolin YE,Ning YE. Face recognition based on improved prameter-free supervised localitypreserving projections[J]. Journal of Shandong University(Engineering Science), 2019, 49(1): 10-16.

图/表 7

图1

表1

表2

图2

表3

表4

表5

参考文献 20

1	DUDA R O , HART P E , STORK D G . Pattern classification[M]. 2nd ed USA: John Wiley & Sons, 2009: 2- 4.
2	ROWIES S T , SAUL L K . Nonlinear dimensionality reduction by locally linear embedding[J]. Science, 2000, 290 (5500): 2323- 2326. doi: 10.1126/science.290.5500.2323
3	ZHANG C , WANG J , ZHAO N , et al. Reconstruction and analysis of multi-pose face images based on nonlinear dimensionality reduction[J]. Pattern Recognition, 2004, 37 (2): 325- 336. doi: 10.1016/j.patcog.2003.07.005
4	SAUL L K , ROWIES S T . Think globally, fit locally: unsupervised learning of low dimensional manifolds[J]. Journal of Machine Learning Research, 2003, 4 (2): 119- 155.
5	TENENBAUM J B , SILVA V D , LANGFOR J C . A global geometric framework for nonlinear dimensionality reduction[J]. Science, 2000, 290 (5500): 219.
6	BELKIN M , NIYOGI P . Laplacian eigenmaps for dimensionality reduction and data representation[J]. Neural Computation, 2003, 15 (6): 1373- 1396. doi: 10.1162/089976603321780317
7	HE X , NIYOGI P . Locality preserving projection[J]. Advances in Neural Information Processing Systems, 2002, 16 (1): 186- 197.
8	HE Xiaofei , YAN S , HU Y , et al. Face recognition using laplacian faces[J]. IEEE Trans on Pattern Analysis and Machine Intelligence, 2005, 27 (3): 328- 340. doi: 10.1109/TPAMI.2005.55
9	ZHENG Z , ZHAO Z , YANG Z . Gabor feature-based face recognition using supervised locality preserving projection[J]. Signal Processing, 2007, 87 (10): 2473- 2483. doi: 10.1016/j.sigpro.2007.03.006
10	张宇, 刘雨东, 计钊. 向量相似度测度方法[J]. 声学技术, 2009, 28 (4): 532- 536. doi: 10.3969/j.issn1000-3630.2009.04.021
	ZHANG Yu , LIU Yudong , JI Zhao . Vector similarity measurement method[J]. Technical Acoustics, 2009, 28 (4): 532- 536. doi: 10.3969/j.issn1000-3630.2009.04.021
11	DORNAIKA F , ASSOUM A . Enhanced and parameterless locality preserving projections for face recognition[J]. Neurocomputing, 2013, 99 (1): 448- 457.
12	黄璞, 唐振民. 无参数局部保持投影及人脸识别[J]. 模式识别与人工智能, 2013, 26 (9): 856- 871.
	HUANG Pu , TANG Zhenmin . Parameter-free locality preserving projections and face recognition[J]. Pattern Recognition and Artifical Intelligenc, 2013, 26 (9): 856- 871.
13	龚劬, 许凯强. 有监督的无参数核局部保持投影及人脸识别[J]. 计算机科学, 2016, 43 (9): 301- 309.
	GONG Qu , XU Kaiqiang . Parameter-less supervised kernel locality preserving projection and face recognition[J]. Computer Science, 2016, 43 (9): 301- 309.
14	梅玲玲, 龚劬. 基于改进的自适应局部保持投影算法的人脸识别[J]. 计算机科学, 2016, 43 (8): 286- 291.
	MEI Lingling , GONG Qu . Face recognition based on improved adaptive locality preserving projection[J]. Computer Science, 2016, 43 (8): 286- 291.
15	邹国锋, 姜树明, 张元元, 等. 基于最大分离度差的有监督核局部保持投影[J]. 计算机应用研究, 2014, 31 (7): 2228- 2232. doi: 10.3969/j.issn.1001-3695.2014.07.075
	ZOU Guofeng , JIANG Shuming , ZHANG Yuanyuan , et al. Supervised kernel locality preserving projection algorithm based on maximum separation degree difference[J]. Application Research of Computers, 2014, 31 (7): 2228- 2232. doi: 10.3969/j.issn.1001-3695.2014.07.075
16	王永茂, 赵珊. 改进的基于DCT与局部保持投影的人脸识别方法[J]. 华中师范大学学报(自然科学版), 2014, 48 (2): 177- 181.
	WANG Yongmao , ZHAO Shan . Improved method based on dct and locality preserving projection for face recognition[J]. Journal of Hua Zhong Normal University (Nat Sci), 2014, 48 (2): 177- 181.
17	丁铭, 贾维敏, 姚敏立. 基于L2范数的局部保持投影算法[J]. 西安交通大学学报, 2016, 50 (2): 33- 37.
	DING Ming , JIA Weimin , YAO Minli . A projection algorithm with local preservation based on l2 norm[J]. Journal of Xi′an Jiaotong University, 2016, 50 (2): 33- 37.
18	LI F , WANG J , TANG B , et al. Life grade recognition method based on supervised uncorrelated orthogonal locality preserving projection and K-nearest neighbor classifier[J]. Neurocomputing, 2014, 138 (138): 271- 282.
19	JOHN Soldera , CARLOS Alberto , RAMIREZ Behaine , et al. Customized orthogonal locality preserving projections with soft-margin maximization for face recognition[J]. IEEE Transactions on Instrumentation and Measurement, 2015, 64 (9): 2417- 2426. doi: 10.1109/TIM.2015.2415012
20	WANG R , NIE F , HONG R , et al. Fast and orthogonal locality preserving projections for dimensionality reduction[J]. IEEE Transactions on Image Processing, 2017, 26 (10): 5019- 5030. doi: 10.1109/TIP.2017.2726188

多维度评价

Viewed

Full text

Abstract

Cited

Shared

Discussed

cm
算法	M₁	M₂	M₃	S_w23	S_b23	r₂₃
PCA	0.54	0.77	0.92	0.84	1.56	1.84
ULDA	0.14	0.13	0.17	0.15	0.17	1.13
LPP	0.49	0.74	0.88	0.81	1.64	2.03
SPLPP	0.39	0.39	0.44	0.41	0.80	1.93
EP-SLPP	0.35	0.35	0.45	0.40	0.94	2.35
SdPLPP	0.32	0.59	0.68	0.63	1.64	2.58

%
算法	训练集个数
算法	2	3	4	5
PCA	68.40	78.25	83.13	87.90
ULDA	79.47	86.46	91.08	93.95
LPP	67.53	77.43	82.25	87.05
SPLPP	71.44	81.36	85.08	89.30
EP-SLPP	79.50	86.46	91.25	94.05
SdPLPP	83.66	91.07	94.33	96.50

%
算法	训练集个数
算法	2	3	4	5
PCA	42.15	48.83	52. 67	56.11
ULDA	56.00	66.83	74.57	77.44
LPP	41.78	49.25	52.29	55.11
SPLPP	42.96	50.25	53.14	56.89
EP-SLPP	54.52	66.75	74.86	78.78
SdPLPP	55.04	66.92	75.90	80.11

训练集	Test1	Test2	Test3	Test4
组合方式	Ia+Ib+Id	Ia+Ib+Ie	Ia+Ic+Id	Ia+Ic+Ie

%
算法	训练集
算法	Test1	Test2	Test3	Test4
PCA	78.25	81.75	70.75	73.50
ULDA	78.17	85.83	74.67	83.67
LPP	78.75	81.75	71.00	74.00
SPLPP	78.75	82.00	70.75	74.00
EP-SLPP	88.33	92.33	80.67	89.17
SdPLPP	86.50	90.67	82.50	89.67

基于改进的有监督无参局部保持投影算法的人脸识别

Face recognition based on improved prameter-free supervised localitypreserving projections

RichHTML

PDF (PC)

摘要/Abstract

引用本文

使用本文

图/表 7

参考文献 20

相关文章 15

多维度评价

本文评价

推荐阅读 10

[1]	那绪博,张莹,李沐阳,陈元畅,华云鹏. 基于ODCG的网约车需求预测模型[J]. 山东大学学报 (工学版), 2023, 53(5): 48-56.
[2]	李颖,王建坤. 基于监督图正则化和信息融合的轻度认知障碍分类方法[J]. 山东大学学报 (工学版), 2023, 53(4): 65-73.
[3]	张学思,张婷,刘兆英,江天鹏. 基于轻量型卷积神经网络的海面红外显著性目标检测方法[J]. 山东大学学报 (工学版), 2022, 52(2): 41-49.
[4]	刘笑,陈家炜,胡峻林. 用于亲属关系鉴别的成对约束组合度量学习[J]. 山东大学学报 (工学版), 2022, 52(2): 50-56.
[5]	曹春红,段鸿轩,曹玲,张乐乐,胡凯,肖芬. 基于多级特征级联的遥感图像实时语义分割[J]. 山东大学学报 (工学版), 2021, 51(2): 19-25.
[6]	杨煦,陈辉,林游思,屠长河. 飞行蝙蝠标记自动提取与追踪算法[J]. 山东大学学报 (工学版), 2019, 49(2): 67-73.
[7]	王国新,陈凤东,刘国栋. 基于彩色伪随机编码结构光特征提取方法[J]. 山东大学学报 (工学版), 2018, 48(5): 55-60.
[8]	叶子云,杨金锋. 一种基于加权图模型的手指静脉识别方法[J]. 山东大学学报(工学版), 2018, 48(3): 103-109.
[9]	张振月,李斐,江铭炎. 基于低秩表示投影的无监督人脸特征提取[J]. 山东大学学报(工学版), 2018, 48(1): 15-20.
[10]	于青民,李晓磊,翟勇. 基于改进EMD和数据分箱的轴承内圈故障特征提取方法[J]. 山东大学学报(工学版), 2017, 47(3): 89-95.
[11]	郭超,杨燕,江永全,宋祎. 基于多视图分类集成的高铁工况识别[J]. 山东大学学报(工学版), 2017, 47(1): 7-14.
[12]	钟智彦,文志强, 张潇云,叶德刚. 基于半色调图像的邻域相似性描述子方法[J]. 山东大学学报(工学版), 2016, 46(3): 58-64.
[13]	周凯,元昌安,覃晓,郑彦,冯文铎. 基于核贝叶斯压缩感知的人脸识别[J]. 山东大学学报(工学版), 2016, 46(3): 74-78.
[14]	卢丹, 周以齐. 基于EEMD和CWT的挖掘机座椅振动分析[J]. 山东大学学报(工学版), 2015, 45(3): 58-64.
[15]	任捷怡, 吴小俊. 一种改进的协方差鉴别学习方法[J]. 山东大学学报(工学版), 2015, 45(1): 9-12.