Face recognition based on Gabor reduction dimensionality features and singular value decomposition features

WANG Xiao-hua; SUN Xiao-jiao

doi:10.3788/OPE.20152313.0554

您当前的位置：

首页 >

文章列表页 >

Face recognition based on Gabor reduction dimensionality features and singular value decomposition features

更新时间：2020-08-13

- Face recognition based on Gabor reduction dimensionality features and singular value decomposition features
- Optics and Precision Engineering Vol. 23, Issue 10z, Pages: 553-558(2015)
- 作者机构：
  
  西安工程大学电信学院西安,710048
- 作者简介：
- 基金信息：
- DOI：10.3788/OPE.20152313.0554
  CLC： TP391.4
- Received：05 May 2015，
  
  Revised：29 May 2015，
  
  Published：14 November 2015
- 稿件说明：
移动端阅览
王晓华, 孙小姣,. 联合Gabor降维特征与奇异值特征的人脸识别[J]. 光学精密工程, 2015,23(10z): 553-558

WANG Xiao-hua, SUN Xiao-jiao,. Face recognition based on Gabor reduction dimensionality features and singular value decomposition features[J]. Editorial Office of Optics and Precision Engineering, 2015,23(10z): 553-558
王晓华, 孙小姣,. 联合Gabor降维特征与奇异值特征的人脸识别[J]. 光学精密工程, 2015,23(10z): 553-558 DOI： 10.3788/OPE.20152313.0554.

WANG Xiao-hua, SUN Xiao-jiao,. Face recognition based on Gabor reduction dimensionality features and singular value decomposition features[J]. Editorial Office of Optics and Precision Engineering, 2015,23(10z): 553-558 DOI： 10.3788/OPE.20152313.0554.

摘要

针对传统的Gabor特征表征图像的全局特征能力较差的问题

提出一种采用Gabor多方向降维特征与图像的奇异值特征相联合的人脸特征表征方法。该方法在对Gabor滤波器直流分量补偿的基础上优化滤波器尺度伸缩随中心频率而变化的性能

以提取人脸图像的多尺度、多方向特征;对同一尺度不同方向的Gabor特征相加以降低特征维数。同时分别提取整幅图像的奇异值分解(SVD)全局特征以及分块SVD特征

将Gabor局部特征分别与上述SVD特征联合起来表征人脸图像。为提高计算效率

应用人脸采样图像进行了实验。实验结果表明

所提方法更好地保留了图像的局部细节、降低了特征数据的冗余

在识别率和计算率上都较传统Gabor滤波器更具优势

在ORL人脸库上的识别率高达98.21%。

Abstract

For the disability of traditional Gabor filter bank on poor global feature representation

Gabor reduction dimensionality features are combined with the Singular Value Decompasition(SVD) global features of an image to characterize the facial features. On the basis of compensating the DC component in the Gabor filter

the scale retractable performance of the filter which varies with its center frequency is optimized to extract multi-scale

multi-orientation of face images. The features were added in same scale of different directions to reduce the dimensionality of features. Meanwhile

the SVD features in the whole image and block image were extracted respectively

then local Gabor features and the SVD feature mentioned above were joint to characterize the face image respectively. In order to improve computational efficiency

the face image was sampled to obtain a sample image. Experimental results show that the proposed method maintains image details and reduces the redundance of feature data better. It shows greater recognition rate and calculation rates than the traditional Gabor filter

and the recognition rate in ORL face database is up to 98.21%.

关键词

Keywords

references

杨利平,辜小花. 用于人脸识别的相对梯度直方图特征描述[J]. 光学精密工程,2014,22(1):152-159. YANG L P,GU X H,Relative gradient histogram features for face recognition[J]. Opt. Precision Eng., 2014, 22(1):152-159.(in Chinese)

杨利平,辜小花,叶洪伟. 用于分类的样本保局鉴别分析方法[J]. 光学精密工程, 2011,19(9):2205-2213. YANG L P,GU X H,YE H W. Sample locality preserving discriminant analysis for classification[J].Opt. Precision Eng.,2011,19(9):2205-2213.(in Chinese)

LEE T S. Image representation using 2D Gabor wavelets[J].IEEE Transactions on Pattern Analysis and Machine Intelligence, 1996, 18(10):959-971.

CHO, HYUNJONG R, RODNEY, et al.. An efficient hybrid face recognition algorithm using PCA and GABOR wavelets[J]. International Journal of Advanced Robotic Systems,2014,4(9):4-12.

刘帅师,田彦涛,万川. 基于Gabor多方向特征融合与分块直方图的人脸表情识别方法[J]. 自动化学报,2011,12(37):1455-1462. LIU SH S,TIAN Y T,WAN CH. Facial expression recognition method based on Gabor multi orientation features fusion and block histogram[J]. Acta Automatica Sinica, 2011, 12(37):1455-1462.(in Chinese)

杨波, 敬忠良. 梅花形采样离散小波框架图像融合算法[J]. 自动化学报, 2010, 36(1):12-22. YANG B, JING ZH L. Image fusion algorithm based on the quincunx-sampled discrete wavelet frame[J]. Acta Automatica Sinica, 2010, 36(1):12-22).(in Chinese)

AHEN H, CHAI, ZH N, HEYDI M V, et al..Gabor ordinal measures for face recognition[J]. IEEE Trans. on Information Forensics and Security, 2014,9(1):14-26.

PINTO N, COX D,High through put derived biologically inspried features for unconstrained face recognition[J].Image Vis. Comput., 2013, 30:159-168.

LUDMILA,KUNCHEV. A theoretical study on six classifier fusion strategies[J]. IEEE Trans. On PAMI,2013,24(2):281-286.

WANG SH ZH. Sparse matrix of image denoising method based on SVD[J]. International Journal of Multimedia and Ubiquitous Engineering, 2014,7(9):.227-236.

AHMADYFARD A, ALIMOHAMADI H, SHARIATI A. A novel approach for detecting defects of random textured tiles using Gabor wavelet[C]. WASJ,2012, 7:1114-1119.

AHONEEN T, HADID A, PIETIKAINEN M. Face description with local binary patterns:application to face recognition[J]. IEEE Trans Pattern Anal Mach Intell, 2006,28:2037-2041.

Views

239

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Face recognition algorithm incorporating CBAM and Siamese neural network

Shortwave infrared visible-light face recognition based on content feature extraction

A distributed face recognition method and performance optimization

Salient detection via local and global feature

3D to 2D: Facial intrinsic shape description maps

Related Author

MENG Tiansheng

WANG Guicong

LI Yingjun

MENG Xiangzhou

Chen-feng LOU

Yong ZHANG

Lin-miao HU

Wei-dong MIN

Related Institution

School of Mechanical Engineering， University of Jinan

University of Chinese Academy of Science

Key Laboratory of Infrared System Detection and Imaging Technology， Chinese Academy of Science

Shanghai Institute of Technical Physics， Chinese Academy of Science

School of Computer Science and Software Engineering, Tianjin Polytechnic University

AI问答

Address：No.3888 Dong Nanhu Road, Changchun, Jilin, China Postal code：130033
Tel：0431-86176855 Email：gxjmgc@ciomp.ac.cn
Technical support is provided by Beijing Founder electronics co., LTD 吉ICP备11002662号-17 京公网安备11010802024621
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰