用于人脸识别的相对梯度直方图特征描述

杨利平; 辜小花

doi:10.3788/OPE.20142201.0152

您当前的位置：

首页 >

文章列表页 >

用于人脸识别的相对梯度直方图特征描述

信息科学 | 更新时间：2020-08-13

- 用于人脸识别的相对梯度直方图特征描述
- Relative gradient histogram features for face recognition
- 光学精密工程 2014年22卷第1期页码：152-159
- 作者机构：
  
  1. 重庆大学光电技术及系统教育部重点实验室重庆,400044
  2. 重庆科技学院重庆,401331
- 作者简介：
- 基金信息：
  
  高等学校博士学科点专项科研基金资助项目(No.20100191120012)();重庆市教委科学技术研究项目(No.KJ121402)();重庆大学中央高校基本科研业务
- DOI：10.3788/OPE.20142201.0152
  中图分类号： TP391.4
- 收稿日期：2013-08-12，
  
  纸质出版日期：2014-01-15
- 稿件说明：
移动端阅览
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 Li-ping, GU Xiao-hua,. Relative gradient histogram features for face recognition[J]. Editorial Office of Optics and Precision Engineering, 2014,22(1): 152-159
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 DOI： 10.3788/OPE.20142201.0152.

YANG Li-ping, GU Xiao-hua,. Relative gradient histogram features for face recognition[J]. Editorial Office of Optics and Precision Engineering, 2014,22(1): 152-159 DOI： 10.3788/OPE.20142201.0152.

摘要

由于方向边缘幅值模式(POEM)在剧烈光照变化情况下无法获得足够的特征描述信息

本文分析了相对梯度幅值图像特点

提出了相对梯度直方图特征描述方法。该方法根据图像的梯度方向对相对梯度幅值图像进行分解、滤波、局部二值模式编码和特征降维

形成了对光照变化

尤其是非均匀光照变化具有健壮性的低维直方图特征。在FERET和YaleB子集上的人脸识别实验证实:在光照变化较小时

相对梯度直方图特征描述方法与方向边缘幅值模式的性能相当

均显著优于经典的局部二值模式特征;在光照剧烈变化时

前者的识别精度比方向边缘幅值模式至少高5%

性能显著优于方向边缘幅值模式和局部二值模式

展示了相对梯度直方图特征描述方法的有效性和对光照变化的良好健壮性。

Abstract

As Pattern of Oriented Edge Magnitude (POEM) method can not acquire enough feature description information in illumination condition changes drastically

this paper analyzes the characteristic of relative gradient magnitude images and proposes a Relative Gradient Histogram Feature(RGHF) description method. The method decomposes the relative gradient magnitude image into several sub images according to the orientations of gradient. Each of these sub images is then filtered and encoded by using Local Binary Patterns(LBPs). Finally

all the encoded LBP histogram features are connected by a lexicographic ordering and are reduced to a low-dimensional subspace to form the RGHF

which is an illumination robust low-dimensional histogram feature. Experimental results on FERET and YaleB subsets indicate when the illumination variation is relative small

the recognition performance of the RGHF is comparable with that of the POEM

superior to that of the LBP significantly. Moreover

when the illumination variation is drastic

the recognition performance of RGHF is at least 5% higher than that of the POEM

more better than those of the POEM and LBP.

关键词

Keywords

references

GAO W, CAO B, SHAN S, et al.. The CAS-PEAL large-scale Chinese face database and baseline evaluations [J]. IEEE Trans. Syst. Man Cybern. Part A-Syst. Hum., 2008, 38(1): 149-161.

杨利平, 龚卫国, 李伟红, 等. 随机采样子空间保局投影人脸识别算法[J]. 光学精密工程, 2008, 16(8): 1465-1470.

YANG L P, GONG W G, LI W H, et al.. Random sampling subspaces locality preserving projections for face recognition [J]. Opt. Precision Eng., 2008, 16(8): 1465-1470. (in Chinese)

BELHUMEUR P, HESPANHA J, KRIEGMAN D. Eigenfaces vs. Fisherfaces: recognition using class specific linear projection [J]. IEEE Trans. Pattern Anal. Mach. Intell., 1997, 19(7): 711-720.

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)

YAN S, XU D, ZHANG B, et al.. Graph embedding and extensions: a general framework for dimensionality reduction [J]. IEEE Trans. Pattern Anal. Mach. Intell., 2007, 29(1):40-51.

LEE K C, HO J, YANG M H, et al.. Visual tracking and recognition using probabilistic appearance manifolds [J]. Comput. Vis. Image Understand. 2005, 99: 303-331.

CHELLAPPA R, NI J, PATEL V M. Remote identification of faces: problems, prospects, and progress [J]. Pattern Recognit. Lett., 2012, 33: 1849-1859.

VU N S, DEE H M, CAPLIER A. Face recognition using the POEM descriptor [J]. Pattern Recognit., 2012, 45: 2478-2488.

ZHANG T H, HUANG K Q, LI X L, et al.. Discriminative orthogonal neighborhood-preserving projections for classification [J]. IEEE Trans. Syst. Man Cybern. Part B-Cybern., 2010, 40(1): 253-263.

TZIMIROPOULOS G, ZAFEIRIOU S, PANTIC M. Subspace learning from image gradient orientations [J]. IEEE Trans. Pattern Anal. Mach. Intell., 2012, 34(12): 2454-2466.

PINTO N, COX D. High-throughput-derived biologically-inspired features for unconstrained face recognition [J]. Image Vis. Comput., 2012, 30: 159-168.

ZHANG B, SHAN S, CHEN X, et al.. Histogram of Gabor phase patterns(HGPP): a novel object representation approach for face recognition [J]. IEEE Trans. Image Process, 2007, 16(1): 57-68.

AHONEN T, HADID A, PIETIKAINEN M. Face description with local binary patterns: application to face recognition [J]. IEEE Trans. Pattern Anal. Mach. Intell., 2006, 28(12): 2037-2041.

OJANSIVU V, HEIKKILA J. Blur insensitive texture classification using local phase quantization [C]. Proceedings of Image and Signal Processing, 2008:236-243.

LOWE D G. Distinctive image features from scale-invariant keypoints [J]. Int. J. Comput. Vis., 2004, 60(2): 91-110.

ALBIOL A, MONZO D, MARTIN A, et al.. Face recognition using HOG-EBGM [J]. Pattern Recognit. Lett., 2008, 29: 1537-1543.

ZHANG T P, TANG Y Y, FANG B, et al.. Face recognition under varying illumination using gradientfaces [J]. IEEE Trans. Image Process., 2009, 18(11): 2599-2606.

龚卫国, 杨利平, 辜小花, 等. 基于多级小波分解的人脸图像光照补偿方法[J]. 光学精密工程, 2008, 16(8): 1459-1464.

GONG W G, YANG L P, GU X H, et al.. Illumination compensation based on multi-level wavelet decomposition for face recognition [J]. Opt. Precision Eng., 2008, 16(8): 1459-1464.(in Chinese)

VU N S, CAPLIER A.Enhanced patterns of oriented edge magnitudes for face recognition and image matching [J]. IEEE Trans. Image Process., 2012, 21(3): 1352-1365.

浏览量

186

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

融合卷积块注意力模块和Siamese神经网络的人脸识别算法

融合分层连续梯度特征的高铁隧道漏缆卡扣检测

基于内容特征提取的短波红外-可见光人脸识别

一种分布式人脸识别方法及性能优化

联合Gabor降维特征与奇异值特征的人脸识别