Shearlet多方向特征融合与加权直方图的人脸识别算法

周霞; 张鸿杰; 王宪

doi:doi:10.3969/j.issn.1003-501x.2013.11.015

光电工程, 2013, 40 (11): 89, 网络出版: 2013-12-04

Shearlet多方向特征融合与加权直方图的人脸识别算法

Face Recognition Based on Shearlet Multi-orientation Features Fusion and Weighted Histogram

论文大纲

周霞 ^*张鸿杰王宪

作者单位

轻工过程先进控制教育部重点实验室 (江南大学 ), 江苏无锡 214122

人脸识别加权直方图特征融合 Shearlet变换 face recognition weighted histogram feature fusion Shearlet transform

摘要

针对 Shearlet变换在提取特征数据时存在冗余性以及无法对全局特征进行稀疏表征的缺点, 提出了一种 Shearlet多方向特征融合与加权直方图的人脸识别算法。首先, 对原始图像采用 Shearlet变换得到多尺度多方向的人脸特征, 然后按照两种编码方式将同一尺度下不同方向的特征进行编码融合, 并将融合后的尺度图像划分为若干大小相等的不重叠矩形块, 利用 Shannon熵理论对各子模式进行加权融合。在 ORL、FERET和 YALE人脸库中做了多组实验, 充分证明该算法相对于传统 Shearlet滤波器在分类识别上更具有优势。

Abstract

The Shearlet multi-orientation features fusion and weighted histogram are proposed to overcome the disadvantage of Shearlet transform, which has data redundance in extracting features and cannot sparsely represent the global characters. First, Shearlet transform is used to extract the multi-orientation facial features. Then two coding methods are proposed to fuse the features from different directions of the same scale into a single feature, and the fused image is divided into a number of equal-sized nonoverlapping rectangular blocks, weighted fusion of each model using the Shannon entropy theory. Many experiments have been done on the ORL, FERET and YALE face database, which fully proved that this method has more advantages in terms of recognition than the traditional Shearlet.

参考文献

[1] Phillips P, Flynn P, Scruggs T, et al. Overview of the face recognition grand challenge [C]// IEEE Computer Society Conference on Computer Vision and Pattern Recognition, San Diego, CA, USA, June 20-25, 2005, 1：947-954.

[2] GAO Xinbo, LU Wen, TAO Dacheng, et al. Image Quality Assessment Based on Multiscale Geometric Analysis [J]. IEEE Transaction on Image Processing(S1057-7149), 2009, 18(7)：807-815.

[3] Woiselle A, Starck J L, Fadili J. 3-D Data Denoising and Inpainting with the Low-Redundancy Fast Curvelet Transform [J]. Journal of Mathematical Imaging and Vision(S0924-9907), 2011, 39(2)：121-139.

[4] YANG Shuyuan, WANG Min, JIAO Licheng, et al. Image fusion based on a new contourlet packet [J]. Information Fusion(S1566-2535), 2010, 11(2)：78-84.

[5] Guo K, Labate D. Optimally sparse multidimensional representation using Shearlets [J]. SIAM Journal on Mathematical Analysis (S0036-1410), 2007, 39：298-318.

[6] Toet A, Hogervorst M A, Nikolov S G, et al. Towards cognitive image fusion [J]. Information Fusion(S1566-2535), 2010, 11(2)：95-113.

[7] 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, 37(12)： 1455-1463.

LIU Shuaishi, TIAN Yantao, WAN Chuan. Facial Expression Recognition Method Based on Gabor Multi-orientation Features Fusion and Block Histogram [J]. Acta Automatica Sinica, 2011, 37(12)：1455-1463.

[8] 李岚, 师飞龙, 徐楠楠. 自适应加权局部相位量化的人脸识别 [J].光电工程, 2012, 39(12)：138-142.

LI Lan, SHI Feilong, XU Nannan. Face recognition based on adaptively weighted local phase quantization [J]. Opto-Electronic Engineering, 2012, 39(12)：138-142.

[9] Guo K, Labate D, Lim W Q. Edge analysis and identification using the continuous shearlet transform [J]. Applied and Computational Harmonic Analysis(S1063-5203), 2009, 27(1)：24-26.

[10] ZHANG Yan, YU Bin, GU Haimin. Face Recognition Using Curvelet-Based Two-Dimensional Principle Component Analysis [J]. International Journal of Pattern Recognition and Artificial Intelligence(S0218-0014), 2012, 26(3)：1-13.

[11] XIA Wei, YIN Shouyi, OUYANG Peng. A High Precision Feature Based on LBP and Gabor Theory for Face Recognition [J]. Sensors(S1424-8220), 2013, 13(4)：4499-4513.

[12] CHENG Yong, HOU Yingkun, ZHAO Chunxia, et al. Robust face recognition based on illumination invariant in nonsubsampled contourlet transform domain [J]. Neurocomputing(S0925-2312), 2010, 73(10)：2217-2224.

周霞, 张鸿杰, 王宪. Shearlet多方向特征融合与加权直方图的人脸识别算法[J]. 光电工程, 2013, 40(11): 89. ZHOU Xia, ZHANG Hongjie, WANG Xian. Face Recognition Based on Shearlet Multi-orientation Features Fusion and Weighted Histogram[J]. Opto-Electronic Engineering, 2013, 40(11): 89.

Shearlet多方向特征融合与加权直方图的人脸识别算法

关于本站 Cookie 的使用提示

全站搜索

Shearlet多方向特征融合与加权直方图的人脸识别算法

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索