融合小波包细节子图及稀疏表示的人脸识别

龚飞; 金炜; 符冉迪; 刘箴; 李纲

doi:doi:10.3969/j.issn.1003-501x.2016.06.006

光电工程, 2016, 43 (6): 32, 网络出版: 2016-07-26

融合小波包细节子图及稀疏表示的人脸识别

Face Recognition Based on the Fusion of Wavelet Packet Sub-images and Sparse Representation

论文大纲

龚飞 ^*金炜符冉迪刘箴李纲

作者单位

宁波大学信息科学与工程学院，浙江宁波 315211

人脸识别小波包分解稀疏表示鲁棒性 face recognition wavelet packet decomposition sparse representation FW-SRC FW-SRC robustness -14

摘要

针对现有人脸识别方法在光照变化、表情变化及噪声干扰等情况下识别率下降的问题，本文将主成分分析 (PCA)，图像的小波包分解 (WPD)和稀疏表示分类 (SRC)等算法结合起来进行研究分析，提出了一种融合小波包细节子图及稀疏表示 (FW-SRC)的人脸识别方法。该方法首先将图像小波包分解以后的子图像进行加权融合，对融合后的图像进行特征提取并构造特征空间，然后用样本在特征空间上的投影集构造稀疏字典，最后通过对人脸图像的稀疏表示实现分类识别。采用 Yale B、AR和 CMU PIE人脸库分别进行了光照、表情及噪声鲁棒性的测试，实验结果表明本文方法不仅提高了人脸识别率，而且在光照强度变化、表情变化以及噪声干扰的情况下具有良好的识别性能。

Abstract

Under the influence of factors such as the variations in illumination, facial expressions and noises, the accuracy of many current face recognition methods is not very satisfactory. A face recognition method named FW-SRC isproposed which is based on the fusion of wavelet packet sub-images (FW) and Sparse Representation-based Classification (SRC) via the combining research and analysis of Principal Component Analysis (PCA), wavelet packet decomposition (WPD) of images and SRC. The proposed method extracted features from the weighted fusion images of wavelet packet sub-images and then constructed the feature space by the weighted fusion images, and constructed sparse dictionary by projection of samples on the feature space, at last classified the faces by SRC. Experimental results on the Yale B, AR and CMU PIE face databases for the robustness test show that the proposed method improves the accuracy for face recognition and it has a good performance.

参考文献

[1] Wright J，Yang A Y，Ganesh A，et al. Robust face recognition via sparse representation [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence(S0162-8828)，2009，31(2)：210-227.

[2] 张勇，党兰学 .线性判别分析特征提取稀疏表示人脸识别方法 [J].郑州大学学报：工学版， 2015，36(2)：94-98. ZHANG Yong，DANG Lanxue. Sparse Representation-based Face Recognition Method by LDA Feature Extraction [J]. Journal of Zhengzhou University: Engineering Science，2015，36(2)：94-98.

[3] YANG Meng，ZHANG Lei. Gabor feature based robust representation and classification for face recognition with Gabor occlusion dictionary [J]. Pattern Recognition(S0031-3203)，2013，46(7)：1865-1878.

[4] ZHANG Lei，YANG Meng，FENG Xiangchu，et al. Sparse representation or collaborative representation: Which helps face recognition [C]// IEEE International Conference on Computer Vision(ICCV’2011)，Barcelona，Spain，Nov 6-13，2011： 471-478.

[5] 刘梓，宋晓宁，唐振民 . 稀疏表示和贪婪搜索的人脸分类 [J].中国图象图形学报， 2015，20(1)：39-49. LIU Zi，SONG Xiaoning，TANG Zhenmin. Sparse representation based face recognition classification algorithm using greedy search strategy [J]. Journal of Image and Graphics，2015，20(1)：39-49.

[6] ZHANG Lihe，ZHANG Kunyu. Weighted discriminative sparse coding for image classification [J]. Chinese Journal of Electronics(S1022-4653)，2014，23(1)：104-108.

[7] LIU Zhonghua，PU Jiexin，XU Meiyu，et al. Face Recognition Via Weighted Two Phase Test Sample Sparse Representation [J]. Neural Processing Letters(S1370-4621)，2015，41(1)：45-53.

[8] 吴倩，张荣，徐大卫 .基于稀疏表示的高光谱数据压缩算法 [J]. 电子与信息学报， 2015，37(1)：78-84. WU Qian，ZHANG Rong，XU Dawei. Hyperspectral Data Compression Based on Sparse Representation [J]. Journal of Electronics and Information Technology，2015，37(1)：78-84.

[9] YIN Kuang，LEI Zhang，ZHANG Yi. Image Denoising Via Sparse Dictionaries Constructed by Subspace Learning [J]. Circuits, Systems, and Signal Processing(S0278-081X)，2014，33(7)：2151-2171.

[10] 金炜，王文龙，符冉迪，等 .联合块匹配与稀疏表示的卫星云图修复 [J]. 光学精密工程， 2014，22(7)：1886-1895. JIN Wei，WANG Wenlong，FU Randi，et al. Satellite cloud image inpainting based on patch matching and sparse representation [J]. Optics and Precision Engineering，2014，22(7)：1886-1895.

[11] Georghiades A，Kriegman D，Belhumeur P. From few to many：Illumination cone models for face recognition under variable lighting and pose [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence(S0162-8828)，2001，23(6)：643-660.

[12] The AR face database [R]. CVC Technical Report#24，June，1998.

[13] Sim T，Baker S，Bsat M. The CMU pose，illumination，and expression database [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence(S0162-8828)，2003，25(12)：1615-1618.

龚飞, 金炜, 符冉迪, 刘箴, 李纲. 融合小波包细节子图及稀疏表示的人脸识别[J]. 光电工程, 2016, 43(6): 32. GONG Fei, JIN Wei, FU Randi, LIU Zhen, LI Gang. Face Recognition Based on the Fusion of Wavelet Packet Sub-images and Sparse Representation[J]. Opto-Electronic Engineering, 2016, 43(6): 32.

融合小波包细节子图及稀疏表示的人脸识别

关于本站 Cookie 的使用提示

全站搜索

融合小波包细节子图及稀疏表示的人脸识别

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索