[1]邵珠宏,欧阳军林,廖帆,等.基于局部特征和集成学习的鲁棒彩色人脸识别算法[J].东南大学学报(自然科学版),2015,45(2):251-255.[doi:10.3969/j.issn.1001-0505.2015.02.010]
　Shao Zhuhong,Ouyang Junlin,Liao Fan,et al.Robust color face recognition algorithm based on local features and ensemble learning[J].Journal of Southeast University (Natural Science Edition),2015,45(2):251-255.[doi:10.3969/j.issn.1001-0505.2015.02.010]
点击复制

基于局部特征和集成学习的鲁棒彩色人脸识别算法()
分享到：

《东南大学学报(自然科学版)》[ISSN:1001-0505/CN:32-1178/N]

卷:
45
期数:
2015年第2期
页码:
251-255
栏目:
计算机科学与工程
出版日期:
2015-03-20

文章信息/Info

Title:
Robust color face recognition algorithm based on local features and ensemble learning
作者:
邵珠宏; 欧阳军林; 廖帆; 舒华忠
东南大学影像科学与技术实验室, 南京210096
Author(s):
Shao Zhuhong;  Ouyang Junlin;  Liao Fan;  Shu Huazhong
Laboratory of Image Sciences and Technology, Southeast University, Nanjing 210096, China
关键词:
彩色人脸识别;  局部特征;  四元数pseudo-Zernike矩;  集成学习
Keywords:
color face recognition;  local feature;  quaternion pseudo-Zernike moment;  ensemble learning
分类号:
TP391
DOI:
10.3969/j.issn.1001-0505.2015.02.010
摘要:
为了充分利用人脸图像的局部信息、改善现有基于整体特征的彩色人脸识别算法的识别率,提出了一种基于局部特征和集成学习分类器的鲁棒彩色人脸识别算法.在特征提取阶段,使用自适应四元数pseudo-Zernike矩(AQPZMs)来描述图像子块的特征.对于具有较大熵的图像子块使用较高阶次的四元数pseudo-Zernike矩(QPZMs)提取特征,反之则使用较低阶次的QPZMs.在匹配识别阶段,使用集成学习分类器进行判别.针对不同彩色人脸图像库的测试结果表明,当人脸图像受到光照、表情等因素影响时,与采用QPZMs或者四元数二维主成分分析(Q2DPCA)进行整体特征提取的识别算法相比,所提算法的识别率更高.
Abstract:
To make full use of local information of face images and improve the recognition rate of the existing color face recognition algorithm based on global features, a robust color face recognition algorithm based on local features and ensemble learning classifier is proposed. In the feature extraction stage, the adaptive quaternion pseudo-Zernike moments(AQPZMs)are used to describe the features of image blocks. The features of image blocks with larger entropy are described by quaternion pseudo-Zernike moments(QPZMs)with higher order. On the contrary, the QPZMs with lower order are used to describe the features of image blocks with smaller entropy. In the classification stage, the ensemble learning classifier is used for identification. The experimental results of different color face datasets show that compared with the recognition algorithms exploiting QPZMs or quaternion two-dimensional principal component analysis(Q2DPCA)to extract global features, the proposed algorithm can achieve higher accuracy when the face images are affected by the factors such as illumination, facial expression and so on.

参考文献/References:

[1] Yang J, Zhang D, Frangi A F, et al. Two-dimensional PCA: a new approach to appearance-based face representation and recognition [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2004, 26(1): 131-137.
[2] Zuo W M, Zhang D, Wang K Q. Bidirectional PCA with assembled matrix distance metric for image recognition [J]. IEEE Transactions on Systems, Man and Cybernetics: Part B: Cybernetics, 2006, 36(4): 863-872.
[3] Gottumukkal R, Asari V K. An improved face recognition technique based on modular PCA approach [J]. Pattern Recognition Letters, 2004, 25(4): 429-436.
[4] Hsieh P C, Tung P C. A novel hybrid approach based on sub-pattern technique and whitened PCA for face recognition [J]. Pattern Recognition, 2009, 42(5): 978-984.
[5] Eftekhari A, Forouzanfar M, Abrishami M H, et al. Block-wise 2D kernel PCA/LDA for face recognition [J]. Information Processing Letters, 2010, 110(17): 761-766.
[6] Wang H X. Block principal component analysis with L1-norm for image analysis [J]. Pattern Recognition Letters, 2012, 33(5): 537-542.
[7] Cavalcanti G D C, Ren T I, Pereira J F. Weighted modular image principal component analysis for face recognition [J]. Expert Systems with Applications, 2013, 40(12): 4971-4977.
[8] Mashhoori A, Jahromi M Z. Block-wise two-directional 2DPCA with ensemble learning for face recognition [J]. Neurocomputing, 2013, 108: 111-117.
[9] Yan L, Pan J S, Chu S C, et al. Adaptively weighted sub-directional two-dimensional linear discriminant analysis for face recognition [J]. Future Generation Computer Systems, 2012, 28(1): 232-235.
[10] Kanan H R, Faez K, Gao Y. Face recognition using adaptively weighted patch PZM array from a single exemplar image per person [J]. Pattern Recognition, 2008, 41(12): 3799-3812.
[11] Sun Y, Chen S, Yin B. Color face recognition based on quaternion matrix representation [J]. Pattern Recognition Letters, 2011, 32(4): 597-605.
[12] Xu Y. Quaternion-based discriminant analysis method for color face recognition [J]. PloS ONE, 2012, 7(8): e43493-1-e43493-4.
[13] 陈北京, 孙星明, 王定成, 等. 基于彩色图像四元数表示的彩色人脸识别[J]. 自动化学报, 2012, 38(11): 1815-1823.
　　Chen Beijing, Sun Xingming, Wang Dingcheng, et al. Color face recognition using quaternion representation of color image [J]. Acta Automatica Sinica, 2012, 38(11): 1815-1823.(in Chinese)
[14] 2D face sets[EB/OL].[2014-08-25]. http://pics.stir.ac.uk/2D_face_sets.htm.
[15] Nefian A V. GT face database [EB/OL]. [2014-08-25]. http://www.anefian.com/research/face_reco.htm.

备注/Memo

备注/Memo:
收稿日期: 2014-10-15.
作者简介: 邵珠宏(1986—),男,博士生;舒华忠(联系人),男,博士,教授,博士生导师,shu.list@seu.edu.cn.
基金项目: 国家重点基础研究发展计划(973计划)资助项目(2011CB707904)、国家自然科学基金资助项目(61073138,6110314,61201344,61271312).
引用本文: 邵珠宏, 欧阳军林,廖帆,等.基于局部特征和集成学习的鲁棒彩色人脸识别算法[J].东南大学学报:自然科学版,2015,45(2):251-255. [doi:10.3969/j.issn.1001-0505.2015.02.010]
更新日期/Last Update: 2015-03-20