零空间保局判别本征脸

楼宋江; 张国印

doi:10.3724/SP.J.1146.2010.00787

零空间保局判别本征脸

doi: 10.3724/SP.J.1146.2010.00787

楼宋江^{* 张国印,},
张国印

计量
- 文章访问数: 3641
- HTML全文浏览量: 170
- PDF下载量: 968
- 被引次数: 0
出版历程
- 收稿日期: 2010-07-28
- 修回日期: 2010-10-25
- 刊出日期: 2011-04-19

Null Space Locality Preserving Discriminant Intrinsicface

Lou Song-Jiang^{* 张国印
,},
Zhang Guo-Yin

摘要

摘要: 本征脸从人脸自身的差别出发，将每一人脸分为脸部共同差别、个体类间差别和个体类内差别，取得了较好的识别效果。但是它未考虑人脸的流形结构，并且会遇到矩阵的奇异性，即小样本问题。针对这些问题，该文提出了零空间保局判别本征脸，该算法充分考虑了个体类内差别和个体类间差别，结合流形学习思想并借助于判别准则使得投影后个体类内之间保持一定的相似性而个体类间之间的区分度有所增加。通过在个体类内保局差异散度矩阵的零空间中求最优特征向量，避免了矩阵的奇异性问题，解决了小样本问题。在人脸识别上的实验验证了算法的正确性和有效性。
- 人脸识别 /
- 本征脸 /
- 保局算法 /
- 小样本问题 /
- 零空间
Abstract: Based on the image differences, Intrinsicface is proposed, which divides the face image into three parts, common facial differences, intrapersonal differences and individual differences, and shows desirable performance. But it does not consider the manifold structure and suffers from the singular problem, which is also called Small Sample Size (SSS) problem. To solve these problems, Null Space Locality Preserving Discriminant Intrinsicface (NSLPDI) is proposed, which makes full use of intrapersonal differences and individual differences and employs the idea of manifold learning so that the similarity in the intra-class is preserved while the separability of samples from different classes is enlarged by discriminant criterion. The optimal feature vectors are extracted from the null space of intrapersonal locality preserving difference scatter matrix, which avoids the singularity and the SSS problem is solved. Experiments on face recognition demonstrate the correctness and effectiveness of the proposed algorithm.
- Face recognition /
- Intrinsicface /
- Locality preserving projection /
- Small Sample Size (SSS) problem /
- Null space

HTML全文

参考文献(1)

Turk M and Pentland A. Eigenfaces for recognition[J].Cognitive Neurosci.1991, 3(1):71-86[2]Belhumeur P N and Kriegman D J. Eigenfaces vs fisherfaces: recognition using class specific linear projection [J].IEEE Transactions on Pattern Analysis and Machine Intelligence.1997, 19:711-720[3]Tenenbaum J B, De Silva V, and Langford J C. A global geometric framework for nonlinear dimensionality reduction [J].Science.2000, 290:2319-2323[4]Rowies S and Saul L. Nonliear dimensionality reduction by locally linear embedding[J].Science.2000, 290:2323-2326[5]Belkin M and Niyogo P. Laplacian eigenmaps for dimensionality reduction and data representation[J].Neural Computation.2003, 15(6):1373-1396[6]He X, Niyogi P, and Han J. Face recognition using laplacianfaces[J].IEEE Transactions on Pattern Analysis and Machine Intelligence.2005, 27(3):328-340[8]Yang J, Zhang D, and Yang J Y, et al.. Globally maximizing, locally minimizing: unsupervised discriminant projection with application to face and palm biometrics[J].IEEE Transactions on Pattern Analysis and Machine Intelligence.2007, 29(4):650-664[11]Gao Quan-xue, Xu Hui, Li Yi-ying, and Xie De-yan. Two dimensional supervised local similarity and diversity projections[J].Pattern Recognition.2010, 43(10):3359-3363[12]Li Bo, Wang Chao, and Huang De-shuang. Supervised feature extraction based on orthogonal discriminant projection [J].Neurocomputing.2009, 73(1-3):191-196[14]Yang Li-ping, Gong Wei-guo, and Gu Xiao-hua, et al.. Null space discriminant locality preserving projections for face recognition[J].Neurocomputing.2008, 71(16-18):3644-3649[15]林玉娥, 顾国昌等. 适用于小样本问题的具有类内保持的正交特征提取算法[J]. 自动化学报. 2010, 36(5): 644-649.[16]Lin Yu-e and Gu Guo-chang, et al.. An Orthogonal feature extraction method based on the within-class preserving for small sample size problem[J].Acta Automatica Sinica.2010, 36(5):644-649[17]Xu Yong, Zhong Ai-ni, Yang Jian, and Zhang David. LPP solution schemes for use with face recognition[J].Pattern Recognition.2010, 43(12):4165-4176[19]Yang Li-ping, Gong Wei-guo, Gu Xiao-hua, Li Wei-hong, and Du Xing. Complete discriminant locality preserving projections for face recognition[J].Journal of Software.2010, 21(6):1277-1286[20]Hong Z Q and Yang J Y. Optimal discriminant plane for a small number of samples and design method of classifier on the plane [J].Pattern Recognition.1991, 24(4):317-324[21]Li H, Jiang T, and Zhang K. Efficient and robust feature extraction by maximum margin criterion[J].IEEE Transactions on Neural Networks.2006, 17(1):157-165[22]Tao Yu-ting and Yang Jian. Quotient vsdifference: comparison between the two discriminant criteria [J].. Neurocomputing.2010, 73(10-12):1808-1817[23]Yu Hua, Yang Jie. A direct LDA algorithm for high-dimensional data- with application to face recognition [J].Pattern Recognition.2001, 34(10):2067-2070

施引文献

资源附件(0)

访问统计