基于L1-范数的二维线性判别分析

陈思宝; 陈道然; 罗斌

doi:10.11999/JEIT141093

基于L1-范数的二维线性判别分析

doi: 10.11999/JEIT141093

基金项目:

国家自然科学基金(61202228)和安徽省高校自然科学研究重点项目(KJ2012A004)资助课题

计量
- 文章访问数: 2003
- HTML全文浏览量: 230
- PDF下载量: 897
- 被引次数: 0
出版历程
- 收稿日期: 2014-08-18
- 修回日期: 2015-02-04
- 刊出日期: 2015-06-19

L1-norm Based Two-dimensional Linear Discriminant Analysis

摘要

摘要: 为了避免图像数据向量化后的维数灾难问题，以及增强对野值(outliers)及噪声的鲁棒性，该文提出一种基于L1-范数的2维线性判别分析(L1-norm-based Two-Dimensional Linear Discriminant Analysis, 2DLDA-L1)降维方法。它充分利用L1-范数对野值及噪声的强鲁棒性，并且直接在图像矩阵上进行投影降维。该文还提出一种快速迭代优化算法，并给出了其单调收敛到局部最优的证明。在多个图像数据库上的实验验证了该方法的鲁棒性与高效性。
- 图像处理 /
- L1-范数 /
- 2维线性判别分析 /
- 线性投影 /
- 降维
Abstract: To overcome the curse of dimensionality caused by vectorization of image matrices, and to increase robustness to outliers, L1-norm based Two-Dimensional Linear Discriminant Analysis (2DLDA-L1) is proposed for dimensionality reduction. It makes full use of strong robustness of L1-norm to outliers and noises. Furthermore, it performs dimensionality reduction directly on image matrices. A rapid iterative optimization algorithm, with its proof of monotonic convergence to local optimum, is given. Experiments on several public image databases verify the robustness and the effectiveness of the proposed method.
- Image processing /
- L1-norm /
- Two-Dimensional Linear Discriminant Analysis (2DLDA) /
- Linear projection /
- Dimensionality reduction

HTML全文

参考文献(21)

Duda R, Hart P, and Stork D. Pattern Classification[M]. Second edition, New York: John Wiley Sons, 2001: 2-5.

Chan L, Salleh S, Ting C, et al.. Face identification and verification using PCA and LDA[C]. International Symposium on Information Technology, Kuala Lumpur, Malaysia, 2008: 1-6.

Rujirakul K, So-In C, Arnonkijpanich B, et al.. PFP-PCA: parallel fixed point PCA face recognition[C]. 2013 4th International Conference on Intelligent Systems, Modelling and Simulation, Bangkok, 2013: 29-31.

Belhumeur P, Hespanha J, and Kriegman D. Eigenfaces vs. fisherfaces: recognition using class specific linear projection[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1997, 19(7): 711-720.

Yang Jian, Zhang D, Frangi A, 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.

Wang Shi-min, Ye Ji-hua, and Ying De-quan. Research of 2DPCA principal component uncertainty in face recognition[C]. 2013 8th International Conference on Computer Science Education, Colombo, Sri Lanka, 2013: 159-162.

Li Ming and Yuan Bao-zong. A novel statistical linear discriminant analysis for image matrix: two-dimensional Fisherfaces[J]. Pattern Recognition Letters, 2005, 26(5): 527-532.

Mahanta M and Plataniotis K. Ranking 2DLDA features based on fisher discriminance[C]. IEEE International Conference on Acoustic, Speech and Signal Processing, Florence, Italy, 2014: 4-9.

Wang Bin-bin, Hao Xin-jie, Chen Li-sheng, et al.. Face recognition based on the feature fusion of 2DLDA and LBP[C]. 2013 Fourth International Conference on Information, Intelligence, Systems and Applications, Piraeus, Greece, 2013: 10-12.

Pang Yan-wei, Li Xue-long, and Yuan Yuan. Robust tensor analysis with L1-norm[J]. IEEE Transactions on Circuits Syst ems for Video Techology, 2010, 20(2): 172-178.

Zheng Wen-ming, Lin Zhou-chen, and Wang Hai-xian. L1-norm kernel discriminant analysis via Bayes error bound optimization for robust feature extraction[J]. IEEE Transactions on Neural Networks and Learning Systems, 2014, 25(4): 793-805.

Kwak N. Principal component analysis based on L1-norm maximization[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2008, 30(9): 1672-1680.

Li Xi, Hu Wei-ming, Wang Han-zi, et al.. Linear discriminant analysis using rotational invariant L1 norm[J]. Neurocomputing, 2010, 73(13): 2571-2579.

Wang Hai-xian, Lu Xue-song, Hu Zi-lan, et al.. Fisher discriminant analysis with L1-norm[J]. IEEE Transactions on Cybernetics, 2013, 44(6): 828-842.

Zhong Fu-jin and Zhang Jia-shu. Linear discriminant analysis based on L1-norm maximization[J]. IEEE Transactions on Image Processing, 2013, 22(8): 3018-3027.

Li Xue-long, Pang Yan-wei, and Yuan Yuan. L1-norm-based 2DPCA[J]. IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics, 2010, 40(4): 1170-1175.

Wang Hai-xian, Tang Qin, and Zheng Wen-ming. L1-norm- based common spatial patterns[J]. IEEE Transactions on Biomedical Engineering, 2012, 59(3): 653-662.

Jenatton R, Obozinski G, and Bach F. Structured sparse principal component analysis[C]. International Conference on Artificial Intelligence and Statistics, Paris, France, 2009: 1-8.

Gross R, Matthews I, Cohn J, et al.. Multi-PIE[C]. 8th IEEE International Conference on Automatic Face Gesture Recognition, Amsterdam, The Netherland, 2008: 1-8.

Martinez A and Benavente R. The AR face database[R]. CVC Technical Report 24, Barcelona, Spain, 1998.

Samaria F and Harter A. Parameterisation of a stochastic model for human face identification[C]. Proceedings of the Second IEEE Workshop on Applications of Computer Vision, Sarasota, USA, 1994, 138-142.

施引文献

资源附件(0)

访问统计