南京大学学报(自然科学版) ›› 2015, Vol. 51 ›› Issue (1): 118124.
管 睿,孙权森*,沈肖波
Guan Rui,Sun Quansen*,Shen Xiaobo
摘要: 随着数据处理方式以及描述角度的不同,同一模式总是能够获得多种不同的特征表示.由于这些特征表示总是反映了同一模式的不同特性或视角,因此,对其进行有效地抽取与融合后,不仅可以保留参与抽取的多组特征的有效鉴别信息,还可以在一定程度上消除特征间的冗余信息,降低识别算法的复杂度,对模式分类来说无疑具有重要的实际意义.由于传统的维数约减方法,如主成分分析(PCA)与线性鉴别分析(LDA),主要针对模式的一组特征进行处理,并不适合对多表示数据进行融合与特征抽取,因此,本文以多表示数据为研究对象,深入研究了多重集典型相关分析的相关理论与算法,采用分数阶思想对组内与组间样本协方差的特征值和奇异值进行重新估计,然后建立分数阶组内与组间散布矩阵,同时引入监督信息,构建了分数阶嵌入的多重集典型相关分析(FEGMCCA)理论框架.
[1] Camastra F, Vinciarelli A. Estimating the intrinsic dimension of data with a fractal-based method. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2002, 24(10): 1404~1407. [2] He X, Ji M, Zhang C, et al. A variance minimization criterion to feature selection using laplacian regularization. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33(10): 2013~2025. [3] Hou C, Zhang C, Wu Y, et al. Multiple view semi-supervised dimensionality reduction. Pattern Recog- nition, 2010, 43(3): 720~730. [4] Chen L F, Liao H M, Ko M T, et al. A new LDA-based face recognition system which can solve the small sample size problem. Pattern Recognition, 2000, 33(10): 1713~1726. [5] Yu H, Yang J. A direct LDA algorithm for high- dimensional data with application to face recognition. Pattern Recognition, 2001, 34(10): 2067~2070. [6] Shen X B, Sun Q S, Yuan Y H. A unified multiset canonical correlation analysis framework based on graph embedding for multiple feature extraction. Neurocomputing, 2014. [7] 孙权森.基于相关投影分析的特征抽取与图像识别研究.博士学位论文. 南京理工大学,2006. [8] Chu M T, Watterson L J. On a multivariate eigenvalue problem: I. Algebraic theory and power method. SIAM Journal on Scientific Computing, 1993, 14(5): 1089~ 1106. [9] 袁运浩. 多重集典型相关分析理论及在高维多表示数据中的应用. 博士学位论文. 南京理工大学,2013. [10] Yuan Y H, Sun Q S. Fractional-order embed -ding multiset canonical correlations with applications to feature fusion. Neurocomputing, 2013, 122: 229~238. [11] Yang J, Zhang D, Frangi A F, et al. Two-dimen- sional PCA: A new approach to appearance -based face representation and recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2004, 26(1): 131~137. [12] Shen X B, Sun Q S. Orthogonal multiset canonical correlation analysis based on fractional-order and its application in multiple feature extraction and recognition. Neural Processing Letters, 2014: 1~16. [13] Shen X B, Sun Q S, Yuan Y H. Orthogonal canonical correlation analysis and its application in feature fusion. IEEE 16th International Conference on Information Fusion (FUSION), 2013. [14] Yuan Y H, Sun Q S. Multiset canonical correlations using globality preserving projections with applications to feature extraction and recognition. IEEE Transactions on Neural Network and Learning System, 2014, 25(6): 1131~1146. [15] Shen X B, Sun Q S, Hong W G. Fractional-order embedding canonical correlation analysis and its applications to multi-view dimensionality reduction and recognition. Pattern Recognition, 2014, 47(3): 1411~1424. [16] 孙权森, 曾生根, 杨茂龙等. 基于典型相关分析的组合特征抽取及脸像鉴别. 计算机研究与发展, 2005, 42(4): 614~621. |
No related articles found! |
|