Title :
Matrix-Variate Factor Analysis and Its Applications
Author :
Xie, Xianchao ; Yan, Shuicheng ; Kwok, James T. ; Huang, Thomas S.
Author_Institution :
Dept. of Stat., Harvard Univ. Sci. Center, Cambridge, MA
Abstract :
Factor analysis (FA) seeks to reveal the relationship between an observed vector variable and a latent variable of reduced dimension. It has been widely used in many applications involving high-dimensional data, such as image representation and face recognition. An intrinsic limitation of FA lies in its potentially poor performance when the data dimension is high, a problem known as curse of dimensionality. Motivated by the fact that images are inherently matrices, we develop, in this brief, an FA model for matrix-variate variables and present an efficient parameter estimation algorithm. Experiments on both toy and real-world image data demonstrate that the proposed matrix-variant FA model is more efficient and accurate than the classical FA approach, especially when the observed variable is high-dimensional and the samples available are limited.
Keywords :
face recognition; image representation; matrix algebra; statistical analysis; canonical statistical method; face recognition; high-dimensional data; image representation; matrix-variate factor analysis; observed vector variable; real-world image data; toy image data; Conditional expectation maximization (EM); face recognition; factor analysis (FA); matrix; Artificial Intelligence; Biometry; Face; Factor Analysis, Statistical; Humans; Image Interpretation, Computer-Assisted; Multivariate Analysis; Pattern Recognition, Automated;
Journal_Title :
Neural Networks, IEEE Transactions on
DOI :
10.1109/TNN.2008.2004963