Face image modeling by multilinear subspace analysis with missing values

The main difficulty in face image modeling is to decompose those semantic factors contributing to the formation of the face images, such as identity, illumination and pose. One promising way is to organize the face images in a higher-order tensor with each mode corresponding to one contributory factor. Then, a technique called Multilinear Subspace Analysis (MSA) is applied to decompose the tensor into the mode-n product of several mode matrices, each of which represents one semantic factor. In practice, however, it is usually difficult to obtain such a complete training tensor since it requires a large amount of face images with all possible combinations of the states of the contributory factors. To solve the problem, this paper proposes a method named M2 SA, which can work on the training tensor with massive missing values. Thus M2 SA can be used to model face images even when there are only a small number of face images with limited variations (which will cause missing values in t...

• Type: Conference
• Year: 2009
• Where: MM
• Authors: Xin Geng, Kate Smith-Miles, Zhi-Hua Zhou, Liang Wang
• Keywords: Face Images, Missing Values, MM 2009, Multimedia, Training Tensor