Summary: Facial Expression Decomposition
Hongcheng Wang, Narendra Ahuja
Beckman Institute, University of Illinois at Urbana­Champaign
{wanghc,ahuja}@vision.ai.uiuc.edu
Abstract
In this paper, we propose a novel approach for facial
expression decomposition ­ Higher­Order Singular Value
Decomposition (HOSVD), a natural generalization of
matrix SVD. We learn the expression subspace and person
subspace from a corpus of images showing seven basic
facial expressions, rather than resort to expert­coded facial
expression parameters as in [3]. We propose a simulta­
neous face and facial expression recognition algorithm,
which can classify the given image into one of the seven
basic facial expression categories, and then other facial
expressions of the new person can be synthesized using the
learned expression subspace model. The contributions of
this work lie mainly in two aspects. First, we propose a new
HOSVD based approach to model the mapping between
persons and expressions, used for facial expression synthe­

Source: Ahuja, Narendra - Department of Electrical and Computer Engineering, University of Illinois at Urbana-Champaign

Collections: Computer Technologies and Information Sciences; Engineering