In this paper we explore the utility of nonlinear dimensionality reduction techniques in the realm of facial expression analysis. First, we test the ability of nonlinear techniques to describe the higher nonlinear nature of human facial expressions. We exploit the data-driven model of an embedding to create novel facial expressions. Finally, we composite the facial expressions back on the face.

i

vii List of Figures xiii

The ever-growing amount of data stored in digital databases raises the question of how to organize and extract useful knowledge. This paper outlines some current developments in the domains of dimensionality reduction, manifold learning, and topological learning. Several aspects are dealt with, ranging from novel algorithmic approaches to their realworld applications. The issue of quality asses...

LLE(Local linear embedding) is a widely used approach for dimension reduction. The neighborhood selection is an important issue for LLE. In this paper, the ε-distance approach and a slightly modified version of k-nn method are introduced. For different types of datasets, different approaches are needed in order to enjoy higher chance to obtain better representation. For some datasets with compl...

Abstract As basic research, it has also received increasing attention from people that the “curse of dimensionality” will lead to increase cost data storage and computing; influences efficiency accuracy dealing with problems. Feature dimensionality reduction as a key link in process pattern recognition become one hot difficulty spot field recognition, machine learning mining. It is most challen...