Layered image model using binary PCA transparency masks
Zoran Živković · 2007
The ”layered image model ” [13] represents an image sequence as a composition of 2D layers where each layer corresponds to a different object. A layer is described by its appearance and its transparency mask. The transparency masks are used to combine the layers. In this paper we present a probabilistic layered model that uses the ”logistic principal component analysis (PCA) ” to describe the masks. The Gaussian based factor analysis was used previously but it does not consider the constraints imposed on the transparency values. The ”logistic PCA ” models the transparency values that are between 0 and 1 more naturally using Bernoulli distributions. The presented model can be used to automatically extract low dimensional representation of the transparency maps of the moving objects from a video sequences more efficiently. 1