A new gaussian mixture conditional random field model for indoor image labeling

In this paper we present a new conditional random field (CRF) model based on Gaussian mixture potentials for indoor image labeling, which is useful in interactive room decoration system. Indoor images which posses many spatial regularities can be efficiently modeled by probabilistic graphical models such as CRF. The potential functions in CRF are usually set empirically and differently for different features depending on applications. We propose a new CRF model based on a general Gaussian mixture potential for different group of features, which has the advantage of labeling accuracy and training simplicity. The new model with belief propagation inference and stochastic gradient descent training is applied to floor region labeling of indoor images in Labelme database. Simulation results and visual effects prove our analysis. Comparing to other CRF models the new approach is more efficient for indoor image labeling tasks.