Combining neural networks and belief networks for image segmentation

In this paper we are concerned with segmenting an image into a number of predefined classes. We show how to fuse together local predictions for the class labels with a prior model of segmentations using the scaled-likelihood method. The prior model is based on a tree-structured belief network. Both the neural network and belief network were trained on a set of training images, and then the combined system was used to make predictions on a set of test images. We show that the combined neural network/belief network classifier gives improved prediction accuracy on 9 out of the 11 classes.