Abstract

This paper considers the dynamic tree (DT) model, first in- troduced in [1]. A dynamic tree specifies a prior over structures of trees, each of which is a forest of one or more tree-structured belief networks (TSBN). In the literature standard tree-structured belief network mod- els have been found to produce “blocky” segmentations when naturally occurring boundaries within an image did not coincide with those of the subtrees in the fixed structure of the network. Dynamic trees have a fiex- ible architecture which allows the structure to vary to create configura- tions where the subtree and image boundaries align, and experimentation with the model has shown significant improvements. Here we derive an EM-style update based upon mean field inference for learning the parameters of the dynamic tree model and apply it to a database of images of outdoor scenes where all of its parameters are learned. DTs are seen to offer significant improvement in perfor- mance over the fixed-architecture TSBN and in a coding comparison the DT achieves 0.294 bits per pixel (bpp) compression compared to 0.378 bpp for lossless JPEG on images of 7 colours.