Abstract
We describe a class of graphical models we call credibility networks
for image interpretation. Using parse trees as internal representations of images,
credibility networks are able to perform segmentation and recognition simultaneously,
removing the need for handcrafted ad hoc segmentation heuristics. Promising results
in the problem of segmenting handwritten digits were obtained.
Download: ps.gz or pdf
In Advances in Neural Information Processing Systems 12 MIT
Press, Cambridge, MA, 2000.
[home page] [publications]