home page
people
research
publications
seminars
travel
search
UCL
Learning to Parse Images
Geoffrey Hinton, Zoubin Ghahramani
and Yee Whye Teh
Gatsby Computational Neuroscience Unit
University College London
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.
In Advances in Neural Information Processing Systems 12 MIT Press, Cambridge, MA, 2000.