Learning to Parse Images
Geoffrey Hinton, Zoubin Ghahramani and Yee Whye Teh
Gatsby Computational Neuroscience Unit
University College London
In Advances in Neural Information Processing Systems 12 MIT
Press, Cambridge, MA, 2000.
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 or pdf