Learning to Parse Images

We describe a class of probabilistic models that we call credibility networks. Using parse trees as internal representations of images, credibility networks are able to perform segmentation and recog(cid: 173) nition simultaneously, removing the need for ad hoc segmentation heuristics. Promising results in the problem of segmenting hand(cid: 173) written digits were obtained. 1

Authors

• Geoffrey Hinton
• Zoubin Ghahramani
• Yee Whye Teh

Keywords

No keywords are indexed for this paper.