Image Parsing: Unifying Segmentation, Detection, and Recognition

DMCA

Image Parsing: Unifying Segmentation, Detection, and Recognition (2005)

Cached

Download Links

Other Repositories/Bibliography

by Zhuowen Tu , Xiangrong Chen , Alan L. Yuille , Song-Chun Zhu

Citations:

233 - 22 self

BibTeX

@MISC{Tu05imageparsing:,
    author = {Zhuowen Tu and Xiangrong Chen and Alan L. Yuille and Song-Chun Zhu},
    title = {Image Parsing: Unifying Segmentation, Detection, and Recognition},
    year = {2005}
}

OpenURL

Abstract

In this paper we present a Bayesian framework for parsing images into their constituent visual patterns. The parsing algorithm optimizes the posterior probability and outputs a scene representation in a "parsing graph", in a spirit similar to parsing sentences in speech and natural language. The algorithm constructs the parsing graph and re-configures it dynamically using a set of reversible Markov chain jumps. This computational framework integrates two popular inference approaches -- generative (top-down) methods and discriminative (bottom-up) methods. The former formulates the posterior probability in terms of generative models for images defined by likelihood functions and priors. The latter computes discriminative probabilities based on a sequence (cascade) of bottom-up tests/filters.

Keyphrases

unifying segmentation parsing graph posterior probability computational framework integrates constituent visual pattern reversible markov chain jump bottom-up test filter popular inference approach natural language generative model latter computes discriminative probability bayesian framework scene representation likelihood function

DMCA