Image Segmentation by Data Driven Markov Chain Monte Carlo

DMCA

Image Segmentation by Data Driven Markov Chain Monte Carlo (2001)

Cached

Download Links

Other Repositories/Bibliography

DBLP

by Zhuowen Tu , Song-Chun Zhu , Heung-yeung Shum

Citations:

277 - 32 self

BibTeX

@MISC{Tu01imagesegmentation,
    author = {Zhuowen Tu and Song-Chun Zhu and Heung-yeung Shum},
    title = {Image Segmentation by Data Driven Markov Chain Monte Carlo},
    year = {2001}
}

OpenURL

Abstract

This paper presents a computational paradigm called Data Driven Markov Chain Monte Carlo (DDMCMC) for image segmentation in the Bayesian statistical framework. The paper contributes to image segmentation in three aspects. Firstly, it designs effective and well balanced Markov Chain dynamics to explore the solution space and makes the split and merge process reversible at a middle level vision formulation. Thus it achieves globally optimal solution independent of initial segmentations. Secondly, instead of computing a single maximum a posteriori solution, it proposes a mathematical principle for computing multiple distinct solutions to incorporates intrinsic ambiguities in image segmentation. A k-adventurers algorithm is proposed for extracting distinct multiple solutions from the Markov chain sequence. Thirdly, it utilizes datadriven (bottom-up) techniques, such as clustering and edge detection, to compute importance proposal probabilities, which eectively drive the Markov chain dynamics and achieve tremendous speedup in comparison to traditional jump-diffusion method[4]. Thus DDMCMC paradigm provides a unifying framework where the role of existing segmentation algorithms, such as, edge detection, clustering, region growing, split-merge, SNAKEs, region competition, are revealed as either realizing Markov chain dynamics or computing importance proposal probabilities. We report some results on color and grey level image segmentation in this paper and refer to a detailed report and a web site for extensive discussion.

Keyphrases

image segmentation importance proposal probability edge detection markov chain dynamic traditional jump-diffusion method extensive discussion tremendous speedup web site markov chain sequence k-adventurers algorithm region competition posteriori solution middle level vision formulation merge process reversible segmentation algorithm bayesian statistical framework region growing balanced markov chain dynamic mathematical principle computational paradigm single maximum distinct multiple solution solution space detailed report multiple distinct solution grey level image segmentation incorporates intrinsic ambiguity initial segmentation thus ddmcmc paradigm optimal solution unifying framework

DMCA