Curvature Prior for MRF-based Segmentation and Shape Inpainting

Details Curvature Prior for MRF-based Segmentation and Shape Inpainting Curvature Prior for MRF-based Segmentation and Shape Inpainting

2011-09-07

arxiv.org/abs/1109.1480v1

Computer Science

Computer Vision and Pattern Recognition

17 pages, 16 figures

Scientific paper

Most image labeling problems such as segmentation and image reconstruction are fundamentally ill-posed and suffer from ambiguities and noise. Higher order image priors encode high level structural dependencies between pixels and are key to overcoming these problems. However, these priors in general lead to computationally intractable models. This paper addresses the problem of discovering compact representations of higher order priors which allow efficient inference. We propose a framework for solving this problem which uses a recently proposed representation of higher order functions where they are encoded as lower envelopes of linear functions. Maximum a Posterior inference on our learned models reduces to minimizing a pairwise function of discrete variables, which can be done approximately using standard methods. Although this is a primarily theoretical paper, we also demonstrate the practical effectiveness of our framework on the problem of learning a shape prior for image segmentation and reconstruction. We show that our framework can learn a compact representation that approximates a prior that encourages low curvature shapes. We evaluate the approximation accuracy, discuss properties of the trained model, and show various results for shape inpainting and image segmentation.

Affiliated with

Also associated with

No associations

Rating

Curvature Prior for MRF-based Segmentation and Shape Inpainting does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Curvature Prior for MRF-based Segmentation and Shape Inpainting, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Curvature Prior for MRF-based Segmentation and Shape Inpainting will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-306499